diff --git a/.gitattributes b/.gitattributes deleted file mode 100644 index a6344aac8c09253b3b630fb776ae94478aa0275b..0000000000000000000000000000000000000000 --- a/.gitattributes +++ /dev/null @@ -1,35 +0,0 @@ -*.7z filter=lfs diff=lfs merge=lfs -text -*.arrow filter=lfs diff=lfs merge=lfs -text -*.bin filter=lfs diff=lfs merge=lfs -text -*.bz2 filter=lfs diff=lfs merge=lfs -text -*.ckpt filter=lfs diff=lfs merge=lfs -text -*.ftz filter=lfs diff=lfs merge=lfs -text -*.gz filter=lfs diff=lfs merge=lfs -text -*.h5 filter=lfs diff=lfs merge=lfs -text -*.joblib filter=lfs diff=lfs merge=lfs -text -*.lfs.* filter=lfs diff=lfs merge=lfs -text -*.mlmodel filter=lfs diff=lfs merge=lfs -text -*.model filter=lfs diff=lfs merge=lfs -text -*.msgpack filter=lfs diff=lfs merge=lfs -text -*.npy filter=lfs diff=lfs merge=lfs -text -*.npz filter=lfs diff=lfs merge=lfs -text -*.onnx filter=lfs diff=lfs merge=lfs -text -*.ot filter=lfs diff=lfs merge=lfs -text -*.parquet filter=lfs diff=lfs merge=lfs -text -*.pb filter=lfs diff=lfs merge=lfs -text -*.pickle filter=lfs diff=lfs merge=lfs -text -*.pkl filter=lfs diff=lfs merge=lfs -text -*.pt filter=lfs diff=lfs merge=lfs -text -*.pth filter=lfs diff=lfs merge=lfs -text -*.rar filter=lfs diff=lfs merge=lfs -text -*.safetensors filter=lfs diff=lfs merge=lfs -text -saved_model/**/* filter=lfs diff=lfs merge=lfs -text -*.tar.* filter=lfs diff=lfs merge=lfs -text -*.tar filter=lfs diff=lfs merge=lfs -text -*.tflite filter=lfs diff=lfs merge=lfs -text -*.tgz filter=lfs diff=lfs merge=lfs -text -*.wasm filter=lfs diff=lfs merge=lfs -text -*.xz filter=lfs diff=lfs merge=lfs -text -*.zip filter=lfs diff=lfs merge=lfs -text -*.zst filter=lfs diff=lfs merge=lfs -text -*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index e5f53057fe1f25623d537f70bd20053843244099..ae712f7324944d6b7c232be26d294e72c7031d46 100644 --- a/README.md +++ b/README.md @@ -1,13 +1,33 @@ --- title: MODUS -emoji: 💻 -colorFrom: purple +emoji: 🎨 +colorFrom: indigo colorTo: purple sdk: gradio -sdk_version: 6.19.0 -python_version: '3.13' +sdk_version: 4.44.1 app_file: app.py pinned: false +short_description: MODUS any-to-any multimodal demo (16 aligned modalities) --- -Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference +# MODUS — any-to-any multimodal demo + +Three-tab Gradio demo for the MODUS 16-modality any-to-any model: + +1. **Any-to-Any** — one condition modality (image or caption) → any set of target + modalities, shown in a gallery (4M-style). +2. **Chained** — condition → intermediate (bridge) → target, showing both. +3. **Representation Analysis** — RGB→Depth/Normal conditioned on + {ViT only, VAE only, ViT+VAE}, side by side. + +## Setup (Space Settings → Variables and secrets) +- **Hardware:** ZeroGPU. +- **`HF_TOKEN`** (secret): a *read* token with access to the gated weights repo + `mqye/modus-16mod-stage3`. +- Optional **`MODUS_WEIGHTS_REPO`**: defaults to `mqye/modus-16mod-stage3`. + +The weights (bf16, ~30GB) + VAE + config + tokenizer are pulled once at startup +via `snapshot_download`; the model is built on CPU (~5min) and moved to the +ZeroGPU GPU per request. Inference config is baked in: modality config +`conf/modalities/instruction_16mod_stage2.yaml`, `use_instruction` off for the +generic modalities (seg/det/grounding keep their own instructions). diff --git a/app.py b/app.py new file mode 100644 index 0000000000000000000000000000000000000000..6d88a15e92374b4ae48bd100da67ccd732ad71c3 --- /dev/null +++ b/app.py @@ -0,0 +1,116 @@ +#!/usr/bin/env python3 +"""MODUS any-to-any demo — HuggingFace Space entrypoint (ZeroGPU). + +Thin ZeroGPU wrapper over the existing 3-tab demo backend (``demo_modus.py`` + +``demo_my/*``). The model is loaded ONCE at startup on CPU (no GPU, no time +limit); each inference call moves it to the ZeroGPU-provided GPU via the +``@spaces.GPU`` decorator (moving ~30GB bf16 over PCIe is seconds, whereas the +build+weight-load is ~5min and must NOT happen inside the GPU-time window). + +Space setup (Settings -> Variables and secrets): + HF_TOKEN read token for the gated weights repo (below) +Optional env (have sane defaults): + MODUS_WEIGHTS_REPO gated HF model repo with the bf16 weights + config + VAE +""" +import os +import sys + +try: + import torch + print(f"[app] torch={torch.__version__} python={sys.version.split()[0]}", flush=True) +except Exception as _e: + print(f"[app] torch import failed: {_e}", flush=True) + +# ── Env MUST be set before importing the demo backend (it reads these at import) ─ +os.environ.setdefault("MODUS_NO_MEAN_RESIZING", "1") # avoid gradio-BLAS deadlock +os.environ.setdefault("MODUS_FORCE_SDPA_ATTN", "1") # no flash-attn on the Space +os.environ.setdefault("MODUS_DEMO_MODALITY_CONFIG", + "conf/modalities/instruction_16mod_stage2.yaml") +os.environ.setdefault("MODUS_DEMO_MODEL_NAME", "bagel_from_json") +os.environ.setdefault("MODUS_DEMO_USE_EMA", "0") + +WEIGHTS_REPO = os.environ.get("MODUS_WEIGHTS_REPO", "mqye/modus-16mod-stage3") + +# ── Pull the gated weights once (model.safetensors + ae + config + tokenizer) ──── +from huggingface_hub import snapshot_download # noqa: E402 + +_weights_dir = snapshot_download( + repo_id=WEIGHTS_REPO, + repo_type="model", + token=os.environ.get("HF_TOKEN"), +) +# The snapshot dir holds BOTH the checkpoint (model.safetensors) and the base +# config/tokenizer/VAE, so it serves as CHECKPOINT_PATH and MODEL_PATH at once. +os.environ["MODUS_DEMO_CHECKPOINT"] = _weights_dir +os.environ["BAGEL_MODEL_PATH"] = _weights_dir +print(f"[app] weights ready at {_weights_dir}", flush=True) + +import spaces # noqa: E402 (ZeroGPU) + +# diffusers 0.20 (imported by the fourm VQVAE feature tokenizers) does +# `from huggingface_hub import cached_download`, which was removed in hub>=0.26 +# (the Space has 0.36). Shim it to hf_hub_download so `import diffusers` succeeds +# and the dino/clip/imagebind tokenizers can load. +import huggingface_hub as _hh # noqa: E402 +if not hasattr(_hh, "cached_download"): + _hh.cached_download = _hh.hf_hub_download + +# Importing demo_modus builds the UI + backend and reads the env set above. +import demo_modus # noqa: E402 + + +# ── ZeroGPU: wrap the two inference entry points so each call gets a GPU slice ─── +# tab1/tab2 call demo_modus.run_task; tab3 calls demo_modus.run_representation_task. +# The tab handlers resolve these by module-global name at call time, so replacing +# the module attribute makes them use the GPU-wrapped versions. +# duration = max GPU-seconds ZeroGPU reserves per call. The Chained tab runs TWO +# generations inside a single run_task call (~60s+), so 60 is too tight ("GPU task +# aborted"); 120 covers chained + cold-start model materialisation. (With PRO the +# reservation size is a non-issue quota-wise.) +_GPU_DURATION = int(os.environ.get("MODUS_GPU_DURATION", "120")) +demo_modus.run_task = spaces.GPU(duration=_GPU_DURATION)(demo_modus.run_task) +# Tab3 runs THREE generations (vit/vae/both) per click. Wrapping run_representation_task +# would take three separate GPU acquisitions in one handler → the 3rd hits "Expired +# ZeroGPU proxy token". Instead wrap the whole tab3 HANDLER so all three run inside a +# single GPU session (one token, one reservation big enough for 3 gens). +demo_modus.tab3_generate = spaces.GPU(duration=180)(demo_modus.tab3_generate) + +# Load the model ONCE at startup. The heavy CPU work (build arch + read 30GB +# weights, ~5min) runs here, OUTSIDE any @spaces.GPU window; the model's .cuda() +# moves are deferred by `spaces` and materialise on the first GPU call. +try: + demo_modus.HOLDER.ensure_loaded() + print("[app] model loaded (CPU) at startup", flush=True) +except Exception as e: # surface in UI, retry lazily on first request + demo_modus.HOLDER.load_error = str(e) + print(f"[app] startup model load failed: {e}", flush=True) + +# Work around a gradio 4.44.1 bug: get_api_info() (called when rendering the main +# "/" route) crashes with `TypeError: argument of type 'bool' is not iterable` when +# a component's JSON schema contains a bool (additionalProperties: true/false). +# Patch gradio_client's schema helpers to tolerate bool schemas. +try: + import gradio_client.utils as _gcu + + _orig_j2p = _gcu._json_schema_to_python_type + + def _safe_j2p(schema, defs=None): + if isinstance(schema, bool): + return "Any" + return _orig_j2p(schema, defs) + + _gcu._json_schema_to_python_type = _safe_j2p + + _orig_get_type = _gcu.get_type + + def _safe_get_type(schema): + if isinstance(schema, bool): + return "Any" + return _orig_get_type(schema) + + _gcu.get_type = _safe_get_type +except Exception as _e: + print(f"[app] gradio_client schema patch skipped: {_e}", flush=True) + +demo = demo_modus.build_ui() +demo.queue().launch(server_name="0.0.0.0", server_port=7860, show_api=False) diff --git a/conf/modalities/bagel_stage3_exact3cond.yaml b/conf/modalities/bagel_stage3_exact3cond.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f98f8ae4522a335acf3ab97ea26725806f8e59ff --- /dev/null +++ b/conf/modalities/bagel_stage3_exact3cond.yaml @@ -0,0 +1,191 @@ +# Stage 3 modality config for the standalone BAGEL exact-3-condition project. +# Intentionally duplicated from instruction_stage2.yaml so this project can +# evolve independently without affecting MODUS experiments. + +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + pos_embed_size: 4 + apply_pos_embed_in_forward: true + pos_embed_name: grounding + loss: + reweight: true + reweight_min_w: 0.005 + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + codebook_spatial_shape: [32, 32] + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + codebook_spatial_shape: [28, 28] + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + codebook_spatial_shape: [32, 32] + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 diff --git a/conf/modalities/hunyuan_image_3.yaml b/conf/modalities/hunyuan_image_3.yaml new file mode 100644 index 0000000000000000000000000000000000000000..395f6ac5d5af6fd8f5e6fe5fa8aa6e8b6e4e95da --- /dev/null +++ b/conf/modalities/hunyuan_image_3.yaml @@ -0,0 +1,31 @@ +# Modality configuration for HunyuanImage-3.0 training. +# +# Only the RGB image modality is needed for text-to-image generation. +# Token keys (start_of_image / end_of_image) are populated by +# data_utils.add_special_tokens(), which adds <|vision_start|> and +# <|vision_end|> to the tokenizer when they are absent. +# These serve as sequence delimiters; actual image patches are placed at +# packed_vae_token_indexes and overwritten by the model's patch_embed. + +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vae: true + represent_vit: true diff --git a/conf/modalities/instruction.yaml b/conf/modalities/instruction.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6e200d0ec94d4acfdbf081cecc3e72be89bb6bc5 --- /dev/null +++ b/conf/modalities/instruction.yaml @@ -0,0 +1,201 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb, grounding, dino, dinolocal, clip, imagebind, imagebindlocal] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, grounding, dino, dinolocal, clip, imagebind, imagebindlocal] + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + pos_embed_size: 4 + apply_pos_embed_in_forward: true + pos_embed_name: grounding # checkpoint compat: attr is "grounding_pos_embed" + conditions: [rgb] + loss: + reweight: true + reweight_min_w: 0.005 + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [28, 28] # 784 tokens, 28×28 grid → 2D RoPE + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 diff --git a/conf/modalities/instruction_10modality_stage2.yaml b/conf/modalities/instruction_10modality_stage2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0803edc6b4b728792d357156fbad8e9989ef44cc --- /dev/null +++ b/conf/modalities/instruction_10modality_stage2.yaml @@ -0,0 +1,142 @@ +# Stage 2 modality config — unconstrained conditions. +# +# Same modality definitions as instruction.yaml, but with ALL condition +# restrictions removed so every modality can be conditioned on every other. + +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + # conditions: unconstrained (any modality can condition caption) + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + # conditions: unconstrained + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + pos_embed_size: 4 + apply_pos_embed_in_forward: true + pos_embed_name: grounding # checkpoint compat: attr is "grounding_pos_embed" + # conditions: unconstrained + loss: + reweight: true + reweight_min_w: 0.005 + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + # conditions: unconstrained + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + # conditions: unconstrained + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + diff --git a/conf/modalities/instruction_16mod_instr.yaml b/conf/modalities/instruction_16mod_instr.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b468f77ac60e49ae369e52b0ef39be1e995526c2 --- /dev/null +++ b/conf/modalities/instruction_16mod_instr.yaml @@ -0,0 +1,259 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: depth + id: 3 + kind: image + start_token_key: start_of_depth # REPLACE: per-modality start (token already exists in base vocab) + start_token: "<|depth_start|>" + end_token_key: end_of_image # shared end (image end is a structural terminator) + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_normal # REPLACE: per-modality start (token already exists in base vocab) + start_token: "<|normal_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + # NOTE: det's learnable pos_embed (grounding_pos_embed, size 4) is REMOVED here. + # The forward pos_embed loop is keyed by token-id range, and cocodet reuses + # det's x1/y1/x2/y2 tokens; with the pos_embed on, a multi-box cocodet sample + # (>4 coord tokens) would index the size-4 embedding out of bounds. det is not + # trained in modus (only present for coord-token-id alignment), so dropping its + # pos_embed is safe. reweight also removed (no reweight for det/cocodet). + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_seg # REPLACE: per-modality start (NEW token) + start_token: "<|seg_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_canny # REPLACE: per-modality start (NEW token) + start_token: "<|canny_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [28, 28] # 784 tokens, 28×28 grid → 2D RoPE + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + # ── NEW: cocodet (Pix2seq detection). stage1 = rgb→cocodet only. + # Coords reuse det's x1/y1/x2/y2 tokens (dedup, 0 new); class = COCO-id-aligned + # tokens (~91 new). dispersed_code_tokens → CE is gathered over the + # non-contiguous {coords ∪ class ∪ end} set, not a contiguous range. + # No reweight, no learnable pos_embed (RoPE + token-id carry order/role). + - name: cocodet + id: 13 + kind: codebook + start_token_key: start_of_cocodet + end_token_key: end_of_cocodet + start_token: "<|cocodet_start|>" + end_token: "<|cocodet_end|>" + represent_vae: true + dispersed_code_tokens: true + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|coco_cls_{i:02d}|>" + start: 0 + end: 90 + # Inference pipeline config. + # decode_method is 'cocodet' (NOT 'detection') — cocodet's output is + # coords+class per box ending on cocodet_end, a DIFFERENT format from the + # grounding/det coords-only decode (generate_detection_coordonly). Handled by + # the dedicated model.generate_cocodet + inferencer.gen_cocodet (which do NOT + # touch the grounding decode). + inference_decode_method: cocodet + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false + + # ── NEW image modalities (stage2): SAM segmentation / edge. Mirror seg/canny + # (direct-PNG image, VIT+VAE, MSE). REPLACE: per-modality start token, shared + # end_of_image. These start tokens are NEW (created via start_token field). + - name: samseg + id: 14 + kind: image + start_token_key: start_of_samseg + start_token: "<|samseg_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: samedge + id: 15 + kind: image + start_token_key: start_of_samedge + start_token: "<|samedge_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true diff --git a/conf/modalities/instruction_16mod_stage1.yaml b/conf/modalities/instruction_16mod_stage1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bae29aee53ced0d6ba4f6b1cb2b55f9890659818 --- /dev/null +++ b/conf/modalities/instruction_16mod_stage1.yaml @@ -0,0 +1,243 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb, grounding, dino, dinolocal, clip, imagebind, imagebindlocal] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, grounding, dino, dinolocal, clip, imagebind, imagebindlocal] + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + # NOTE: det's learnable pos_embed (grounding_pos_embed, size 4) is REMOVED here. + # The forward pos_embed loop is keyed by token-id range, and cocodet reuses + # det's x1/y1/x2/y2 tokens; with the pos_embed on, a multi-box cocodet sample + # (>4 coord tokens) would index the size-4 embedding out of bounds. det is not + # trained in modus (only present for coord-token-id alignment), so dropping its + # pos_embed is safe. reweight also removed (no reweight for det/cocodet). + conditions: [rgb] + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [28, 28] # 784 tokens, 28×28 grid → 2D RoPE + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + # ── NEW: cocodet (Pix2seq detection). stage1 = rgb→cocodet only. + # Coords reuse det's x1/y1/x2/y2 tokens (dedup, 0 new); class = COCO-id-aligned + # tokens (~91 new). dispersed_code_tokens → CE is gathered over the + # non-contiguous {coords ∪ class ∪ end} set, not a contiguous range. + # No reweight, no learnable pos_embed (RoPE + token-id carry order/role). + - name: cocodet + id: 13 + kind: codebook + start_token_key: start_of_cocodet + end_token_key: end_of_cocodet + start_token: "<|cocodet_start|>" + end_token: "<|cocodet_end|>" + represent_vae: true + conditions: [rgb] + dispersed_code_tokens: true + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|coco_cls_{i:02d}|>" + start: 0 + end: 90 + # Inference pipeline config. + # decode_method is 'cocodet' (NOT 'detection') — cocodet's output is + # coords+class per box ending on cocodet_end, a DIFFERENT format from the + # grounding/det coords-only decode (generate_detection_coordonly). Handled by + # the dedicated model.generate_cocodet + inferencer.gen_cocodet (which do NOT + # touch the grounding decode). + inference_decode_method: cocodet + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false diff --git a/conf/modalities/instruction_16mod_stage1_rgbcond.yaml b/conf/modalities/instruction_16mod_stage1_rgbcond.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0c341b864361541e0f580d6010890ab33babf419 --- /dev/null +++ b/conf/modalities/instruction_16mod_stage1_rgbcond.yaml @@ -0,0 +1,266 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: depth + id: 3 + kind: image + start_token_key: start_of_depth # REPLACE: per-modality start (token already exists in base vocab) + start_token: "<|depth_start|>" + end_token_key: end_of_image # shared end (image end is a structural terminator) + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_normal # REPLACE: per-modality start (token already exists in base vocab) + start_token: "<|normal_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + conditions: ["rgb"] # stage1 rgbcond: condition on rgb only (rgb->X warmup) + end_token_key: end_of_det + represent_vae: true + # NOTE: det's learnable pos_embed (grounding_pos_embed, size 4) is REMOVED here. + # The forward pos_embed loop is keyed by token-id range, and cocodet reuses + # det's x1/y1/x2/y2 tokens; with the pos_embed on, a multi-box cocodet sample + # (>4 coord tokens) would index the size-4 embedding out of bounds. det is not + # trained in modus (only present for coord-token-id alignment), so dropping its + # pos_embed is safe. reweight also removed (no reweight for det/cocodet). + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_seg # REPLACE: per-modality start (NEW token) + start_token: "<|seg_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_canny # REPLACE: per-modality start (NEW token) + start_token: "<|canny_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + conditions: ["rgb"] # stage1 rgbcond: condition on rgb only (rgb->X warmup) + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + conditions: ["rgb"] # stage1 rgbcond: condition on rgb only (rgb->X warmup) + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + conditions: ["rgb"] # stage1 rgbcond: condition on rgb only (rgb->X warmup) + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [28, 28] # 784 tokens, 28×28 grid → 2D RoPE + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + conditions: ["rgb"] # stage1 rgbcond: condition on rgb only (rgb->X warmup) + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + conditions: ["rgb"] # stage1 rgbcond: condition on rgb only (rgb->X warmup) + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + # ── NEW: cocodet (Pix2seq detection). stage1 = rgb→cocodet only. + # Coords reuse det's x1/y1/x2/y2 tokens (dedup, 0 new); class = COCO-id-aligned + # tokens (~91 new). dispersed_code_tokens → CE is gathered over the + # non-contiguous {coords ∪ class ∪ end} set, not a contiguous range. + # No reweight, no learnable pos_embed (RoPE + token-id carry order/role). + - name: cocodet + id: 13 + kind: codebook + start_token_key: start_of_cocodet + conditions: ["rgb"] # stage1 rgbcond: condition on rgb only (rgb->X warmup) + end_token_key: end_of_cocodet + start_token: "<|cocodet_start|>" + end_token: "<|cocodet_end|>" + represent_vae: true + dispersed_code_tokens: true + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|coco_cls_{i:02d}|>" + start: 0 + end: 90 + # Inference pipeline config. + # decode_method is 'cocodet' (NOT 'detection') — cocodet's output is + # coords+class per box ending on cocodet_end, a DIFFERENT format from the + # grounding/det coords-only decode (generate_detection_coordonly). Handled by + # the dedicated model.generate_cocodet + inferencer.gen_cocodet (which do NOT + # touch the grounding decode). + inference_decode_method: cocodet + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false + + # ── NEW image modalities (stage2): SAM segmentation / edge. Mirror seg/canny + # (direct-PNG image, VIT+VAE, MSE). REPLACE: per-modality start token, shared + # end_of_image. These start tokens are NEW (created via start_token field). + - name: samseg + id: 14 + kind: image + start_token_key: start_of_samseg + start_token: "<|samseg_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: samedge + id: 15 + kind: image + start_token_key: start_of_samedge + start_token: "<|samedge_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true diff --git a/conf/modalities/instruction_16mod_stage2.yaml b/conf/modalities/instruction_16mod_stage2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..c0ebcd90446388f17d435defd4566162a7489452 --- /dev/null +++ b/conf/modalities/instruction_16mod_stage2.yaml @@ -0,0 +1,272 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + inference_add_instruction: false # stage2/3 trained with use_target_instruction=false (no generic instr) + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + inference_add_instruction: false # any2caption (stage2) trained without a target instruction + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + inference_add_instruction: false # generic [start X] not trained in stage2/3 (use_target_instruction=false) + + - name: depth + id: 3 + kind: image + start_token_key: start_of_depth # REPLACE: per-modality start (token already exists in base vocab) + start_token: "<|depth_start|>" + end_token_key: end_of_image # shared end (image end is a structural terminator) + represent_vit: true + represent_vae: true + inference_add_instruction: false + + - name: normal + id: 4 + kind: image + start_token_key: start_of_normal # REPLACE: per-modality start (token already exists in base vocab) + start_token: "<|normal_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + inference_add_instruction: false + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + # NOTE: det's learnable pos_embed (grounding_pos_embed, size 4) is REMOVED here. + # The forward pos_embed loop is keyed by token-id range, and cocodet reuses + # det's x1/y1/x2/y2 tokens; with the pos_embed on, a multi-box cocodet sample + # (>4 coord tokens) would index the size-4 embedding out of bounds. det is not + # trained in modus (only present for coord-token-id alignment), so dropping its + # pos_embed is safe. reweight also removed (no reweight for det/cocodet). + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_seg # REPLACE: per-modality start (NEW token) + start_token: "<|seg_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_canny # REPLACE: per-modality start (NEW token) + start_token: "<|canny_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + inference_add_instruction: false + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + inference_add_instruction: false # start_of_dino token triggers it; generic instr not in stage2/3 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + inference_add_instruction: false + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [28, 28] # 784 tokens, 28×28 grid → 2D RoPE + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + inference_add_instruction: false + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + inference_add_instruction: false + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + inference_add_instruction: false + + # ── NEW: cocodet (Pix2seq detection). stage1 = rgb→cocodet only. + # Coords reuse det's x1/y1/x2/y2 tokens (dedup, 0 new); class = COCO-id-aligned + # tokens (~91 new). dispersed_code_tokens → CE is gathered over the + # non-contiguous {coords ∪ class ∪ end} set, not a contiguous range. + # No reweight, no learnable pos_embed (RoPE + token-id carry order/role). + - name: cocodet + id: 13 + kind: codebook + start_token_key: start_of_cocodet + end_token_key: end_of_cocodet + start_token: "<|cocodet_start|>" + end_token: "<|cocodet_end|>" + represent_vae: true + dispersed_code_tokens: true + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|coco_cls_{i:02d}|>" + start: 0 + end: 90 + # Inference pipeline config. + # decode_method is 'cocodet' (NOT 'detection') — cocodet's output is + # coords+class per box ending on cocodet_end, a DIFFERENT format from the + # grounding/det coords-only decode (generate_detection_coordonly). Handled by + # the dedicated model.generate_cocodet + inferencer.gen_cocodet (which do NOT + # touch the grounding decode). + inference_decode_method: cocodet + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false + + # ── NEW image modalities (stage2): SAM segmentation / edge. Mirror seg/canny + # (direct-PNG image, VIT+VAE, MSE). REPLACE: per-modality start token, shared + # end_of_image. These start tokens are NEW (created via start_token field). + - name: samseg + id: 14 + kind: image + start_token_key: start_of_samseg + start_token: "<|samseg_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + inference_add_instruction: false + + - name: samedge + id: 15 + kind: image + start_token_key: start_of_samedge + start_token: "<|samedge_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + inference_add_instruction: false diff --git a/conf/modalities/instruction_2d_only_stage1.yaml b/conf/modalities/instruction_2d_only_stage1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..6a1ec1fce8f352ada534e5962746c3946cf5e202 --- /dev/null +++ b/conf/modalities/instruction_2d_only_stage1.yaml @@ -0,0 +1,65 @@ +# 2D-only stage1 modality registry. +# +# Keeps text/caption and image-like modalities only. Drops DET/DINO/CLIP/ +# ImageBind codebook modalities so this run can isolate whether 1D/codebook CE +# is the main source of Hunyuan T2I prior drift. + +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb, depth, normal, seg, canny] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, depth, normal, seg, canny] + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, rgb, normal, seg, canny] + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, rgb, depth, seg, canny] + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, rgb, depth, normal, canny] + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, rgb, depth, normal, seg] diff --git a/conf/modalities/instruction_9modality_stage1.yaml b/conf/modalities/instruction_9modality_stage1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b6ffacd5a3b1f0959d24b3d038ac03ec1973f759 --- /dev/null +++ b/conf/modalities/instruction_9modality_stage1.yaml @@ -0,0 +1,114 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb, grounding, dino] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, grounding, dino] + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + pos_embed_size: 4 + apply_pos_embed_in_forward: true + pos_embed_name: grounding # checkpoint compat: attr is "grounding_pos_embed" + conditions: [rgb] + loss: + reweight: true + reweight_min_w: 0.005 + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 diff --git a/conf/modalities/instruction_9modality_stage3.yaml b/conf/modalities/instruction_9modality_stage3.yaml new file mode 100644 index 0000000000000000000000000000000000000000..576f01539c43c91cd7f2dc4b405922d5987057db --- /dev/null +++ b/conf/modalities/instruction_9modality_stage3.yaml @@ -0,0 +1,115 @@ +# Stage 3 modality config — 9 modalities (text + 8 task), unconstrained conditions. +# +# Mirrors instruction_9modality_stage1.yaml but drops every `conditions: [...]` +# restriction so any modality can be conditioned on any other (matches the old +# stage3 training run that was originally configured via CLI flags only). +# det reweight + det/dino learnable pos-embeds are preserved. + +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + pos_embed_size: 4 + apply_pos_embed_in_forward: true + pos_embed_name: grounding # checkpoint compat: attr is "grounding_pos_embed" + loss: + reweight: true + reweight_min_w: 0.005 + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 diff --git a/conf/modalities/instruction_hunyuan_16mod_stage1.yaml b/conf/modalities/instruction_hunyuan_16mod_stage1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..d5b929b00aafa949031f3dd97f1cb612e9ef5ecf --- /dev/null +++ b/conf/modalities/instruction_hunyuan_16mod_stage1.yaml @@ -0,0 +1,257 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb, grounding, dino, dinolocal, clip, imagebind, imagebindlocal] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, grounding, dino, dinolocal, clip, imagebind, imagebindlocal] + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + # det's learnable pos_embed (size 4) + reweight are REMOVED so cocodet — which + # reuses det's x1/y1/x2/y2 tokens (coco_cls is cocodet's own) — can carry >4 + # coord tokens per sample without indexing the size-4 pos_embed out of bounds. + # det is not a target here (only present for coord-token-id alignment); + # grounding reuses these tokens and is now RoPE-only for its bbox coords. + conditions: [rgb] + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [28, 28] # 784 tokens, 28×28 grid → 2D RoPE + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + # ── cocodet (Pix2seq detection). Coords reuse det's x1/y1/x2/y2 tokens (dedup, + # 0 new); class = COCO-id-aligned tokens (~91 new). dispersed_code_tokens → CE + # is gathered over the non-contiguous {coords ∪ class ∪ end} set, not a + # contiguous range. No reweight, no learnable pos_embed (RoPE + token-id). + - name: cocodet + id: 13 + kind: codebook + start_token_key: start_of_cocodet + end_token_key: end_of_cocodet + start_token: "<|cocodet_start|>" + end_token: "<|cocodet_end|>" + represent_vae: true + conditions: [rgb] # rgb→cocodet, consistent with det/dino/clip in this config + dispersed_code_tokens: true + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|coco_cls_{i:02d}|>" + start: 0 + end: 90 + # Inference: dedicated model.generate_cocodet + inferencer.gen_cocodet + # (coords+class per box ending on cocodet_end; NOT the grounding/det decode). + inference_decode_method: cocodet + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false + + # ── SAM segmentation / edge. Mirror seg/canny (direct-PNG image, ViT+VAE, MSE). + # Per-modality start token, shared end_of_image. Start tokens are NEW. + - name: samseg + id: 14 + kind: image + start_token_key: start_of_samseg + start_token: "<|samseg_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: samedge + id: 15 + kind: image + start_token_key: start_of_samedge + start_token: "<|samedge_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true diff --git a/conf/modalities/instruction_hunyuan_16mod_stage2.yaml b/conf/modalities/instruction_hunyuan_16mod_stage2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b9768ef74b56ddf5b6117b530542ef9bd17eed7e --- /dev/null +++ b/conf/modalities/instruction_hunyuan_16mod_stage2.yaml @@ -0,0 +1,250 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb, grounding, dino, dinolocal, clip, imagebind, imagebindlocal] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, grounding, dino, dinolocal, clip, imagebind, imagebindlocal] + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + # det's learnable pos_embed (size 4) + reweight are REMOVED so cocodet — which + # reuses det's x1/y1/x2/y2 tokens (coco_cls is cocodet's own) — can carry >4 + # coord tokens per sample without indexing the size-4 pos_embed out of bounds. + # det is not a target here (only present for coord-token-id alignment); + # grounding reuses these tokens and is now RoPE-only for its bbox coords. + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [28, 28] # 784 tokens, 28×28 grid → 2D RoPE + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + # ── cocodet (Pix2seq detection). Coords reuse det's x1/y1/x2/y2 tokens (dedup, + # 0 new); class = COCO-id-aligned tokens (~91 new). dispersed_code_tokens → CE + # is gathered over the non-contiguous {coords ∪ class ∪ end} set, not a + # contiguous range. No reweight, no learnable pos_embed (RoPE + token-id). + - name: cocodet + id: 13 + kind: codebook + start_token_key: start_of_cocodet + end_token_key: end_of_cocodet + start_token: "<|cocodet_start|>" + end_token: "<|cocodet_end|>" + represent_vae: true + dispersed_code_tokens: true + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|coco_cls_{i:02d}|>" + start: 0 + end: 90 + # Inference: dedicated model.generate_cocodet + inferencer.gen_cocodet + # (coords+class per box ending on cocodet_end; NOT the grounding/det decode). + inference_decode_method: cocodet + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false + + # ── SAM segmentation / edge. Mirror seg/canny (direct-PNG image, ViT+VAE, MSE). + # Per-modality start token, shared end_of_image. Start tokens are NEW. + - name: samseg + id: 14 + kind: image + start_token_key: start_of_samseg + start_token: "<|samseg_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: samedge + id: 15 + kind: image + start_token_key: start_of_samedge + start_token: "<|samedge_start|>" + end_token_key: end_of_image + represent_vit: true + represent_vae: true diff --git a/conf/modalities/instruction_stage2.yaml b/conf/modalities/instruction_stage2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f78b8059c4c8a16a44c8de5ceb1bc89a7ef4aa6c --- /dev/null +++ b/conf/modalities/instruction_stage2.yaml @@ -0,0 +1,204 @@ +# Stage 2 modality config — unconstrained conditions. +# +# Same modality definitions as instruction.yaml, but with ALL condition +# restrictions removed so every modality can be conditioned on every other. + +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + # conditions: unconstrained (any modality can condition caption) + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + # conditions: unconstrained + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + pos_embed_size: 4 + apply_pos_embed_in_forward: true + pos_embed_name: grounding # checkpoint compat: attr is "grounding_pos_embed" + # conditions: unconstrained + loss: + reweight: true + reweight_min_w: 0.005 + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + # conditions: unconstrained + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + # conditions: unconstrained + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + # conditions: unconstrained + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + # conditions: unconstrained + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + # conditions: unconstrained + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + diff --git a/conf/modalities/instruction_t2i_only_stage1.yaml b/conf/modalities/instruction_t2i_only_stage1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e274080a2f07b0a7cf53b4ca10f6a8fc0ad60462 --- /dev/null +++ b/conf/modalities/instruction_t2i_only_stage1.yaml @@ -0,0 +1,27 @@ +# v65 = T2I-only stage1 modality registry. +# Keeps text + caption + rgb only. Drops every other modality. +# Pair with `hunyuan_image_3_v65_t2i_only.yaml`. + +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption] diff --git a/conf/modalities/legacy.yaml b/conf/modalities/legacy.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e20e6981855d35de026697690b8ed949b196486b --- /dev/null +++ b/conf/modalities/legacy.yaml @@ -0,0 +1,38 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: start_of_caption + end_token_key: end_of_caption + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: depth + id: 3 + kind: image + start_token_key: start_of_depth + end_token_key: end_of_depth + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_normal + end_token_key: end_of_normal + represent_vit: true + represent_vae: true + + diff --git a/conf/modalities/rebuttal_rgb2target.yaml b/conf/modalities/rebuttal_rgb2target.yaml new file mode 100644 index 0000000000000000000000000000000000000000..df43d02399f5a3c9d8a86f2d666692bdbbde7d4a --- /dev/null +++ b/conf/modalities/rebuttal_rgb2target.yaml @@ -0,0 +1,116 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb, grounding, dino] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, grounding, dino] + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [rgb] + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [rgb] + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + pos_embed_size: 4 + apply_pos_embed_in_forward: true + pos_embed_name: grounding # checkpoint compat: attr is "grounding_pos_embed" + conditions: [rgb] + loss: + reweight: true + reweight_min_w: 0.005 + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 diff --git a/conf/modalities/stage1_oversample_bbox2rgb_dinolocal2rgb.yaml b/conf/modalities/stage1_oversample_bbox2rgb_dinolocal2rgb.yaml new file mode 100644 index 0000000000000000000000000000000000000000..dc59cac6b5810a2cbb25d50b0edac0a4b3c0b38e --- /dev/null +++ b/conf/modalities/stage1_oversample_bbox2rgb_dinolocal2rgb.yaml @@ -0,0 +1,203 @@ +modalities: + - name: text + id: 0 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + + - name: caption + id: 1 + kind: text + start_token_key: bos_token_id + end_token_key: eos_token_id + represent_vae: true + conditions: [rgb, grounding, dinolocal] + condition_probs: [0.1, 0.45, 0.45] + + - name: rgb + id: 2 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + conditions: [caption, grounding, dinolocal] + condition_probs: [0.1, 0.45, 0.45] + + - name: depth + id: 3 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: normal + id: 4 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: det + id: 5 + kind: codebook + start_token_key: start_of_det + end_token_key: end_of_det + represent_vae: true + pos_embed_size: 4 + apply_pos_embed_in_forward: true + pos_embed_name: grounding # checkpoint compat: attr is "grounding_pos_embed" + conditions: [rgb] + loss: + reweight: true + reweight_min_w: 0.005 + start_token: "<|det_start|>" + end_token: "<|det_end|>" + extra_tokens: ["<|box_start|>", "<|box_end|>"] + code_token_groups: + - token_format: "<|x1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y1_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|x2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|y2_{i:03d}|>" + start: 0 + end: 999 + - token_format: "<|score_{i:02d}|>" + start: 0 + end: 99 + # Inference pipeline config + inference_decode_method: detection + inference_max_tokens: 1000 + inference_cfg_uncond: text + inference_add_instruction: false # det uses start_of_det token, not text instruction + + - name: seg + id: 6 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: canny + id: 7 + kind: image + start_token_key: start_of_image + end_token_key: end_of_image + represent_vit: true + represent_vae: true + + - name: dino + id: 8 + kind: codebook + start_token_key: start_of_dino + end_token_key: end_of_dino + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|dino_start|>" + end_token: "<|dino_end|>" + code_vocab_size: 8192 + code_token_format: "<|dino_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: dino + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: dinolocal + id: 9 + kind: codebook + start_token_key: start_of_dinolocal + end_token_key: end_of_dinolocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|dinolocal_start|>" + end_token: "<|dinolocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|dinolocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_DINOv2-B14_8k_224-448" + # Inference pipeline config + inference_decode_method: dinolocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: clip + id: 10 + kind: codebook + start_token_key: start_of_clip + end_token_key: end_of_clip + pos_embed_size: 784 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [28, 28] # 784 tokens, 28×28 grid → 2D RoPE + start_token: "<|clip_start|>" + end_token: "<|clip_end|>" + code_vocab_size: 8192 + code_token_format: "<|clip_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_CLIP-B16_8k_224-448" + # Inference pipeline config + inference_decode_method: clip + inference_max_tokens: 785 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebind + id: 11 + kind: codebook + start_token_key: start_of_imagebind + end_token_key: end_of_imagebind + pos_embed_size: 16 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + start_token: "<|imagebind_start|>" + end_token: "<|imagebind_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebind_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14-global_8k_16_224" + # Inference pipeline config + inference_decode_method: imagebind + inference_max_tokens: 17 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 + + - name: imagebindlocal + id: 12 + kind: codebook + start_token_key: start_of_imagebindlocal + end_token_key: end_of_imagebindlocal + pos_embed_size: 1024 + apply_pos_embed_in_forward: true + represent_vae: true + conditions: [rgb] + codebook_spatial_shape: [32, 32] # 1024 tokens, 32×32 grid → 2D RoPE + start_token: "<|imagebindlocal_start|>" + end_token: "<|imagebindlocal_end|>" + code_vocab_size: 8192 + code_token_format: "<|imagebindlocal_{i:04d}|>" + external_tokenizer_kind: vqvae + external_tokenizer_repo: "EPFL-VILAB/4M_tokenizers_ImageBind-H14_8k_224-448" + # Inference pipeline config + inference_decode_method: imagebindlocal + inference_max_tokens: 1025 + inference_cfg_uncond: img + inference_cfg_img_scale: 1.0 diff --git a/core/__init__.py b/core/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..02f6c24a5a0a3878899a1d777c40bbfcaec4f790 --- /dev/null +++ b/core/__init__.py @@ -0,0 +1,11 @@ +""" +Core utilities for MODUS. + +This package is intentionally small and dependency-light so it can be used by: +- training scripts +- inference/demo scripts +- dataset packing +- model code +""" + + diff --git a/core/modality.py b/core/modality.py new file mode 100644 index 0000000000000000000000000000000000000000..449ca97ed0d43115e101a139336acc84de92a3e1 --- /dev/null +++ b/core/modality.py @@ -0,0 +1,394 @@ +from __future__ import annotations + +from dataclasses import dataclass, field as dc_field, replace as dc_replace +from typing import Any, Dict, Iterable, List, Mapping, Optional, Tuple + + +TokenRange = Tuple[int, int] # (base_id, length) + + +@dataclass(frozen=True) +class LossConfig: + """Per-modality loss configuration (lives in the modality YAML).""" + reweight: bool = False + reweight_min_w: float = 0.005 + reweight_det_vocab_dim: int = 4000 # only used when reweight=True for coordinate codebooks + + +@dataclass(frozen=True) +class ModalitySpec: + """ + Config-driven definition of a single modality. + + Every tunable per-modality knob lives here so that the training script, + model forward, and dataset packing can all be driven from one YAML. + """ + + name: str + id: int + start_token_key: str + end_token_key: str + kind: str = "text" # text | image | codebook + + # Token range ``(base, length)`` for CE-loss vocab slicing. + # Codebook modalities get their own range from the tokenizer; text + # modalities are auto-assigned ``(0, text_vocab_end)`` in + # ``ModalityRegistry.from_config``. Image modalities (ViT/VAE) + # never produce CE tokens, so they keep ``None``. + code_token_range: Optional[TokenRange] = None + + # Explicit, possibly **non-contiguous** set of CE-loss token ids. Used for + # modalities whose alphabet is dispersed across the vocab and therefore + # cannot be expressed as a single ``(base, length)`` range (e.g. cocodet, + # which reuses det's low-vocab coordinate tokens + new high-vocab class/end + # tokens). When set, the model does gather-CE over exactly these ids instead + # of the contiguous-slice path. ``None`` for every existing modality. + code_token_ids: Optional[Tuple[int, ...]] = None + + # Learnable positional embedding for code tokens. + pos_embed_size: Optional[int] = None + apply_pos_embed_in_forward: bool = False + + # Image representation flags (used by dataset packing and inferencer). + represent_vit: bool = True + represent_vae: bool = False + + # Which other modalities may condition this one during training. + # ``None`` means "use all available"; an explicit list restricts. + conditions: Optional[Tuple[str, ...]] = None + # Optional sampling probabilities aligned with ``conditions`` order. + # If omitted, the dataset uses a uniform distribution. + condition_probs: Optional[Tuple[float, ...]] = None + + # Per-modality loss parameters (CE smoothing / reweighting). + loss: LossConfig = LossConfig() + + # Override the model attribute name for the pos-embed (for checkpoint compat). + # Defaults to ``name`` (e.g. modality "dino" → attr ``dino_pos_embed``). + # Set to e.g. "grounding" for det → ``grounding_pos_embed``. + pos_embed_name: Optional[str] = None + + # 2D spatial shape for codebook modalities (h, w). + # None → 1D sequential (uses text region of build_2d_rope, gets sequential positions). + # Set e.g. (32, 32) for dinolocal, (28, 28) for clip → gets 2D RoPE same as VAE latents. + codebook_spatial_shape: Optional[Tuple[int, int]] = None + + # External tokenizer for inference decoding/encoding (e.g. DINO VQVAE). + external_tokenizer_repo: Optional[str] = None + external_tokenizer_kind: str = "vqvae" + + # ── Inference-time configuration ───────────────────────────────────── + # These fields drive the unified inference pipeline so that the + # inferencer does not need per-modality if/elif chains. + + # Decode method: "auto" resolves from ``kind`` (image→image, text→text). + # Explicit values: "image", "text", "detection", "dino". + inference_decode_method: str = "auto" + + # Maximum AR tokens for text / codebook decoding (None → inferencer default). + inference_max_tokens: Optional[int] = None + + # Which CFG unconditional context to use when this modality is a *target*: + # "text" → cfg_text_context (drop text, keep image) e.g. detection + # "img" → cfg_img_context (drop image, keep text) e.g. dino + # "both" → dual CFG with both contexts e.g. image generation + # "none" → no CFG e.g. plain text + inference_cfg_uncond: str = "auto" + + # Whether to prepend "[start {name} x10]" instruction before generation. + inference_add_instruction: bool = True + + # Default CFG image scale for this modality when it is the *target*. + # ``None`` → use the global default from the base config. + inference_cfg_img_scale: Optional[float] = None + + +class ModalityRegistry: + """Runtime registry consumed by dataset packing, model forward, and inferencer.""" + + def __init__(self, specs: Iterable[ModalitySpec]): + specs = list(specs) + if len(specs) == 0: + raise ValueError("ModalityRegistry requires at least one ModalitySpec.") + + self._by_name: Dict[str, ModalitySpec] = {} + self._by_id: Dict[int, ModalitySpec] = {} + for s in specs: + if s.name in self._by_name: + raise ValueError(f"Duplicate modality name: {s.name}") + if s.id in self._by_id: + raise ValueError(f"Duplicate modality id: {s.id}") + self._by_name[s.name] = s + self._by_id[s.id] = s + + # ── lookups ────────────────────────────────────────────────────────── + + @property + def specs(self) -> List[ModalitySpec]: + return list(self._by_name.values()) + + def get(self, name: str) -> ModalitySpec: + return self._by_name[name] + + def get_by_id(self, modality_id: int) -> ModalitySpec: + return self._by_id[modality_id] + + def name_to_id(self) -> Dict[str, int]: + return {k: v.id for k, v in self._by_name.items()} + + def id_to_name(self) -> Dict[int, str]: + return {k: v.name for k, v in self._by_id.items()} + + def modality_name(self, modality_id: int) -> str: + spec = self._by_id.get(modality_id) + return spec.name if spec is not None else f"unknown_{modality_id}" + + def start_token_key(self, name: str) -> str: + return self._by_name[name].start_token_key + + def end_token_key(self, name: str) -> str: + return self._by_name[name].end_token_key + + def start_token_id(self, new_token_ids: Mapping[str, Any], name: str) -> int: + return int(new_token_ids[self.start_token_key(name)]) + + def end_token_id(self, new_token_ids: Mapping[str, Any], name: str) -> int: + return int(new_token_ids[self.end_token_key(name)]) + + def code_token_range(self, name: str) -> Optional[TokenRange]: + return self._by_name[name].code_token_range + + def has_codebook_modalities(self) -> bool: + """True if any registered modality is ``kind == 'codebook'``.""" + return any(s.kind == "codebook" for s in self._by_name.values()) + + def conditions_for(self, target_modality: str) -> Optional[List[str]]: + """ + Return the allowed conditioning modalities for *target_modality*. + + ``None`` means "no restriction — use all available". + """ + spec = self._by_name.get(target_modality) + if spec is None or spec.conditions is None: + return None + return list(spec.conditions) + + def condition_probs_for(self, target_modality: str) -> Optional[List[float]]: + """ + Return optional condition sampling probabilities for *target_modality*. + + The returned probabilities align with ``conditions_for(target_modality)``. + ``None`` means "use uniform condition sampling". + """ + spec = self._by_name.get(target_modality) + if spec is None or spec.condition_probs is None: + return None + return list(spec.condition_probs) + + def resolve_decode_method(self, name: str) -> str: + """Return the concrete decode method for *name* (resolves ``"auto"``).""" + spec = self._by_name[name] + if spec.inference_decode_method != "auto": + return spec.inference_decode_method + if spec.kind == "image": + return "image" + if spec.kind == "text": + return "text" + # codebook — guess from name + if "det" in spec.name: + return "detection" + if spec.name == "dinolocal": + return "dinolocal" + if "dino" in spec.name: + return "dino" + return "text" + + def resolve_cfg_uncond(self, name: str) -> str: + """Return the concrete CFG-uncond context type (resolves ``"auto"``).""" + spec = self._by_name[name] + if spec.inference_cfg_uncond != "auto": + return spec.inference_cfg_uncond + dm = self.resolve_decode_method(name) + if dm == "image": + return "both" + if dm == "detection": + return "text" + if dm in ("dino", "dinolocal"): + return "img" + return "none" + + def resolve_cfg_img_scale(self, name: str, default: float = 2.0) -> float: + """Return the per-modality CFG image scale, or *default* if not specified.""" + spec = self._by_name[name] + if spec.inference_cfg_img_scale is not None: + return spec.inference_cfg_img_scale + return default + + def needs_external_tokenizer(self, name: str) -> bool: + """Return True if the modality has an external tokenizer (e.g. DINO VQVAE).""" + spec = self._by_name.get(name) + return spec is not None and spec.external_tokenizer_repo is not None + + def modalities_with_forward_pos_embed(self) -> List[ModalitySpec]: + return [ + s + for s in self._by_name.values() + if s.pos_embed_size is not None and s.apply_pos_embed_in_forward + ] + + # ── construction from YAML dict ───────────────────────────────────── + + @staticmethod + def from_config( + cfg: Any, + *, + token_ranges: Optional[Mapping[str, TokenRange]] = None, + code_token_ids: Optional[Mapping[str, List[int]]] = None, + ) -> "ModalityRegistry": + """ + Build a registry from the parsed YAML config dict. + + Expected structure:: + + cfg["modalities"]: list[{name, id, start_token_key, end_token_key, kind, ...}] + + ``token_ranges`` maps modality name → ``(base, length)`` and is typically + computed after tokenizer token additions. + """ + if cfg is None: + raise ValueError("cfg is required") + + # Accept either ``{"modalities": [...]}`` or a bare list. + modalities = cfg.get("modalities") if isinstance(cfg, dict) else cfg + if modalities is None: + raise ValueError("No 'modalities' key found in cfg") + + specs: List[ModalitySpec] = [] + token_ranges = dict(token_ranges or {}) + code_token_ids = dict(code_token_ids or {}) + + for m in modalities: + name = str(m["name"]) + + # Resolve code_token_range: prefer runtime-computed, fall back to cfg. + _range = token_ranges.get(name) + if _range is None and m.get("code_token_range") is not None: + _range = tuple(m["code_token_range"]) + + # Resolve explicit (possibly dispersed) code_token_ids, if any. + _ids = code_token_ids.get(name) + if _ids is None and m.get("code_token_ids") is not None: + _ids = m["code_token_ids"] + _ids = tuple(int(i) for i in _ids) if _ids is not None else None + + # pos_embed_size may be None. + _pos = m.get("pos_embed_size") + pos_embed_size = int(_pos) if _pos is not None else None + + # Parse conditions (list of strings or None). + _conds = m.get("conditions") + conditions = tuple(_conds) if _conds is not None else None + _cond_probs = m.get("condition_probs") + condition_probs = tuple(float(x) for x in _cond_probs) if _cond_probs is not None else None + if condition_probs is not None: + if conditions is None: + raise ValueError( + f"Modality '{name}' sets 'condition_probs' without 'conditions'." + ) + if len(condition_probs) != len(conditions): + raise ValueError( + f"Modality '{name}' has {len(conditions)} conditions but " + f"{len(condition_probs)} condition_probs." + ) + if any(p < 0.0 for p in condition_probs): + raise ValueError(f"Modality '{name}' has negative values in condition_probs.") + probs_sum = float(sum(condition_probs)) + if abs(probs_sum - 1.0) > 1e-6: + raise ValueError( + f"Modality '{name}' condition_probs must sum to 1.0, got {probs_sum}." + ) + + # Parse per-modality loss config. + _loss_dict = m.get("loss") or {} + loss_cfg = LossConfig( + reweight=bool(_loss_dict.get("reweight", False)), + reweight_min_w=float(_loss_dict.get("reweight_min_w", 0.005)), + reweight_det_vocab_dim=int(_loss_dict.get("reweight_det_vocab_dim", 4000)), + ) + + _pe_name = m.get("pos_embed_name") + pe_name = str(_pe_name) if _pe_name is not None else None + + # 2D spatial shape for codebook modalities. + _shape = m.get("codebook_spatial_shape") + codebook_spatial_shape = tuple(int(x) for x in _shape) if _shape is not None else None + + # Inference-time fields (optional in YAML; sensible defaults). + _infer = m.get("inference") or {} + _infer_decode = str(_infer.get("decode_method", m.get("inference_decode_method", "auto"))) + _infer_max = _infer.get("max_tokens", m.get("inference_max_tokens")) + _infer_cfg = str(_infer.get("cfg_uncond", m.get("inference_cfg_uncond", "auto"))) + _infer_add_instr = bool(_infer.get("add_instruction", m.get("inference_add_instruction", True))) + _infer_cfg_img = _infer.get("cfg_img_scale", m.get("inference_cfg_img_scale")) + _infer_cfg_img = float(_infer_cfg_img) if _infer_cfg_img is not None else None + + spec = ModalitySpec( + name=name, + id=int(m["id"]), + start_token_key=str(m["start_token_key"]), + end_token_key=str(m["end_token_key"]), + kind=str(m.get("kind", "text")), + code_token_range=_range, + code_token_ids=_ids, + pos_embed_size=pos_embed_size, + apply_pos_embed_in_forward=bool(m.get("apply_pos_embed_in_forward", False)), + represent_vit=bool(m.get("represent_vit", True)), + represent_vae=bool(m.get("represent_vae", False)), + conditions=conditions, + condition_probs=condition_probs, + loss=loss_cfg, + pos_embed_name=pe_name, + codebook_spatial_shape=codebook_spatial_shape, + external_tokenizer_repo=m.get("external_tokenizer_repo"), + external_tokenizer_kind=str(m.get("external_tokenizer_kind", "vqvae")), + inference_decode_method=_infer_decode, + inference_max_tokens=int(_infer_max) if _infer_max is not None else None, + inference_cfg_uncond=_infer_cfg, + inference_add_instruction=_infer_add_instr, + inference_cfg_img_scale=_infer_cfg_img, + ) + specs.append(spec) + + # ── Auto-assign text token range to text-kind modalities ───────── + # Find text_vocab_end = min base across all codebook ranges. + text_vocab_end: Optional[int] = None + for s in specs: + if s.code_token_range is not None: + cb_base, _ = s.code_token_range + text_vocab_end = int(cb_base) if text_vocab_end is None else min(text_vocab_end, int(cb_base)) + + if text_vocab_end is not None: + text_range: TokenRange = (0, text_vocab_end) + specs = [ + dc_replace(s, code_token_range=text_range) + if s.kind == "text" and s.code_token_range is None else s + for s in specs + ] + + return ModalityRegistry(specs) + + +def infer_contiguous_token_range(token_ids: List[int]) -> TokenRange: + """Given a list of token IDs, infer ``(base, length)`` and validate contiguity.""" + if len(token_ids) == 0: + raise ValueError("token_ids cannot be empty") + token_ids_sorted = sorted(int(x) for x in token_ids) + base = token_ids_sorted[0] + length = len(token_ids_sorted) + expected = list(range(base, base + length)) + if token_ids_sorted != expected: + raise ValueError( + "Token IDs are not contiguous; cannot represent as a range efficiently. " + f"base={base}, length={length}, first10={token_ids_sorted[:10]}" + ) + return base, length diff --git a/core/model_registry.py b/core/model_registry.py new file mode 100644 index 0000000000000000000000000000000000000000..7bb435638db964a740978cc8ab2237ee550b7cfa --- /dev/null +++ b/core/model_registry.py @@ -0,0 +1,47 @@ +from __future__ import annotations + +from dataclasses import dataclass +from typing import Any, Callable, Dict, Optional, Tuple + + +ModelBuilder = Callable[..., Any] + + +class ModelRegistry: + """ + Minimal model registry to decouple scripts from concrete model classes. + + Goal: + - training/inference scripts choose `model.name` in config + - swapping architectures doesn't require editing scripts, only adding a builder registration + """ + + def __init__(self): + self._builders: Dict[str, ModelBuilder] = {} + + def register(self, name: str, builder: ModelBuilder) -> None: + if name in self._builders: + raise ValueError(f"Model '{name}' is already registered.") + self._builders[name] = builder + + def build(self, name: str, **kwargs) -> Any: + if name not in self._builders: + known = ", ".join(sorted(self._builders.keys())) + raise KeyError(f"Unknown model '{name}'. Known: {known}") + return self._builders[name](**kwargs) + + +GLOBAL_MODEL_REGISTRY = ModelRegistry() + + +def register_model(name: str) -> Callable[[ModelBuilder], ModelBuilder]: + def _decorator(fn: ModelBuilder) -> ModelBuilder: + GLOBAL_MODEL_REGISTRY.register(name, fn) + return fn + return _decorator + + +def build_model(name: str, **kwargs) -> Any: + return GLOBAL_MODEL_REGISTRY.build(name, **kwargs) + + diff --git a/core/tokenizer_utils.py b/core/tokenizer_utils.py new file mode 100644 index 0000000000000000000000000000000000000000..263923e4775adc96f3bd10f2a6eef329bdb1bcfd --- /dev/null +++ b/core/tokenizer_utils.py @@ -0,0 +1,257 @@ +""" +Config-driven tokenizer setup. + +All modality tokens (delimiters, codebook entries) are specified in the modality +YAML and added here. No hard-coded ``use_det`` / ``use_dino`` flags. +""" +from __future__ import annotations + +from dataclasses import dataclass +from typing import Any, Dict, List, Optional, Tuple + +from core.modality import TokenRange, infer_contiguous_token_range +from data.data_utils import add_special_tokens + + +@dataclass +class TokenizerArtifacts: + """Return value of :func:`build_tokenizer_and_special_tokens`.""" + tokenizer: Any + new_token_ids: Dict[str, Any] + token_ranges: Dict[str, TokenRange] + # Explicit dispersed CE-token id sets, for modalities that set + # ``dispersed_code_tokens: true`` (e.g. cocodet). modality name -> id list. + code_token_ids: Dict[str, List[int]] + + +def load_base_tokenizer(*, model_args: Any, training_args: Any): + """Load the base tokenizer (before any token additions). + + Dispatches to HunyuanImage3TokenizerFast when model_name == 'hunyuan_image_3', + otherwise falls back to the standard Qwen2Tokenizer. + """ + if getattr(model_args, "model_name", "bagel") == "hunyuan_image_3": + from modeling.hunyuan_image_3.src.tokenization_hunyuan_image_3 import ( + HunyuanImage3TokenizerFast, + ) + return HunyuanImage3TokenizerFast.from_pretrained( + model_args.model_path, + model_version="HunyuanImage-3.0-Instruct", + ) + + from modeling.qwen2.tokenization_qwen2 import Qwen2Tokenizer + + pretrained_path = ( + model_args.model_path + if getattr(training_args, "finetune_from_hf", False) + else model_args.llm_path + ) + return Qwen2Tokenizer.from_pretrained(pretrained_path) + + +# ── internal helpers ───────────────────────────────────────────────────────── + +def _add_tokens(tokenizer, tokens: List[str]) -> None: + """Add tokens in order, deduplicating while preserving first occurrence.""" + seen: set = set() + ordered: List[str] = [] + for t in tokens: + if t not in seen: + seen.add(t) + ordered.append(t) + tokenizer.add_tokens(ordered) + + +def _ensure_token_key( + tokenizer, + new_token_ids: Dict[str, Any], + *, + token_key: str, + token_str: Optional[str], +) -> None: + """ + Make sure ``new_token_ids[token_key]`` exists, creating the token if needed. + """ + if token_key in new_token_ids: + return + if hasattr(tokenizer, token_key): + new_token_ids[token_key] = int(getattr(tokenizer, token_key)) + return + if token_str is None: + raise KeyError( + f"Token key '{token_key}' not in tokenizer or new_token_ids and no token_str provided." + ) + try: + tokenizer.add_special_tokens({"additional_special_tokens": [token_str]}) + except Exception: + tokenizer.add_tokens([token_str]) + new_token_ids[token_key] = int(tokenizer.convert_tokens_to_ids(token_str)) + + +def _code_tokens_from_cfg(m: Dict[str, Any]) -> List[str]: + """Build the list of code-token strings from a modality config dict.""" + + # Preferred: explicit groups (e.g. DET coordinate tokens). + groups = m.get("code_token_groups") + if groups is not None: + out: List[str] = [] + for g in groups: + if not isinstance(g, dict): + g = dict(g) + token_format = str(g["token_format"]) + start = int(g.get("start", 0)) + end = int(g["end"]) + for i in range(start, end + 1): + out.append(token_format.format( + i=i, + prefix=m.get("code_token_prefix", m.get("name")), + )) + return out + + # Fallback: contiguous vocab with format / prefix. + vocab = m.get("code_vocab_size") + if vocab is None: + raise ValueError( + f"Codebook modality '{m.get('name')}' needs 'code_vocab_size' or 'code_token_groups'." + ) + vocab = int(vocab) + token_format = str(m.get("code_token_format", "<|{prefix}_{i:04d}|>")) + prefix = str(m.get("code_token_prefix", m.get("name"))) + return [token_format.format(prefix=prefix, i=i) for i in range(vocab)] + + +def _add_modality_tokens( + tokenizer, + *, + m: Dict[str, Any], + new_token_ids: Dict[str, Any], + token_ranges: Dict[str, TokenRange], + code_token_ids_out: Dict[str, List[int]], + deferred_tokens: List[Any], +) -> None: + """ + Add all tokens for one modality entry (text/image/codebook) from its YAML dict. + + For **codebook** modalities the addition order is *code tokens first, then + delimiter / extra tokens*. This matches the ordering used when the + original checkpoint was trained so that token IDs remain identical. + """ + kind = str(m.get("kind", "text")) + start_key = str(m["start_token_key"]) + end_key = str(m["end_token_key"]) + + if kind != "codebook": + # Image/text modalities: resolve already-existing start/end tokens now + # (shared start_of_image, or start_of_depth/normal added by + # add_special_tokens). Any genuinely NEW token (e.g. a per-modality + # start_of_seg/canny/samseg/samedge under REPLACE) is DEFERRED and added + # at the very tail in build_tokenizer_and_special_tokens — so introducing + # an image modality with its own start token does NOT shift the ids of + # codebook tokens added later in the loop, preserving cross-stage ckpt + # alignment. + vocab = tokenizer.get_vocab() + for token_key, token_str in ((start_key, m.get("start_token")), (end_key, m.get("end_token"))): + if token_key in new_token_ids: + continue + if token_str is not None and str(token_str) in vocab: + new_token_ids[token_key] = int(vocab[str(token_str)]) + elif token_str is not None: + deferred_tokens.append((token_key, str(token_str))) + else: + _ensure_token_key(tokenizer, new_token_ids, token_key=token_key, token_str=None) + return + + # ── codebook modality ──────────────────────────────────────────────── + code_tokens = _code_tokens_from_cfg(m) + + start_tok = m.get("start_token") + end_tok = m.get("end_token") + delim_tokens: List[str] = [] + if start_tok is not None: + delim_tokens.append(str(start_tok)) + if end_tok is not None: + delim_tokens.append(str(end_tok)) + delim_tokens.extend(str(t) for t in (m.get("extra_tokens") or [])) + + # One batch: code tokens first, delimiters after → matches checkpoint ordering. + _add_tokens(tokenizer, code_tokens + delim_tokens) + + # Populate delimiter keys. + if start_tok is not None and start_key not in new_token_ids: + new_token_ids[start_key] = int(tokenizer.convert_tokens_to_ids(str(start_tok))) + elif start_key not in new_token_ids: + _ensure_token_key(tokenizer, new_token_ids, token_key=start_key, token_str=None) + if end_tok is not None and end_key not in new_token_ids: + new_token_ids[end_key] = int(tokenizer.convert_tokens_to_ids(str(end_tok))) + elif end_key not in new_token_ids: + _ensure_token_key(tokenizer, new_token_ids, token_key=end_key, token_str=None) + + name = str(m["name"]) + token_ids = [int(tokenizer.convert_tokens_to_ids(t)) for t in code_tokens] + if bool(m.get("dispersed_code_tokens", False)): + # Dispersed alphabet (e.g. cocodet: reused det coords at low vocab ids + + # new class tokens at the tail) — cannot be a single contiguous range. + # Record the explicit CE-token id set = all code tokens + the end + # delimiter (a CE target / stop token). The start delimiter is + # input-only, so it is excluded. + ids = list(token_ids) + end_id = new_token_ids.get(end_key) + if end_id is not None: + ids.append(int(end_id)) + code_token_ids_out[name] = ids + else: + # Record contiguous code-token range. + token_ranges[name] = infer_contiguous_token_range(token_ids) + + +# ── public API ─────────────────────────────────────────────────────────────── + +def build_tokenizer_and_special_tokens( + tokenizer, + *, + modalities_cfg: Dict[str, Any], +) -> TokenizerArtifacts: + """ + Fully config-driven tokenizer setup. + + 1. Adds universal special tokens (``<|im_start|>``, ``<|vision_start|>``, …) + via the legacy ``add_special_tokens`` helper (for checkpoint compat). + 2. Iterates over ``modalities_cfg["modalities"]`` and adds delimiter / code + tokens for each entry. + + Returns a :class:`TokenizerArtifacts` with the final tokenizer, a dict of + all special-token IDs, and a dict of code-token ranges for codebook modalities. + """ + token_ranges: Dict[str, TokenRange] = {} + code_token_ids: Dict[str, List[int]] = {} + deferred_tokens: List[Any] = [] + + # Step 1: universal special tokens (checkpoint-compatible ordering). + tokenizer, new_token_ids, _num = add_special_tokens(tokenizer) + + # Step 2: per-modality tokens from YAML. + modalities = modalities_cfg.get("modalities", modalities_cfg) + for m in modalities: + if not isinstance(m, dict): + m = dict(m) + _add_modality_tokens( + tokenizer, + m=m, + new_token_ids=new_token_ids, + token_ranges=token_ranges, + code_token_ids_out=code_token_ids, + deferred_tokens=deferred_tokens, + ) + + # Step 3: append deferred NEW image-modality start/end tokens at the tail + # (after all codebook tokens) so they never shift existing ids across stages. + for token_key, token_str in deferred_tokens: + if token_key not in new_token_ids: + _ensure_token_key(tokenizer, new_token_ids, token_key=token_key, token_str=token_str) + + return TokenizerArtifacts( + tokenizer=tokenizer, + new_token_ids=new_token_ids, + token_ranges=token_ranges, + code_token_ids=code_token_ids, + ) diff --git a/data/__init__.py b/data/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..943b7d3a7a676d9a500bf048d4307f4f803221f5 --- /dev/null +++ b/data/__init__.py @@ -0,0 +1,2 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 \ No newline at end of file diff --git a/data/any2any_preprocess/_build_preview_and_montage.py b/data/any2any_preprocess/_build_preview_and_montage.py new file mode 100644 index 0000000000000000000000000000000000000000..d91129b3b0d90d2595667bee9aaaa8e1ebf39931 --- /dev/null +++ b/data/any2any_preprocess/_build_preview_and_montage.py @@ -0,0 +1,52 @@ +import io, os +import pyarrow.parquet as pq +from PIL import Image, ImageDraw + +BASE_SRC = ('datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding' + '_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet') +Q95 = 'datasets/blip3o/parquet_16mod_normalq95_sample/sa_000000.parquet' +PREVIEW_DIR = 'datasets/blip3o/modus_preview' +MONTAGE = 'eval_outputs/modus_hero_montage.png' +N_ROWS = 500 + +# ---- 1. print sample uids per source to confirm the alignment key ---- +print('==== uid samples (alignment key check) ====', flush=True) +for f in ['sa_000000.parquet', 'webdataset_shard_000.parquet', 'webdataset_JDB_2.parquet']: + p = f'{BASE_SRC}/{f}' + t = pq.ParquetFile(p).read_row_group(0, columns=['uid']) + uids = t.column('uid').to_pylist()[:4] + print(f' {f}: {uids}', flush=True) + +# ---- 2. build small preview parquet (subset of q95-compressed sa_000000) ---- +os.makedirs(PREVIEW_DIR, exist_ok=True) +pf = pq.ParquetFile(Q95) +table = pf.read_row_group(0).slice(0, N_ROWS) +dst = f'{PREVIEW_DIR}/modus_preview_sa_500.parquet' +pq.write_table(table, dst, compression='snappy') +print(f'\npreview: {dst} rows={table.num_rows} size={os.path.getsize(dst)/1e6:.1f} MB', flush=True) + +# ---- 3. hero montage: rows=samples, cols=modalities ---- +MODS = ['rgb', 'depth', 'normal', 'canny', 'sam_seg', 'sam_edge'] +N_SHOW = 5 +cell, pad, hdr = 300, 6, 26 +cols = {m: table.column(m).to_pylist()[:N_SHOW] for m in MODS} + +def dec(b): + if b is None: return None + if isinstance(b, memoryview): b = b.tobytes() + return Image.open(io.BytesIO(b)).convert('RGB') + +W = len(MODS)*(cell+pad)+pad +H = hdr + N_SHOW*(cell+pad)+pad +grid = Image.new('RGB', (W, H), 'white') +d = ImageDraw.Draw(grid) +for c, m in enumerate(MODS): + d.text((pad+c*(cell+pad)+4, 6), m, fill='black') +for r in range(N_SHOW): + for c, m in enumerate(MODS): + im = dec(cols[m][r]) + if im is None: continue + grid.paste(im.resize((cell, cell)), (pad+c*(cell+pad), hdr+pad+r*(cell+pad))) +os.makedirs(os.path.dirname(MONTAGE), exist_ok=True) +grid.save(MONTAGE) +print(f'montage: {MONTAGE} ({W}x{H})', flush=True) diff --git a/data/any2any_preprocess/_cast_preview_images.py b/data/any2any_preprocess/_cast_preview_images.py new file mode 100644 index 0000000000000000000000000000000000000000..95317d89b1cf5dca3cdf5f7e8aca99e62941d8a2 --- /dev/null +++ b/data/any2any_preprocess/_cast_preview_images.py @@ -0,0 +1,34 @@ +"""Cast the preview parquet's raw-bytes image columns to the HF `Image` feature +so the dataset viewer renders thumbnails.""" +import json +import os +from datasets import load_dataset, Image, Value + +SRC = 'datasets/blip3o/modus_preview/modus_preview_sa_500.parquet' +OUT_DIR = 'datasets/blip3o/modus_preview_upload/data' +OUT = f'{OUT_DIR}/modus_preview_sa_500.parquet' +IMG_COLS = ['rgb', 'depth', 'normal', 'canny', 'sam_seg', 'sam_edge'] + +# Display-name order requested by the user (uid=key first; det_seg + grounding +# raw blobs moved to the very end). +ORDER = [ + 'uid', 'rgb', 'depth', 'normal', 'sam_seg', 'canny', 'sam_edge', + 'coco_det', 'caption', 'dino_global', 'dino', 'clip448', + 'imagebind_global', 'imagebind', 'det_seg', 'grounding', +] + +ds = load_dataset('parquet', data_files=SRC, split='train') +print('loaded:', ds.num_rows, 'rows; features before:', list(ds.features.keys())) +for c in IMG_COLS: + ds = ds.cast_column(c, Image()) +# Flatten deep-nested blobs to JSON strings so the HF viewer worker doesn't OOM. +for c in ['det_seg', 'grounding']: + ds = ds.map(lambda ex, col=c: {col: json.dumps(ex[col], default=str, ensure_ascii=False)}) + ds = ds.cast_column(c, Value('string')) +assert set(ORDER) == set(ds.column_names), set(ORDER) ^ set(ds.column_names) +ds = ds.select_columns(ORDER) +print('column order:', ds.column_names) + +os.makedirs(OUT_DIR, exist_ok=True) +ds.to_parquet(OUT) +print(f'wrote {OUT} size={os.path.getsize(OUT)/1e6:.1f} MB', flush=True) diff --git a/data/any2any_preprocess/_sb_full_rebuild.sh b/data/any2any_preprocess/_sb_full_rebuild.sh new file mode 100644 index 0000000000000000000000000000000000000000..cc251e9373542ad5984a4a10e0d365efdaf78949 --- /dev/null +++ b/data/any2any_preprocess/_sb_full_rebuild.sh @@ -0,0 +1,18 @@ +#!/bin/bash +#SBATCH --job-name=modus_full_rebuild +#SBATCH --partition=debug +#SBATCH --time=01:30:00 +#SBATCH --nodes=1 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=128 +#SBATCH --mem=700GB +#SBATCH --account=a143 +#SBATCH --output=logs/full_rebuild_%j.out +#SBATCH --error=logs/full_rebuild_%j.err +#SBATCH --environment=/iopsstor/scratch/cscs/mye/workspace/BAGEL/environment/bagel.toml + +M=/iopsstor/scratch/cscs/mye/workspace/MODUS_RELEASE/MODUS +srun --environment=/iopsstor/scratch/cscs/mye/workspace/BAGEL/environment/bagel.toml \ + bash -c "cd $M && export PYTHONPATH='$M/data/any2any_preprocess:\$PYTHONPATH' && \ + python3 data/any2any_preprocess/run_full_rebuild.py \ + --num-tasks 1 --task-id 0 --concurrency 64" diff --git a/data/any2any_preprocess/_sb_recompress_normal_sample.sh b/data/any2any_preprocess/_sb_recompress_normal_sample.sh new file mode 100644 index 0000000000000000000000000000000000000000..54653aad7de6e2b4228c768039fea6fcfa6d1c9b --- /dev/null +++ b/data/any2any_preprocess/_sb_recompress_normal_sample.sh @@ -0,0 +1,24 @@ +#!/bin/bash +#SBATCH --job-name=norm_q95_smp +#SBATCH --partition=debug +#SBATCH --time=01:30:00 +#SBATCH --nodes=1 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=8 +#SBATCH --mem=64GB +#SBATCH --account=a143 +#SBATCH --output=logs/norm_q95_sample_%j.out +#SBATCH --error=logs/norm_q95_sample_%j.err +#SBATCH --environment=/iopsstor/scratch/cscs/mye/workspace/BAGEL/environment/bagel.toml + +M=/iopsstor/scratch/cscs/mye/workspace/MODUS_RELEASE/MODUS +SRC="$M/datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet" +OUT="$M/datasets/blip3o/parquet_16mod_normalq95_sample" + +srun --environment=/iopsstor/scratch/cscs/mye/workspace/BAGEL/environment/bagel.toml \ + bash -c "cd $M && python3 data/any2any_preprocess/recompress_normal_jpeg.py \ + --out_dir '$OUT' \ + '$SRC/sa_000000.parquet' \ + '$SRC/sa_000001.parquet' \ + '$SRC/sa_000002.parquet' \ + '$SRC/sa_000003.parquet'" diff --git a/data/any2any_preprocess/_sb_upload.sh b/data/any2any_preprocess/_sb_upload.sh new file mode 100644 index 0000000000000000000000000000000000000000..eaa5398f771d63215865022167a19b6e6feadf3e --- /dev/null +++ b/data/any2any_preprocess/_sb_upload.sh @@ -0,0 +1,21 @@ +#!/bin/bash +#SBATCH --job-name=modus_upload +#SBATCH --partition=debug +#SBATCH --time=01:30:00 +#SBATCH --nodes=1 +#SBATCH --ntasks-per-node=1 +#SBATCH --cpus-per-task=32 +#SBATCH --mem=200GB +#SBATCH --account=a143 +#SBATCH --output=logs/upload_%j.out +#SBATCH --error=logs/upload_%j.err +#SBATCH --environment=/iopsstor/scratch/cscs/mye/workspace/BAGEL/environment/bagel.toml + +# Resumable upload of the whole modus_full folder (all configs) + README. +M=/iopsstor/scratch/cscs/mye/workspace/MODUS_RELEASE/MODUS +srun --environment=/iopsstor/scratch/cscs/mye/workspace/BAGEL/environment/bagel.toml \ + bash -c "cd $M && export HF_TOKEN_FILE=/users/mye/.hf_token && \ + python3 -c \"from huggingface_hub import HfApi; t=open('/users/mye/.hf_token').read().strip(); \ + HfApi(token=t).upload_file(path_or_fileobj='datasets/blip3o/modus_preview_upload/README.md', path_in_repo='README.md', repo_id='epfl-vilab-modus/MODUS-16Modality', repo_type='dataset', commit_message='full configs card'); print('README ok')\" ; \ + python3 data/any2any_preprocess/upload_full.py \ + epfl-vilab-modus/MODUS-16Modality datasets/blip3o/modus_full '*/*.parquet'" diff --git a/data/any2any_preprocess/_verify_normal_q95.py b/data/any2any_preprocess/_verify_normal_q95.py new file mode 100644 index 0000000000000000000000000000000000000000..19b80666f014de5eb4fb651baee6f54a58da503b --- /dev/null +++ b/data/any2any_preprocess/_verify_normal_q95.py @@ -0,0 +1,34 @@ +import io, os +import pyarrow.parquet as pq +from PIL import Image + +SRC = ('datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding' + '_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000000.parquet') +NEW = 'datasets/blip3o/parquet_16mod_normalq95_sample/sa_000000.parquet' +OUT = 'eval_outputs/normal_q95_check' +os.makedirs(OUT, exist_ok=True) + +def load(path, col, n): + t = pq.ParquetFile(path).read_row_group(0, columns=[col]) + vals = t.column(col).to_pylist()[:n] + out = [] + for b in vals: + if isinstance(b, memoryview): b = b.tobytes() + out.append(Image.open(io.BytesIO(b)).convert('RGB')) + return out + +N = 3 +rgb = load(SRC, 'rgb', N) +nsrc = load(SRC, 'normal', N) +nnew = load(NEW, 'normal', N) + +cell = 384 +grid = Image.new('RGB', (cell*3, cell*N), 'white') +for r in range(N): + for c, im in enumerate([rgb[r], nsrc[r], nnew[r]]): + grid.paste(im.resize((cell, cell)), (c*cell, r*cell)) +path = f'{OUT}/rgb_normalPNG_normalJPEGq95.png' +grid.save(path) +print(f'saved {path} (cols: rgb | normal-PNG(src) | normal-JPEGq95(new))', flush=True) +for r in range(N): + print(f' row{r}: normal src size={nsrc[r].size} new size={nnew[r].size}', flush=True) diff --git a/data/any2any_preprocess/build_full_release.py b/data/any2any_preprocess/build_full_release.py new file mode 100644 index 0000000000000000000000000000000000000000..24b23ff52b2ff7e1e934e49138669ebd877ada8a --- /dev/null +++ b/data/any2any_preprocess/build_full_release.py @@ -0,0 +1,108 @@ +"""Build the MODUS full-release parquet for one source config. + +Per config: + sa1b / journeydb : annotations-only -> DROP ['rgb','caption'] ; recompress normal->JPEG q95 + cc12m : self-contained -> keep all columns ; recompress normal->JPEG q95 + +Streams by row group (bounded memory). Resumable: skips outputs that already +exist and are complete; writes to a .tmp then atomically renames. + +Usage: + python build_full_release.py --config sa1b --out_dir --workers 8 file1.parquet [...] +""" +import argparse +import io +import os +from concurrent.futures import ProcessPoolExecutor, as_completed + +import pyarrow as pa +import pyarrow.parquet as pq +from PIL import Image + +DROP = {'sa1b': ['rgb', 'caption'], 'journeydb': ['rgb', 'caption'], 'cc12m': []} +JPEG_QUALITY = 95 + + +def _recompress_normal(b): + if b is None: + return None + if isinstance(b, memoryview): + b = b.tobytes() + with Image.open(io.BytesIO(b)) as im: + img = im.convert('RGB') + out = io.BytesIO() + img.save(out, format='JPEG', quality=JPEG_QUALITY) + img.close() + return out.getvalue() + + +def process_one(src, dst, drop_cols): + if os.path.exists(dst) and os.path.getsize(dst) > 0: + return src, 'skip', os.path.getsize(dst) + tmp = dst + '.tmp' + pf = pq.ParquetFile(src) + names = pf.schema_arrow.names + keep = [n for n in names if n not in drop_cols] + out_schema = pa.schema([pf.schema_arrow.field(n) for n in keep]) + has_normal = 'normal' in keep + norm_field = out_schema.field('normal') if has_normal else None + ni = keep.index('normal') if has_normal else -1 + + # Stream in small batches so peak memory is bounded regardless of row-group size. + writer = pq.ParquetWriter(tmp, out_schema, compression='snappy') + try: + for batch in pf.iter_batches(batch_size=128, columns=keep): + t = pa.Table.from_batches([batch], schema=out_schema) + if has_normal: + col = [_recompress_normal(b) for b in t.column('normal').to_pylist()] + t = t.set_column(ni, norm_field, pa.array(col, type=norm_field.type)) + writer.write_table(t) + del t + finally: + writer.close() + os.replace(tmp, dst) + return src, 'done', os.path.getsize(dst) + + +def main(): + ap = argparse.ArgumentParser() + ap.add_argument('--config', required=True, choices=list(DROP)) + ap.add_argument('--out_dir', required=True) + ap.add_argument('--workers', type=int, default=8) + ap.add_argument('files', nargs='+') + args = ap.parse_args() + os.makedirs(args.out_dir, exist_ok=True) + drop_cols = DROP[args.config] + + tasks = [(f, os.path.join(args.out_dir, os.path.basename(f)), drop_cols) + for f in args.files] + done = skip = 0 + + if args.workers == 1: + # Sequential, in-process (used when spawned as a per-chunk subprocess so + # the OS reclaims all memory on exit — no leak accumulation). + for src, dst, dc in tasks: + _, status, _ = process_one(src, dst, dc) + done += status == 'done' + skip += status == 'skip' + print(f'{status} {os.path.basename(src)}', flush=True) + print(f'CHUNK {args.config}: {done} built, {skip} skipped', flush=True) + return + + tot_out = 0 + with ProcessPoolExecutor(max_workers=args.workers) as ex: + futs = [ex.submit(process_one, *t) for t in tasks] + for i, fu in enumerate(as_completed(futs), 1): + src, status, sz = fu.result() + tot_out += sz + done += status == 'done' + skip += status == 'skip' + if i % 10 == 0 or status == 'done': + print(f'[{i}/{len(tasks)}] {status} {os.path.basename(src)} ' + f'done={done} skip={skip} out={tot_out/1e9:.1f}GB', flush=True) + print(f'CONFIG {args.config}: {done} built, {skip} skipped, ' + f'total_out={tot_out/1e9:.1f}GB', flush=True) + + +if __name__ == '__main__': + main() diff --git a/data/any2any_preprocess/check_vqa.py b/data/any2any_preprocess/check_vqa.py new file mode 100644 index 0000000000000000000000000000000000000000..72e2af559c3dbbba588f1b289d9dd847caa2012d --- /dev/null +++ b/data/any2any_preprocess/check_vqa.py @@ -0,0 +1,188 @@ +import os +import json +import argparse +from typing import Dict, Any, Tuple, List + + +def is_valid_name(name: Any) -> bool: + return isinstance(name, str) and len(name.strip()) > 0 + + +def process_labels_jsonl(images_dir: str, labels_path: str, max_lines: int = -1) -> Tuple[Dict[str, Any], List[str]]: + stats: Dict[str, Any] = dict( + num_records=0, + num_invalid_json=0, + num_image_refs=0, + num_images_missing=0, + num_unique_images_missing=0, + num_video_refs=0, + num_videos_missing=0, + ) + missing_images_unique = set() + + with open(labels_path, "r") as f: + for line_idx, line in enumerate(f): + if max_lines > 0 and line_idx >= max_lines: + break + try: + record = json.loads(line) + except Exception: + stats["num_invalid_json"] += 1 + continue + + stats["num_records"] += 1 + + # Check images (string or list) + if "image" in record: + if isinstance(record["image"], list): + image_names = record["image"] + else: + image_names = [record["image"]] + + for name in image_names: + stats["num_image_refs"] += 1 + if not is_valid_name(name): + stats["num_images_missing"] += 1 + missing_images_unique.add(str(name)) + continue + image_path = os.path.join(images_dir, name) + if not os.path.isfile(image_path): + stats["num_images_missing"] += 1 + missing_images_unique.add(name) + + # Check video if present (optional) + if "video" in record: + stats["num_video_refs"] += 1 + video_name = record["video"] + if not is_valid_name(video_name): + stats["num_videos_missing"] += 1 + else: + video_path = os.path.join(images_dir, video_name) + if not os.path.isfile(video_path): + stats["num_videos_missing"] += 1 + + stats["num_unique_images_missing"] = len(missing_images_unique) + # Return up to some examples of missing files for debugging + sample_missing = list(missing_images_unique)[:50] + return stats, sample_missing + + +def scan_base_dir(base_dir: str, max_lines: int = -1) -> Dict[str, Any]: + summary: Dict[str, Any] = dict(per_dataset={}, totals={}) + totals = dict( + datasets_scanned=0, + num_records=0, + num_invalid_json=0, + num_image_refs=0, + num_images_missing=0, + num_unique_images_missing=0, # accumulated across datasets (sum, not set-union) + num_video_refs=0, + num_videos_missing=0, + ) + + if not os.path.isdir(base_dir): + raise FileNotFoundError(f"Base dir does not exist: {base_dir}") + + # Pre-collect datasets that have labels.jsonl for better progress logging + ds_entries = [] + for entry in sorted(os.listdir(base_dir)): + ds_dir = os.path.join(base_dir, entry) + if not os.path.isdir(ds_dir): + continue + labels_path = os.path.join(ds_dir, "label", "labels.jsonl") + if os.path.isfile(labels_path): + ds_entries.append(entry) + + total_datasets = len(ds_entries) + for idx, entry in enumerate(ds_entries, 1): + ds_dir = os.path.join(base_dir, entry) + images_dir = os.path.join(ds_dir, "images") + labels_path = os.path.join(ds_dir, "label", "labels.jsonl") + + print(f"[{idx}/{total_datasets}] Scanning {entry} ...", flush=True) + + totals["datasets_scanned"] += 1 + ds_stats, sample_missing = process_labels_jsonl(images_dir, labels_path, max_lines=max_lines) + + summary["per_dataset"][entry] = dict(stats=ds_stats, sample_missing_images=sample_missing) + + # Accumulate totals (note: unique missing is summed per dataset) + for k in [ + "num_records", + "num_invalid_json", + "num_image_refs", + "num_images_missing", + "num_unique_images_missing", + "num_video_refs", + "num_videos_missing", + ]: + totals[k] += ds_stats[k] + + # Immediate per-dataset summary line + pct = 100.0 * ds_stats["num_images_missing"] / max(1, ds_stats["num_image_refs"]) + print( + f" -> records={ds_stats['num_records']}, image_refs={ds_stats['num_image_refs']}, " + f"missing_images={ds_stats['num_images_missing']} ({pct:.3f}%), videos_missing={ds_stats['num_videos_missing']}", + flush=True, + ) + + summary["totals"] = totals + return summary + + +def main(): + parser = argparse.ArgumentParser(description="Check VQA JSONL image/video references against images directories.") + parser.add_argument( + "--base_dir", + type=str, + default="./datasets/llava_onevision_vqa", + help="Root directory containing per-dataset subfolders with images/ and label/labels.jsonl", + ) + parser.add_argument( + "--max_lines", + type=int, + default=-1, + help="If >0, limit number of lines per JSONL file for a faster sample-based check.", + ) + parser.add_argument( + "--out_json", + type=str, + default="", + help="Optional path to write a JSON summary report.", + ) + + args = parser.parse_args() + + summary = scan_base_dir(args.base_dir, max_lines=args.max_lines) + + totals = summary["totals"] + print("==== VQA Consistency Check ====") + print( + f"Datasets: {totals['datasets_scanned']} | Records: {totals['num_records']} | " + f"Image refs: {totals['num_image_refs']} | Missing images: {totals['num_images_missing']} | " + f"Video refs: {totals['num_video_refs']} | Missing videos: {totals['num_videos_missing']}" + ) + if totals["num_image_refs"] > 0: + miss_pct = 100.0 * totals["num_images_missing"] / max(1, totals["num_image_refs"]) + print(f"Image missing rate: {miss_pct:.4f}%") + + # Print a few per-dataset highlights + for ds_name, data in list(summary["per_dataset"].items())[:20]: + s = data["stats"] + pct = 100.0 * s["num_images_missing"] / max(1, s["num_image_refs"]) + print( + f"- {ds_name}: records={s['num_records']}, image_refs={s['num_image_refs']}, " + f"missing_images={s['num_images_missing']} ({pct:.3f}%)" + ) + + if args.out_json: + with open(args.out_json, "w") as f: + json.dump(summary, f) + print(f"Summary written to {args.out_json}") + + +if __name__ == "__main__": + main() + + +# python data/any2any_preprocess/check_vqa.py --base_dir ./datasets/llava_onevision_vqa \ No newline at end of file diff --git a/data/any2any_preprocess/generate_parquest_grounding_canny_dino_global.py b/data/any2any_preprocess/generate_parquest_grounding_canny_dino_global.py new file mode 100644 index 0000000000000000000000000000000000000000..74d24faae7a8aea561a87f88107c9abfb86ef864 --- /dev/null +++ b/data/any2any_preprocess/generate_parquest_grounding_canny_dino_global.py @@ -0,0 +1,205 @@ +import os +import io +import glob +import tarfile +import logging +from typing import Dict, List, Optional + +import numpy as np +import pandas as pd + + +# Set up logging +logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') +logger = logging.getLogger(__name__) + + +class GlobalDinoReplacer: + def __init__(self, base_dir: str, + input_parquet_dir: Optional[str] = None, + global_dino_dir: Optional[str] = None, + output_parquet_dir: Optional[str] = None) -> None: + self.base_dir = base_dir + + # Defaults aligned with generate_parquet_grounding_canny_dino.py + self.input_parquet_dir = input_parquet_dir or os.path.join( + base_dir, 'parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino' + ) + self.global_dino_dir = global_dino_dir or os.path.join(base_dir, 'dinov2_global') + self.output_parquet_dir = output_parquet_dir or os.path.join( + base_dir, 'parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global' + ) + + os.makedirs(self.output_parquet_dir, exist_ok=True) + + def _list_input_parquets(self) -> List[str]: + files = glob.glob(os.path.join(self.input_parquet_dir, '*.parquet')) + return sorted(files) + + def _load_global_dino_from_tar(self, tar_path: str) -> Dict[str, np.ndarray]: + """Load all uid -> flattened tokens from a dinov2_global tar.""" + results: Dict[str, np.ndarray] = {} + + if not os.path.exists(tar_path): + logger.warning(f"Global DINO tar not found: {tar_path}") + return results + + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if not member.isfile(): + continue + name = member.name + if not name.endswith('_tokens_global.npy'): + continue + + file_obj = tar.extractfile(member) + if file_obj is None: + continue + + content = file_obj.read() + npy = np.load(io.BytesIO(content)) + + # Derive uid by stripping extension and the trailing `_tokens` + uid = os.path.splitext(name)[0] + if uid.endswith('_tokens_global'): + uid = uid[:-len('_tokens_global')] + + results[uid] = npy.flatten() + except Exception as e: + logger.error(f"Failed to read {tar_path}: {e}") + + return results + + def _replace_dino_column(self, df: pd.DataFrame, uid_to_tokens: Dict[str, np.ndarray], + strict: bool = False) -> pd.DataFrame: + if 'uid' not in df.columns: + raise ValueError("Input parquet missing required 'uid' column") + + num_rows = len(df) + replaced = 0 + missing = 0 + + # Prepare a new column without mutating during iteration to avoid pandas warnings + new_dino_column: List[object] = [] + for _, row in df.iterrows(): + uid = row['uid'] + tokens = uid_to_tokens.get(uid) + if tokens is None: + missing += 1 + if strict: + new_dino_column.append(None) + else: + # Keep original if present + new_dino_column.append(row.get('dino_global', None)) + else: + new_dino_column.append(tokens) + replaced += 1 + + logger.info(f"Replaced DINO tokens for {replaced}/{num_rows} rows; missing {missing}") + + if strict and missing > 0: + logger.error("Strict mode: some UIDs are missing global DINO tokens") + + df = df.copy() + df['dino_global'] = new_dino_column + return df + + def process_one_parquet(self, parquet_path: str, overwrite: bool = False, strict: bool = False) -> Optional[str]: + base_name = os.path.splitext(os.path.basename(parquet_path))[0] + out_path = os.path.join(self.output_parquet_dir, f"{base_name}.parquet") + + if os.path.exists(out_path) and not overwrite: + logger.info(f"Output exists, skipping: {out_path}") + return out_path + + # Load the input parquet + df = pd.read_parquet(parquet_path, engine='pyarrow') + + # Load corresponding global dino tar + global_dino_tar = os.path.join(self.global_dino_dir, f"{base_name}.tar") + logger.info(f"Loading global DINO tokens from: {global_dino_tar}") + uid_to_tokens = self._load_global_dino_from_tar(global_dino_tar) + + + if not uid_to_tokens: + logger.warning(f"No tokens loaded from {global_dino_tar}; leaving original 'dino' values") + + # Replace column + df = self._replace_dino_column(df, uid_to_tokens, strict=strict) + + # Persist + df.to_parquet( + out_path, + index=False, + engine='pyarrow', + compression='snappy', + row_group_size=1000, + ) + logger.info(f"Wrote updated parquet with global DINO to: {out_path}") + return out_path + + def process_all(self, overwrite: bool = False, strict: bool = False, + start_from: int = 0) -> List[str]: + inputs = self._list_input_parquets() + if start_from > 0: + inputs = inputs[start_from:] + + if not inputs: + logger.error("No input parquet files found") + return [] + + logger.info(f"Found {len(inputs)} parquet files to update") + outputs: List[str] = [] + for parquet_path in inputs: + try: + result = self.process_one_parquet(parquet_path, overwrite=overwrite, strict=strict) + if result: + outputs.append(result) + except Exception as e: + logger.error(f"Error processing {parquet_path}: {e}") + + logger.info(f"Successfully wrote {len(outputs)} updated parquet files") + return outputs + + +def main() -> None: + import argparse + + parser = argparse.ArgumentParser(description='Replace DINO tokens in existing parquet files with dinov2_global tokens') + parser.add_argument('--base_dir', type=str, default='./datasets/blip3o', + help='Base directory (default: ./datasets/blip3o)') + parser.add_argument('--input_parquet_dir', type=str, default=None, + help='Input parquet directory; defaults to parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino') + parser.add_argument('--global_dino_dir', type=str, default=None, + help='Directory containing dinov2_global tars; defaults to base_dir/dinov2_global') + parser.add_argument('--output_parquet_dir', type=str, default=None, + help='Output parquet directory; defaults to parquet_*_dino_global') + parser.add_argument('--overwrite', action='store_true', help='Overwrite existing output parquet if present') + parser.add_argument('--strict', action='store_true', + help='If set, missing UIDs in global DINO will set dino=None and log error') + parser.add_argument('--start_from', type=int, default=0, + help='Index to start processing from (for resuming)') + + args = parser.parse_args() + + replacer = GlobalDinoReplacer( + base_dir=args.base_dir, + input_parquet_dir=args.input_parquet_dir, + global_dino_dir=args.global_dino_dir, + output_parquet_dir=args.output_parquet_dir, + ) + + outputs = replacer.process_all(overwrite=args.overwrite, strict=args.strict, start_from=args.start_from) + if outputs: + logger.info("Outputs written:") + for p in outputs: + logger.info(f" - {p}") + else: + logger.error("No outputs were created") + + +if __name__ == '__main__': + main() + + diff --git a/data/any2any_preprocess/generate_parquet.py b/data/any2any_preprocess/generate_parquet.py new file mode 100644 index 0000000000000000000000000000000000000000..6f0ca68fd42e61f4f49ac2a85cfd1453bde9918f --- /dev/null +++ b/data/any2any_preprocess/generate_parquet.py @@ -0,0 +1,229 @@ +import os +import tarfile +import pandas as pd +import numpy as np +from PIL import Image +import io +import glob +import json +from tqdm import tqdm +import logging + +# Set up logging +logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') +logger = logging.getLogger(__name__) + +class TarProcessor: + def __init__(self, base_dir): + self.base_dir = base_dir + self.rgb_caption_dir = os.path.join(base_dir, 'datasets') + self.depth_dir = os.path.join(base_dir, 'datasets_depth') + self.normal_dir = os.path.join(base_dir, 'datasets_normal') + self.det_seg_dir = os.path.join(base_dir, 'datasets_seg_swinb') + self.parquet_dir = os.path.join(base_dir, 'parquet_rgb_caption_depth_normal_det_seg') + + # Create parquet directory if it doesn't exist + os.makedirs(self.parquet_dir, exist_ok=True) + + def get_tar_files(self): + """Get all tar files from rgb_caption directory""" + tar_files = glob.glob(os.path.join(self.rgb_caption_dir, '*.tar')) + return sorted(tar_files) + + def extract_from_tar(self, tar_path, file_type): + """ + Extract images and captions from tar file + + Args: + tar_path: Path to tar file + file_type: 'rgb_caption', 'depth', 'normal', 'det_seg' + """ + data = {} + + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if member.isfile(): + filename = member.name + uid = os.path.splitext(filename)[0] # Remove extension + + # Extract file content + f = tar.extractfile(member) + if f is None: + continue + + content = f.read() + + if file_type == 'rgb_caption': + # Handle RGB + caption files + if filename.endswith('.jpg') or filename.endswith('.jpeg') or filename.endswith('.png'): + data[uid] = {'image': content, 'caption': None} + elif filename.endswith('.txt'): + # Find corresponding image + base_name = os.path.splitext(filename)[0] + if base_name in data: + data[base_name]['caption'] = content.decode('utf-8').strip() + else: + data[base_name] = {'image': None, 'caption': content.decode('utf-8').strip()} + + elif file_type == 'depth': + # Handle depth maps (PNG format) + if filename.endswith('.png'): + data[uid] = content + + elif file_type == 'normal': + # Handle normal maps (RGB format) + if filename.endswith('.jpg') or filename.endswith('.jpeg') or filename.endswith('.png'): + data[uid] = content + elif file_type == 'det_seg': + # Handle detection maps (JSON format) + if filename.endswith('.json'): + # Decode bytes to string and parse JSON + json_str = content.decode('utf-8') + json_data = json.loads(json_str) + data[uid] = json_data + except Exception as e: + logger.error(f"Error processing {tar_path}: {e}") + return {} + + return data + + def process_tar_file(self, rgb_caption_tar): + """Process a single tar file and create corresponding parquet""" + + # Extract base name (e.g., 'sa_000000' from 'sa_000000.tar') + base_name = os.path.splitext(os.path.basename(rgb_caption_tar))[0] + + # Construct paths for corresponding depth and normal tar files + depth_tar = os.path.join(self.depth_dir, f"{base_name}.tar") + normal_tar = os.path.join(self.normal_dir, f"{base_name}.tar") + det_seg_tar = os.path.join(self.det_seg_dir, f"{base_name}.tar") + + logger.info(f"Processing {base_name}") + + # Check if corresponding files exist + if not os.path.exists(depth_tar): + logger.warning(f"Depth tar file not found: {depth_tar}") + return None + if not os.path.exists(normal_tar): + logger.warning(f"Normal tar file not found: {normal_tar}") + return None + if not os.path.exists(det_seg_tar): + logger.warning(f"Det seg tar file not found: {det_seg_tar}") + return None + + # Extract data from all three tar files + logger.info(f"Extracting from rgb_caption: {rgb_caption_tar}") + rgb_caption_data = self.extract_from_tar(rgb_caption_tar, 'rgb_caption') + + logger.info(f"Extracting from depth: {depth_tar}") + depth_data = self.extract_from_tar(depth_tar, 'depth') + + logger.info(f"Extracting from normal: {normal_tar}") + normal_data = self.extract_from_tar(normal_tar, 'normal') + + logger.info(f"Extracting from det_seg: {det_seg_tar}") + det_seg_data = self.extract_from_tar(det_seg_tar, 'det_seg') + + # Find common UIDs + logger.info(f"rgb_caption_data.keys() - det_seg_data.keys(): {len(set(rgb_caption_data.keys())) - len(set(det_seg_data.keys()))}") + common_uids = set(rgb_caption_data.keys()) & set(depth_data.keys()) & set(normal_data.keys()) & set(det_seg_data.keys()) + + if not common_uids: + logger.warning(f"No common UIDs found for {base_name}") + return None + + logger.info(f"Found {len(common_uids)} common UIDs") + + # Sort UIDs for consistent ordering + sorted_uids = sorted(common_uids) + logger.info(f"Sorted {len(sorted_uids)} UIDs") + + # Create DataFrame + rows = [] + for uid in tqdm(sorted_uids, desc=f"Processing {base_name}"): + rgb_info = rgb_caption_data[uid] + + # Skip if missing image or caption + if rgb_info['image'] is None or rgb_info['caption'] is None: + continue + + row = { + 'uid': uid, + 'rgb': rgb_info['image'], + 'caption': rgb_info['caption'], + 'depth': depth_data[uid], + 'normal': normal_data[uid], + 'det_seg': det_seg_data[uid] + } + rows.append(row) + + if not rows: + logger.warning(f"No valid rows for {base_name}") + return None + + # Create DataFrame + df = pd.DataFrame(rows) + + # Debug information + logger.info(f"DataFrame shape: {df.shape}") + if not df.empty: + logger.info(f"Sample UIDs: {df['uid'].head().tolist()}") + logger.info(f"Data types: {df.dtypes.to_dict()}") + + # Save to parquet with better settings for dataset compatibility + output_path = os.path.join(self.parquet_dir, f"{base_name}.parquet") + + # Use better parquet settings for dataset compatibility + df.to_parquet( + output_path, + index=False, + engine='pyarrow', + compression='snappy', + row_group_size=1000 # Smaller row group size for more groups + ) + logger.info(f"Saved {len(df)} rows to {output_path}") + + return output_path + + def process_all_tars(self): + """Process all tar files and create corresponding parquet files""" + tar_files = self.get_tar_files() + + if not tar_files: + logger.error("No tar files found in rgb_caption directory") + return + + logger.info(f"Found {len(tar_files)} tar files to process") + + processed_files = [] + for tar_file in tar_files: + try: + output_path = self.process_tar_file(tar_file) + if output_path: + processed_files.append(output_path) + except Exception as e: + logger.error(f"Error processing {tar_file}: {e}") + + logger.info(f"Successfully processed {len(processed_files)} files") + return processed_files + +def main(): + # Set the base directory + base_dir = './datasets/blip3o' + + # Create processor + processor = TarProcessor(base_dir) + + # Process all tar files + processed_files = processor.process_all_tars() + + if processed_files: + logger.info(f"Successfully created {len(processed_files)} parquet files:") + for file in processed_files: + logger.info(f" - {file}") + else: + logger.error("No parquet files were created") + +if __name__ == "__main__": + main() diff --git a/data/any2any_preprocess/generate_parquet_clip448_imagebind.py b/data/any2any_preprocess/generate_parquet_clip448_imagebind.py new file mode 100644 index 0000000000000000000000000000000000000000..82f266e0841ca55bdb3d780bd4bed89b0f323ac4 --- /dev/null +++ b/data/any2any_preprocess/generate_parquet_clip448_imagebind.py @@ -0,0 +1,318 @@ +import os +import io +import glob +import tarfile +import logging +from typing import Dict, List, Optional, Tuple + +import numpy as np +import pandas as pd +from tqdm import tqdm + + +# Set up logging +logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') +logger = logging.getLogger(__name__) + + +class MultiModalEnricher: + """Read existing parquet files and add clip448 and imagebind columns from tar archives.""" + + def __init__(self, base_dir: str, + input_parquet_dir: Optional[str] = None, + clip448_dir: Optional[str] = None, + imagebind_dir: Optional[str] = None, + output_parquet_dir: Optional[str] = None) -> None: + self.base_dir = base_dir + + # Defaults + self.input_parquet_dir = input_parquet_dir or os.path.join( + base_dir, 'parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global' + ) + self.clip448_dir = clip448_dir or os.path.join(base_dir, 'datasets_clip448') + self.imagebind_dir = imagebind_dir or os.path.join(base_dir, 'datasets_imagebind') + self.output_parquet_dir = output_parquet_dir or os.path.join( + base_dir, 'parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind' + ) + + os.makedirs(self.output_parquet_dir, exist_ok=True) + + # ------------------------------------------------------------------ + # Listing helpers + # ------------------------------------------------------------------ + + def _list_input_parquets(self) -> List[str]: + files = glob.glob(os.path.join(self.input_parquet_dir, '*.parquet')) + return sorted(files) + + # ------------------------------------------------------------------ + # Tar loaders + # ------------------------------------------------------------------ + + def _load_clip448_from_tar(self, tar_path: str) -> Dict[str, np.ndarray]: + """Load uid -> flattened local tokens from a clip448 tar. + + Files inside: {uid}_tokens.npy (shape (28,28) int64) + """ + results: Dict[str, np.ndarray] = {} + + if not os.path.exists(tar_path): + logger.warning(f"CLIP448 tar not found: {tar_path}") + return results + + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if not member.isfile(): + continue + name = member.name + if not name.endswith('_tokens.npy'): + continue + + file_obj = tar.extractfile(member) + if file_obj is None: + continue + + content = file_obj.read() + npy = np.load(io.BytesIO(content)) + + # Derive uid: strip .npy then _tokens + uid = os.path.splitext(name)[0] # remove .npy + if uid.endswith('_tokens'): + uid = uid[:-len('_tokens')] + + results[uid] = npy.flatten() + except Exception as e: + logger.error(f"Failed to read CLIP448 tar {tar_path}: {e}") + + return results + + def _load_imagebind_from_tar(self, tar_path: str) -> Tuple[Dict[str, np.ndarray], Dict[str, np.ndarray]]: + """Load uid -> flattened tokens from an imagebind tar. + + Files inside: + {uid}_tokens.npy (local, shape (32,32) int64) + {uid}_tokens_global.npy (global, shape (16,1,1) int64) + + Returns (local_map, global_map). + """ + local_results: Dict[str, np.ndarray] = {} + global_results: Dict[str, np.ndarray] = {} + + if not os.path.exists(tar_path): + logger.warning(f"ImageBind tar not found: {tar_path}") + return local_results, global_results + + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if not member.isfile(): + continue + name = member.name + if not name.endswith('.npy'): + continue + + file_obj = tar.extractfile(member) + if file_obj is None: + continue + + content = file_obj.read() + npy = np.load(io.BytesIO(content)) + + base = os.path.splitext(name)[0] # remove .npy + + if base.endswith('_tokens_global'): + uid = base[:-len('_tokens_global')] + global_results[uid] = npy.flatten() + elif base.endswith('_tokens'): + uid = base[:-len('_tokens')] + local_results[uid] = npy.flatten() + except Exception as e: + logger.error(f"Failed to read ImageBind tar {tar_path}: {e}") + + return local_results, global_results + + # ------------------------------------------------------------------ + # Column addition + # ------------------------------------------------------------------ + + def _add_columns(self, df: pd.DataFrame, + clip448_map: Dict[str, np.ndarray], + ib_local_map: Dict[str, np.ndarray], + ib_global_map: Dict[str, np.ndarray], + strict: bool = False) -> pd.DataFrame: + """Add clip448, imagebind, and imagebind_global columns to *df*.""" + + if 'uid' not in df.columns: + raise ValueError("Input parquet missing required 'uid' column") + + num_rows = len(df) + stats = {'clip448': 0, 'imagebind': 0, 'imagebind_global': 0, + 'clip448_miss': 0, 'imagebind_miss': 0, 'imagebind_global_miss': 0} + + clip448_col: List[object] = [] + ib_local_col: List[object] = [] + ib_global_col: List[object] = [] + + for _, row in df.iterrows(): + uid = row['uid'] + + # clip448 + tokens = clip448_map.get(uid) + if tokens is None: + stats['clip448_miss'] += 1 + clip448_col.append(row.get('clip448', None) if not strict else None) + else: + clip448_col.append(tokens) + stats['clip448'] += 1 + + # imagebind local + tokens = ib_local_map.get(uid) + if tokens is None: + stats['imagebind_miss'] += 1 + ib_local_col.append(row.get('imagebind', None) if not strict else None) + else: + ib_local_col.append(tokens) + stats['imagebind'] += 1 + + # imagebind global + tokens = ib_global_map.get(uid) + if tokens is None: + stats['imagebind_global_miss'] += 1 + ib_global_col.append(row.get('imagebind_global', None) if not strict else None) + else: + ib_global_col.append(tokens) + stats['imagebind_global'] += 1 + + logger.info( + f"Rows: {num_rows} | " + f"clip448: {stats['clip448']} ok / {stats['clip448_miss']} miss | " + f"imagebind: {stats['imagebind']} ok / {stats['imagebind_miss']} miss | " + f"imagebind_global: {stats['imagebind_global']} ok / {stats['imagebind_global_miss']} miss" + ) + + if strict and (stats['clip448_miss'] or stats['imagebind_miss'] or stats['imagebind_global_miss']): + logger.error("Strict mode: some UIDs are missing tokens from one or more modalities") + + df = df.copy() + df['clip448'] = clip448_col + df['imagebind'] = ib_local_col + df['imagebind_global'] = ib_global_col + return df + + # ------------------------------------------------------------------ + # Processing + # ------------------------------------------------------------------ + + def process_one_parquet(self, parquet_path: str, overwrite: bool = False, + strict: bool = False) -> Optional[str]: + base_name = os.path.splitext(os.path.basename(parquet_path))[0] + out_path = os.path.join(self.output_parquet_dir, f"{base_name}.parquet") + + if os.path.exists(out_path) and not overwrite: + logger.info(f"Output exists, skipping: {out_path}") + return out_path + + # Load existing parquet + df = pd.read_parquet(parquet_path, engine='pyarrow') + + # Load clip448 tar + clip448_tar = os.path.join(self.clip448_dir, f"{base_name}.tar") + logger.info(f"Loading CLIP448 tokens from: {clip448_tar}") + clip448_map = self._load_clip448_from_tar(clip448_tar) + + # Load imagebind tar + imagebind_tar = os.path.join(self.imagebind_dir, f"{base_name}.tar") + logger.info(f"Loading ImageBind tokens from: {imagebind_tar}") + ib_local_map, ib_global_map = self._load_imagebind_from_tar(imagebind_tar) + + if not clip448_map: + logger.warning(f"No CLIP448 tokens loaded from {clip448_tar}") + if not ib_local_map: + logger.warning(f"No ImageBind local tokens loaded from {imagebind_tar}") + if not ib_global_map: + logger.warning(f"No ImageBind global tokens loaded from {imagebind_tar}") + + # Add new columns + df = self._add_columns(df, clip448_map, ib_local_map, ib_global_map, strict=strict) + + # Persist + df.to_parquet( + out_path, + index=False, + engine='pyarrow', + compression='snappy', + row_group_size=1000, + ) + logger.info(f"Wrote enriched parquet to: {out_path}") + return out_path + + def process_all(self, overwrite: bool = False, strict: bool = False, + start_from: int = 0) -> List[str]: + inputs = self._list_input_parquets() + if start_from > 0: + inputs = inputs[start_from:] + + if not inputs: + logger.error("No input parquet files found") + return [] + + logger.info(f"Found {len(inputs)} parquet files to enrich") + outputs: List[str] = [] + for parquet_path in tqdm(inputs, desc="Enriching parquets", unit="file"): + try: + result = self.process_one_parquet(parquet_path, overwrite=overwrite, strict=strict) + if result: + outputs.append(result) + except Exception as e: + logger.error(f"Error processing {parquet_path}: {e}") + + logger.info(f"Successfully wrote {len(outputs)} enriched parquet files") + return outputs + + +def main() -> None: + import argparse + + parser = argparse.ArgumentParser( + description='Add CLIP448 and ImageBind tokens to existing parquet files' + ) + parser.add_argument('--base_dir', type=str, default='./datasets/blip3o', + help='Base directory (default: ./datasets/blip3o)') + parser.add_argument('--input_parquet_dir', type=str, default=None, + help='Input parquet directory; defaults to parquet_*_dino_global') + parser.add_argument('--clip448_dir', type=str, default=None, + help='Directory containing clip448 tars; defaults to base_dir/datasets_clip448') + parser.add_argument('--imagebind_dir', type=str, default=None, + help='Directory containing imagebind tars; defaults to base_dir/datasets_imagebind') + parser.add_argument('--output_parquet_dir', type=str, default=None, + help='Output parquet directory; defaults to parquet_*_clip448_imagebind') + parser.add_argument('--overwrite', action='store_true', + help='Overwrite existing output parquet if present') + parser.add_argument('--strict', action='store_true', + help='If set, missing UIDs will set column=None and log error') + parser.add_argument('--start_from', type=int, default=0, + help='Index to start processing from (for resuming)') + + args = parser.parse_args() + + enricher = MultiModalEnricher( + base_dir=args.base_dir, + input_parquet_dir=args.input_parquet_dir, + clip448_dir=args.clip448_dir, + imagebind_dir=args.imagebind_dir, + output_parquet_dir=args.output_parquet_dir, + ) + + outputs = enricher.process_all(overwrite=args.overwrite, strict=args.strict, start_from=args.start_from) + if outputs: + logger.info("Outputs written:") + for p in outputs: + logger.info(f" - {p}") + else: + logger.error("No outputs were created") + + +if __name__ == '__main__': + main() + diff --git a/data/any2any_preprocess/generate_parquet_grounding.py b/data/any2any_preprocess/generate_parquet_grounding.py new file mode 100644 index 0000000000000000000000000000000000000000..a90bd23378371b64caa56aac900eb568c7020f15 --- /dev/null +++ b/data/any2any_preprocess/generate_parquet_grounding.py @@ -0,0 +1,583 @@ +import os +import tarfile +import pandas as pd +import numpy as np +from PIL import Image +import io +import glob +import json +from tqdm import tqdm +import logging +import pycocotools.mask as mask_util +import matplotlib.pyplot as plt + +# Set up logging +logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') +logger = logging.getLogger(__name__) + +class GroundingProcessor: + def __init__(self, base_dir): + self.base_dir = base_dir + self.rgb_caption_dir = os.path.join(base_dir, 'datasets') + self.depth_dir = os.path.join(base_dir, 'datasets_depth') + self.normal_dir = os.path.join(base_dir, 'datasets_normal') + self.det_seg_dir = os.path.join(base_dir, 'datasets_seg_swinb') + self.grounding_dir = os.path.join(base_dir, 'datasets_grounding') # Pre-processed grounding tars + self.parquet_dir = os.path.join(base_dir, 'parquet_rgb_caption_depth_normal_det_seg_grounding') + + # Create parquet directory if it doesn't exist + os.makedirs(self.parquet_dir, exist_ok=True) + + def get_tar_files(self): + """Get all tar files from rgb_caption directory""" + tar_files = glob.glob(os.path.join(self.rgb_caption_dir, '*.tar')) + return sorted(tar_files) + + + def extract_from_tar(self, tar_path, file_type): + """ + Extract data from tar file + + Args: + tar_path: Path to tar file + file_type: 'rgb_caption', 'depth', 'normal', 'det_seg', 'grounding' + """ + data = {} + + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if member.isfile(): + filename = member.name + uid = os.path.splitext(filename)[0] # Remove extension + + # Extract file content + f = tar.extractfile(member) + if f is None: + continue + + content = f.read() + + if file_type == 'rgb_caption': + # Handle RGB + caption files + if filename.endswith('.jpg') or filename.endswith('.jpeg') or filename.endswith('.png'): + data[uid] = {'image': content, 'caption': None} + elif filename.endswith('.txt'): + # Find corresponding image + base_name = os.path.splitext(filename)[0] + if base_name in data: + data[base_name]['caption'] = content.decode('utf-8').strip() + else: + data[base_name] = {'image': None, 'caption': content.decode('utf-8').strip()} + + elif file_type == 'depth': + # Handle depth maps (PNG format) + if filename.endswith('.png'): + data[uid] = content + + elif file_type == 'normal': + # Handle normal maps (RGB format) + if filename.endswith('.jpg') or filename.endswith('.jpeg') or filename.endswith('.png'): + data[uid] = content + + elif file_type == 'det_seg': + # Handle detection maps (JSON format) + if filename.endswith('.json'): + # Decode bytes to string and parse JSON + json_str = content.decode('utf-8') + json_data = json.loads(json_str) + data[uid] = json_data + + elif file_type == 'grounding': + # Handle grounding JSON files + if filename.endswith('.json'): + # Decode bytes to string and parse JSON + json_str = content.decode('utf-8') + json_data = json.loads(json_str) + data[uid] = json_data + except Exception as e: + logger.error(f"Error processing {tar_path}: {e}") + return {} + + return data + + + def extract_grounding_data(self, grounding_data): + """Extract grounding information from JSON data""" + if not grounding_data: + return None + + # Get the first (and usually only) key which is the image name + image_key = list(grounding_data.keys())[0] + image_data = grounding_data[image_key] + + # Extract objects and their bounding boxes + objects = image_data.get('objects', []) + floating_objects = image_data.get('floating_objects', []) + + # Extract grounding relationships + relationships = image_data.get('relationships', {}) + grounding_phrases = relationships.get('grounding', []) + + # Extract captions with grounding details + short_captions = image_data.get('short_captions', []) + dense_caption = image_data.get('dense_caption', {}) + + return { + 'objects': objects, + 'floating_objects': floating_objects, + 'grounding_phrases': grounding_phrases, + 'short_captions': short_captions, + 'dense_caption': dense_caption + } + + def normalize_bbox(self, bbox, image_size): + """Normalize bbox to 0-999 based on image dimensions""" + if not bbox or len(bbox) != 4: + return [] + + # RLE format: size = [width, height] + img_height, img_width = image_size + + x1, y1, x2, y2 = bbox + + # Normalize to 0-999 and clamp values + norm_x1 = max(0, min(999, int((x1 / img_width) * 999))) + norm_y1 = max(0, min(999, int((y1 / img_height) * 999))) + norm_x2 = max(0, min(999, int((x2 / img_width) * 999))) + norm_y2 = max(0, min(999, int((y2 / img_height) * 999))) + + return [norm_x1, norm_y1, norm_x2, norm_y2] + + + def resize_and_crop_bbox(self, bbox, orig_size, target_size=512): + """ + Resize and center-crop a bounding box using CLIP/BLIP-style transform. + + Args: + bbox: list or tuple [x1, y1, x2, y2] in pixel coords. + orig_size: [W, H] original image size. + target_size: int, final square crop size (default=512). + + Returns: + [x1', y1', x2', y2'] after resize+crop. + Also returns (scale, left, top) for debugging. + """ + if not bbox or len(bbox) != 4: + return [] + + H, W = orig_size + x1, y1, x2, y2 = bbox + + # --- 1. Resize (keep aspect ratio, short side -> target_size) --- + scale = target_size / min(W, H) + new_W, new_H = W * scale, H * scale + + # --- 2. Center crop to target_size×target_size --- + left = max(0, (new_W - target_size) / 2) + top = max(0, (new_H - target_size) / 2) + + # --- 3. Apply transform to bbox --- + x1_new = x1 * scale - left + y1_new = y1 * scale - top + x2_new = x2 * scale - left + y2_new = y2 * scale - top + + # Clip to [0, target_size] + x1_new, y1_new, x2_new, y2_new = np.clip( + [x1_new, y1_new, x2_new, y2_new], + 0, target_size + ) + + return [x1_new, y1_new, x2_new, y2_new] + + + def visualize_rle_mask(self, rle_data, save_path=None): + """Visualize RLE mask from segmentation data""" + try: + # Decode RLE to binary mask + mask = mask_util.decode(rle_data) + + # Create visualization + fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 6)) + + # Show mask + ax1.imshow(mask, cmap='gray') + ax1.set_title('RLE Mask') + ax1.axis('off') + + # Show mask with bbox overlay + ax2.imshow(mask, cmap='gray', alpha=0.7) + + # Add bbox if available + if 'bbox' in rle_data: + bbox = rle_data['bbox'] + x1, y1, x2, y2 = bbox + width = x2 - x1 + height = y2 - y1 + rect = plt.Rectangle((x1, y1), width, height, + fill=False, edgecolor='red', linewidth=2) + ax2.add_patch(rect) + ax2.set_title('Mask + Bbox') + else: + ax2.set_title('Mask Only') + ax2.axis('off') + + plt.tight_layout() + + if save_path: + plt.savefig(save_path, dpi=150, bbox_inches='tight') + logger.info(f"Mask visualization saved to {save_path}") + else: + plt.show() + + plt.close() + + except Exception as e: + logger.error(f"Error visualizing RLE mask: {e}") + + def visualize_object_mask(self, grounding_data, uid, object_id=0, save_path=None): + """Visualize a specific object's mask from grounding data""" + try: + if not grounding_data or 'objects' not in grounding_data: + logger.warning(f"No objects found for {uid}") + return + + objects = grounding_data['objects'] + if object_id >= len(objects): + logger.warning(f"Object ID {object_id} not found for {uid}") + return + + obj = objects[object_id] + if 'segmentation' not in obj: + logger.warning(f"No segmentation found for object {object_id} in {uid}") + return + + segmentation = obj['segmentation'] + bbox = obj.get('bbox', []) + + # Create RLE data for visualization + rle_data = { + 'size': segmentation['size'], + 'counts': segmentation['counts'], + 'bbox': bbox + } + + # Visualize + if save_path: + save_path_with_id = save_path.replace('.png', f'_obj_{object_id}.png') + else: + save_path_with_id = None + + self.visualize_rle_mask(rle_data, save_path_with_id) + + except Exception as e: + logger.error(f"Error visualizing object mask for {uid}: {e}") + + def create_grounding_samples(self, grounding_data, uid): + """Create training samples from grounding data""" + if not grounding_data: + return [] + + samples = [] + + # Get image size from first object's segmentation + image_size = None + if grounding_data['objects'] and 'segmentation' in grounding_data['objects'][0]: + image_size = grounding_data['objects'][0]['segmentation']['size'] + assert image_size is not None + else: + logger.warning(f"No segmentation data found for {uid}, skipping bbox processing") + return [] + + # Process grounding phrases + for phrase_info in grounding_data['grounding_phrases']: + phrase = phrase_info['phrase'] + object_ids = phrase_info['object_ids'] + + # Find corresponding objects and their bboxes + for obj_id in object_ids: + for obj in grounding_data['objects']: + if obj.get('id') == obj_id: + bbox = obj.get('bbox', []) + + # Process bbox if valid + if bbox and len(bbox) == 4: + bbox = self.resize_and_crop_bbox(bbox, image_size, 512) + bbox = self.normalize_bbox(bbox, [512, 512]) + else: + bbox = [] + + sample = { + 'uid': uid, + 'phrase': phrase, + 'object_id': obj_id, + 'bbox': bbox, + 'labels': obj.get('labels', []), + 'attributes': obj.get('attributes', []), + 'sample_type': 'grounding_phrase', + 'segmentation': obj.get('segmentation', []), + } + samples.append(sample) + break + + # Process short captions with details + for caption_info in grounding_data['short_captions']: + caption = caption_info['caption'] + for detail in caption_info.get('details', []): + phrase = detail['phrase'] + object_id = detail.get('id') + bbox = detail.get('bbox', []) + + # Process bbox if valid + if bbox and len(bbox) == 4: + bbox = self.resize_and_crop_bbox(bbox, image_size, 512) + bbox = self.normalize_bbox(bbox, [512, 512]) + else: + bbox = [] + + tokens_positive = detail.get('tokens_positive', []) + + sample = { + 'uid': uid, + 'phrase': phrase, + 'caption_id': object_id, + 'bbox': bbox, + 'tokens_positive': tokens_positive, + 'full_caption': caption, + 'sample_type': 'short_caption' + } + samples.append(sample) + + # # Process dense caption + # if grounding_data['dense_caption']: + # dense_caption = grounding_data['dense_caption'] + # caption = dense_caption.get('caption', '') + # for detail in dense_caption.get('details', []): + # phrase = detail['phrase'] + # object_ids = detail.get('ids', []) + # bboxes = detail.get('bbox', []) + # tokens_positive = detail.get('tokens_positive', []) + + # sample = { + # 'uid': uid, + # 'phrase': phrase, + # 'object_ids': object_ids, + # 'bboxes': bboxes, + # 'tokens_positive': tokens_positive, + # 'full_caption': caption, + # 'sample_type': 'dense_caption' + # } + # samples.append(sample) + + return samples + + def process_tar_file(self, rgb_caption_tar): + """Process a single tar file and create corresponding parquet""" + + # Extract base name (e.g., 'sa_000000' from 'sa_000000.tar') + base_name = os.path.splitext(os.path.basename(rgb_caption_tar))[0] + + # Construct paths for corresponding depth, normal, det_seg, grounding tar files + depth_tar = os.path.join(self.depth_dir, f"{base_name}.tar") + normal_tar = os.path.join(self.normal_dir, f"{base_name}.tar") + det_seg_tar = os.path.join(self.det_seg_dir, f"{base_name}.tar") + grounding_tar = os.path.join(self.grounding_dir, f"{base_name}.tar") + + logger.info(f"Processing {base_name}") + + # Check if corresponding files exist + if not os.path.exists(depth_tar): + logger.warning(f"Depth tar file not found: {depth_tar}") + return None + if not os.path.exists(normal_tar): + logger.warning(f"Normal tar file not found: {normal_tar}") + return None + if not os.path.exists(det_seg_tar): + logger.warning(f"Det seg tar file not found: {det_seg_tar}") + return None + # Initialize grounding_data + grounding_data = {} + + if not os.path.exists(grounding_tar): + logger.warning(f"Grounding tar file not found: {grounding_tar} - will process without grounding data") + else: + logger.info(f"Extracting from grounding: {grounding_tar}") + grounding_data = self.extract_from_tar(grounding_tar, 'grounding') + + # Extract data from all tar files + logger.info(f"Extracting from rgb_caption: {rgb_caption_tar}") + rgb_caption_data = self.extract_from_tar(rgb_caption_tar, 'rgb_caption') + + logger.info(f"Extracting from depth: {depth_tar}") + depth_data = self.extract_from_tar(depth_tar, 'depth') + + logger.info(f"Extracting from normal: {normal_tar}") + normal_data = self.extract_from_tar(normal_tar, 'normal') + + logger.info(f"Extracting from det_seg: {det_seg_tar}") + det_seg_data = self.extract_from_tar(det_seg_tar, 'det_seg') + + # Find common UIDs (grounding is optional) + common_uids = set(rgb_caption_data.keys()) & set(depth_data.keys()) & set(normal_data.keys()) & set(det_seg_data.keys()) + + if not common_uids: + logger.warning(f"No common UIDs found for {base_name}") + return None + + logger.info(f"Found {len(common_uids)} common UIDs") + + # Sort UIDs for consistent ordering + sorted_uids = sorted(common_uids) + + # Create samples for each UID + all_samples = [] + + for uid in sorted_uids: + rgb_info = rgb_caption_data[uid] + + # Skip if missing image or caption + if rgb_info['image'] is None or rgb_info['caption'] is None: + continue + + # Create base sample with all modalities + sample = { + 'uid': uid, + 'rgb': rgb_caption_data[uid]['image'], + 'caption': rgb_caption_data[uid]['caption'], + 'depth': depth_data[uid], + 'normal': normal_data[uid], + 'det_seg': det_seg_data[uid] + } + + # Add grounding data if available + if uid in grounding_data: + extracted_grounding = self.extract_grounding_data(grounding_data[uid]) + if extracted_grounding: + raw_image = Image.open(io.BytesIO(rgb_caption_data[uid]['image'])) + raw_image_size = raw_image.size + assert raw_image_size == (512, 512), f"Raw image size is {raw_image_size} but expected (512, 512) for {uid}" + grounding_samples = self.create_grounding_samples(extracted_grounding, uid) + if grounding_samples: + sample['grounding'] = grounding_samples + + # visualize_segmentation = sample['grounding'][1]['segmentation'] + # self.visualize_rle_mask(visualize_segmentation,save_path=f"visualize_{uid}_1.png") + all_samples.append(sample) + + if not all_samples: + logger.warning(f"No samples found for {base_name}") + return None + + # Create DataFrame + df = pd.DataFrame(all_samples) + + # Debug information + logger.info(f"DataFrame shape: {df.shape}") + if not df.empty: + logger.info(f"Sample UIDs: {df['uid'].head().tolist()}") + # Count grounding samples + grounding_counts = [] + for _, row in df.iterrows(): + if 'grounding' in row and row['grounding'] is not None and isinstance(row['grounding'], list): + grounding_counts.append(len(row['grounding'])) + else: + grounding_counts.append(0) + if grounding_counts: + logger.info(f"Grounding samples per row: {np.mean(grounding_counts):.2f} avg, {max(grounding_counts)} max") + else: + logger.info("No grounding samples found") + + # Save to parquet + output_path = os.path.join(self.parquet_dir, f"{base_name}.parquet") + + df.to_parquet( + output_path, + index=False, + engine='pyarrow', + compression='snappy', + row_group_size=1000 + ) + logger.info(f"Saved {len(df)} grounding samples to {output_path}") + + return output_path + + def process_all_tars(self): + """Process all tar files and create corresponding parquet files""" + tar_files = self.get_tar_files() + + if not tar_files: + logger.error("No tar files found in rgb_caption directory") + return + + logger.info(f"Found {len(tar_files)} tar files to process") + + processed_files = [] + for tar_file in tar_files: + try: + output_path = self.process_tar_file(tar_file) + if output_path: + processed_files.append(output_path) + except Exception as e: + logger.error(f"Error processing {tar_file}: {e}") + + logger.info(f"Successfully processed {len(processed_files)} files") + return processed_files + +def main(): + import argparse + + parser = argparse.ArgumentParser(description='Generate parquet files with grounding data') + parser.add_argument('--base_dir', type=str, default='./datasets/blip3o', + help='Base directory (default: ./datasets/blip3o)') + parser.add_argument('--visualize_mask', action='store_true', + help='Visualize RLE masks for debugging') + parser.add_argument('--visualize_tar', type=str, default=None, + help='Specific tar file to visualize (e.g., sa_000001.tar)') + parser.add_argument('--visualize_uid', type=str, default=None, + help='Specific UID to visualize (e.g., sa_1)') + parser.add_argument('--visualize_object_id', type=int, default=0, + help='Object ID to visualize (default: 0)') + + args = parser.parse_args() + + # Set the base directory + base_dir = args.base_dir + + # Create processor + processor = GroundingProcessor(base_dir) + + # Visualize mask if requested + if args.visualize_mask and args.visualize_tar: + logger.info(f"Visualizing mask for {args.visualize_tar}, object {args.visualize_object_id}") + + # Find the grounding tar file for this UID + grounding_tar = os.path.join(processor.grounding_dir, f"{args.visualize_tar}.tar") + if os.path.exists(grounding_tar): + grounding_data = processor.extract_from_tar(grounding_tar, 'grounding') + if args.visualize_uid in grounding_data: + extracted_grounding = processor.extract_grounding_data(grounding_data[args.visualize_uid]) + if extracted_grounding: + save_path = f"mask_visualization_{args.visualize_uid}.png" + processor.visualize_object_mask(extracted_grounding, args.visualize_uid, + args.visualize_object_id, save_path) + else: + logger.error(f"No grounding data found for {args.visualize_uid}") + else: + logger.error(f"UID {args.visualize_uid} not found in grounding tar") + else: + logger.error(f"Grounding tar not found: {grounding_tar}") + return + + # Process all tar files + processed_files = processor.process_all_tars() + + if processed_files: + logger.info(f"Successfully created {len(processed_files)} grounding parquet files:") + for file in processed_files: + logger.info(f" - {file}") + else: + logger.error("No grounding parquet files were created") + +if __name__ == "__main__": + main() diff --git a/data/any2any_preprocess/generate_parquet_grounding_canny_dino.py b/data/any2any_preprocess/generate_parquet_grounding_canny_dino.py new file mode 100644 index 0000000000000000000000000000000000000000..d1be950b2ac8edad7ffd4f1887d25d58b48cc5b5 --- /dev/null +++ b/data/any2any_preprocess/generate_parquet_grounding_canny_dino.py @@ -0,0 +1,627 @@ +import os +import tarfile +import pandas as pd +import numpy as np +from PIL import Image +import io +import glob +import json +from tqdm import tqdm +import logging +import pycocotools.mask as mask_util +import matplotlib.pyplot as plt + +# Set up logging +logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') +logger = logging.getLogger(__name__) + +class GroundingProcessor: + def __init__(self, base_dir): + self.base_dir = base_dir + self.rgb_caption_dir = os.path.join(base_dir, 'datasets') + self.depth_dir = os.path.join(base_dir, 'datasets_depth') + self.normal_dir = os.path.join(base_dir, 'datasets_normal') + self.det_seg_dir = os.path.join(base_dir, 'datasets_seg_swinb') + self.grounding_dir = os.path.join(base_dir, 'datasets_grounding') # Pre-processed grounding tars + self.canny_dir = os.path.join(base_dir, 'datasets_cannyedge') + self.dino_dir = os.path.join(base_dir, 'dinov2') + self.parquet_dir = os.path.join(base_dir, 'parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino') + + # Create parquet directory if it doesn't exist + os.makedirs(self.parquet_dir, exist_ok=True) + + def get_tar_files(self): + """Get all tar files from rgb_caption directory""" + tar_files = glob.glob(os.path.join(self.rgb_caption_dir, '*.tar')) + return sorted(tar_files) + + + def extract_from_tar(self, tar_path, file_type): + """ + Extract data from tar file + + Args: + tar_path: Path to tar file + file_type: 'rgb_caption', 'depth', 'normal', 'det_seg', 'grounding', 'canny', 'dino' + """ + data = {} + + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if member.isfile(): + filename = member.name + uid = os.path.splitext(filename)[0] # Remove extension + + # Extract file content + f = tar.extractfile(member) + if f is None: + continue + + content = f.read() + + if file_type == 'rgb_caption': + # Handle RGB + caption files + if filename.endswith('.jpg') or filename.endswith('.jpeg') or filename.endswith('.png'): + data[uid] = {'image': content, 'caption': None} + elif filename.endswith('.txt'): + # Find corresponding image + base_name = os.path.splitext(filename)[0] + if base_name in data: + data[base_name]['caption'] = content.decode('utf-8').strip() + else: + data[base_name] = {'image': None, 'caption': content.decode('utf-8').strip()} + + elif file_type == 'depth': + # Handle depth maps (PNG format) + if filename.endswith('.png'): + data[uid] = content + + elif file_type == 'normal': + # Handle normal maps (RGB format) + if filename.endswith('.jpg') or filename.endswith('.jpeg') or filename.endswith('.png'): + data[uid] = content + + elif file_type == 'det_seg': + # Handle detection maps (JSON format) + if filename.endswith('.json'): + # Decode bytes to string and parse JSON + json_str = content.decode('utf-8') + json_data = json.loads(json_str) + data[uid] = json_data + + elif file_type == 'grounding': + # Handle grounding JSON files + if filename.endswith('.json'): + # Decode bytes to string and parse JSON + json_str = content.decode('utf-8') + json_data = json.loads(json_str) + data[uid] = json_data + + elif file_type == 'canny': + # Handle Canny maps (PNG format, similar to depth) + if filename.endswith('.png'): + data[uid] = content + + elif file_type == 'dino': + # Handle DINOv2 features (NPY format) + if filename.endswith('_tokens.npy'): + # Load NPY data from bytes + npy_data = np.load(io.BytesIO(content)) + uid = uid[:-len('_tokens')] + # Flatten the array for parquet storage + data[uid] = npy_data.flatten() + except Exception as e: + logger.error(f"Error processing {tar_path}: {e}") + return {} + + return data + + def extract_grounding_data(self, grounding_data): + """Extract grounding information from JSON data""" + if not grounding_data: + return None + + # Get the first (and usually only) key which is the image name + image_key = list(grounding_data.keys())[0] + image_data = grounding_data[image_key] + + # Extract objects and their bounding boxes + objects = image_data.get('objects', []) + floating_objects = image_data.get('floating_objects', []) + + # Extract grounding relationships + relationships = image_data.get('relationships', {}) + grounding_phrases = relationships.get('grounding', []) + + # Extract captions with grounding details + short_captions = image_data.get('short_captions', []) + dense_caption = image_data.get('dense_caption', {}) + + return { + 'objects': objects, + 'floating_objects': floating_objects, + 'grounding_phrases': grounding_phrases, + 'short_captions': short_captions, + 'dense_caption': dense_caption + } + + def normalize_bbox(self, bbox, image_size): + """Normalize bbox to 0-999 based on image dimensions""" + if not bbox or len(bbox) != 4: + return [] + + # RLE format: size = [width, height] + img_height, img_width = image_size + + x1, y1, x2, y2 = bbox + + # Normalize to 0-999 and clamp values + norm_x1 = max(0, min(999, int((x1 / img_width) * 999))) + norm_y1 = max(0, min(999, int((y1 / img_height) * 999))) + norm_x2 = max(0, min(999, int((x2 / img_width) * 999))) + norm_y2 = max(0, min(999, int((y2 / img_height) * 999))) + + return [norm_x1, norm_y1, norm_x2, norm_y2] + + + def resize_and_crop_bbox(self, bbox, orig_size, target_size=512): + """ + Resize and center-crop a bounding box using CLIP/BLIP-style transform. + + Args: + bbox: list or tuple [x1, y1, x2, y2] in pixel coords. + orig_size: [W, H] original image size. + target_size: int, final square crop size (default=512). + + Returns: + [x1', y1', x2', y2'] after resize+crop. + Also returns (scale, left, top) for debugging. + """ + if not bbox or len(bbox) != 4: + return [] + + H, W = orig_size + x1, y1, x2, y2 = bbox + + # --- 1. Resize (keep aspect ratio, short side -> target_size) --- + scale = target_size / min(W, H) + new_W, new_H = W * scale, H * scale + + # --- 2. Center crop to target_size×target_size --- + left = max(0, (new_W - target_size) / 2) + top = max(0, (new_H - target_size) / 2) + + # --- 3. Apply transform to bbox --- + x1_new = x1 * scale - left + y1_new = y1 * scale - top + x2_new = x2 * scale - left + y2_new = y2 * scale - top + + # Clip to [0, target_size] + x1_new, y1_new, x2_new, y2_new = np.clip( + [x1_new, y1_new, x2_new, y2_new], + 0, target_size + ) + + return [x1_new, y1_new, x2_new, y2_new] + + + def visualize_rle_mask(self, rle_data, save_path=None): + """Visualize RLE mask from segmentation data""" + try: + # Decode RLE to binary mask + mask = mask_util.decode(rle_data) + + # Create visualization + fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(12, 6)) + + # Show mask + ax1.imshow(mask, cmap='gray') + ax1.set_title('RLE Mask') + ax1.axis('off') + + # Show mask with bbox overlay + ax2.imshow(mask, cmap='gray', alpha=0.7) + + # Add bbox if available + if 'bbox' in rle_data: + bbox = rle_data['bbox'] + x1, y1, x2, y2 = bbox + width = x2 - x1 + height = y2 - y1 + rect = plt.Rectangle((x1, y1), width, height, + fill=False, edgecolor='red', linewidth=2) + ax2.add_patch(rect) + ax2.set_title('Mask + Bbox') + else: + ax2.set_title('Mask Only') + ax2.axis('off') + + plt.tight_layout() + + if save_path: + plt.savefig(save_path, dpi=150, bbox_inches='tight') + logger.info(f"Mask visualization saved to {save_path}") + else: + plt.show() + + plt.close() + + except Exception as e: + logger.error(f"Error visualizing RLE mask: {e}") + + def visualize_object_mask(self, grounding_data, uid, object_id=0, save_path=None): + """Visualize a specific object's mask from grounding data""" + try: + if not grounding_data or 'objects' not in grounding_data: + logger.warning(f"No objects found for {uid}") + return + + objects = grounding_data['objects'] + if object_id >= len(objects): + logger.warning(f"Object ID {object_id} not found for {uid}") + return + + obj = objects[object_id] + if 'segmentation' not in obj: + logger.warning(f"No segmentation found for object {object_id} in {uid}") + return + + segmentation = obj['segmentation'] + bbox = obj.get('bbox', []) + + # Create RLE data for visualization + rle_data = { + 'size': segmentation['size'], + 'counts': segmentation['counts'], + 'bbox': bbox + } + + # Visualize + if save_path: + save_path_with_id = save_path.replace('.png', f'_obj_{object_id}.png') + else: + save_path_with_id = None + + self.visualize_rle_mask(rle_data, save_path_with_id) + + except Exception as e: + logger.error(f"Error visualizing object mask for {uid}: {e}") + + def create_grounding_samples(self, grounding_data, uid): + """Create training samples from grounding data""" + if not grounding_data: + return [] + + samples = [] + + # Get image size from first object's segmentation + image_size = None + if grounding_data['objects'] and 'segmentation' in grounding_data['objects'][0]: + image_size = grounding_data['objects'][0]['segmentation']['size'] + assert image_size is not None + else: + logger.warning(f"No segmentation data found for {uid}, skipping bbox processing") + return [] + + # Process grounding phrases + for phrase_info in grounding_data['grounding_phrases']: + phrase = phrase_info['phrase'] + object_ids = phrase_info['object_ids'] + + # Find corresponding objects and their bboxes + for obj_id in object_ids: + for obj in grounding_data['objects']: + if obj.get('id') == obj_id: + bbox = obj.get('bbox', []) + + # Process bbox if valid + if bbox and len(bbox) == 4: + bbox = self.resize_and_crop_bbox(bbox, image_size, 512) + bbox = self.normalize_bbox(bbox, [512, 512]) + else: + bbox = [] + + sample = { + 'uid': uid, + 'phrase': phrase, + 'object_id': obj_id, + 'bbox': bbox, + 'labels': obj.get('labels', []), + 'attributes': obj.get('attributes', []), + 'sample_type': 'grounding_phrase', + 'segmentation': obj.get('segmentation', []), + } + samples.append(sample) + break + + # Process short captions with details + for caption_info in grounding_data['short_captions']: + caption = caption_info['caption'] + for detail in caption_info.get('details', []): + phrase = detail['phrase'] + object_id = detail.get('id') + bbox = detail.get('bbox', []) + + # Process bbox if valid + if bbox and len(bbox) == 4: + bbox = self.resize_and_crop_bbox(bbox, image_size, 512) + bbox = self.normalize_bbox(bbox, [512, 512]) + else: + bbox = [] + + tokens_positive = detail.get('tokens_positive', []) + + sample = { + 'uid': uid, + 'phrase': phrase, + 'caption_id': object_id, + 'bbox': bbox, + 'tokens_positive': tokens_positive, + 'full_caption': caption, + 'sample_type': 'short_caption' + } + samples.append(sample) + + # # Process dense caption + # if grounding_data['dense_caption']: + # dense_caption = grounding_data['dense_caption'] + # caption = dense_caption.get('caption', '') + # for detail in dense_caption.get('details', []): + # phrase = detail['phrase'] + # object_ids = detail.get('ids', []) + # bboxes = detail.get('bbox', []) + # tokens_positive = detail.get('tokens_positive', []) + + # sample = { + # 'uid': uid, + # 'phrase': phrase, + # 'object_ids': object_ids, + # 'bboxes': bboxes, + # 'tokens_positive': tokens_positive, + # 'full_caption': caption, + # 'sample_type': 'dense_caption' + # } + # samples.append(sample) + + return samples + + def process_tar_file(self, rgb_caption_tar): + """Process a single tar file and create corresponding parquet""" + + # Extract base name (e.g., 'sa_000000' from 'sa_000000.tar') + base_name = os.path.splitext(os.path.basename(rgb_caption_tar))[0] + + # Construct paths for corresponding depth, normal, det_seg, grounding, canny, dino tar files + depth_tar = os.path.join(self.depth_dir, f"{base_name}.tar") + normal_tar = os.path.join(self.normal_dir, f"{base_name}.tar") + det_seg_tar = os.path.join(self.det_seg_dir, f"{base_name}.tar") + grounding_tar = os.path.join(self.grounding_dir, f"{base_name}.tar") + canny_tar = os.path.join(self.canny_dir, f"{base_name}.tar") + dino_tar = os.path.join(self.dino_dir, f"{base_name}.tar") + + logger.info(f"Processing {base_name}") + + # Check if corresponding files exist + if not os.path.exists(depth_tar): + logger.warning(f"Depth tar file not found: {depth_tar}") + return None + if not os.path.exists(normal_tar): + logger.warning(f"Normal tar file not found: {normal_tar}") + return None + if not os.path.exists(det_seg_tar): + logger.warning(f"Det seg tar file not found: {det_seg_tar}") + return None + if not os.path.exists(canny_tar): + logger.warning(f"Canny tar file not found: {canny_tar}") + return None + if not os.path.exists(dino_tar): + logger.warning(f"DINOv2 tar file not found: {dino_tar}") + return None + # Initialize grounding_data + grounding_data = {} + + if not os.path.exists(grounding_tar): + logger.warning(f"Grounding tar file not found: {grounding_tar} - will process without grounding data") + else: + logger.info(f"Extracting from grounding: {grounding_tar}") + grounding_data = self.extract_from_tar(grounding_tar, 'grounding') + + # Extract data from all tar files + logger.info(f"Extracting from rgb_caption: {rgb_caption_tar}") + rgb_caption_data = self.extract_from_tar(rgb_caption_tar, 'rgb_caption') + + logger.info(f"Extracting from depth: {depth_tar}") + depth_data = self.extract_from_tar(depth_tar, 'depth') + + logger.info(f"Extracting from normal: {normal_tar}") + normal_data = self.extract_from_tar(normal_tar, 'normal') + + logger.info(f"Extracting from det_seg: {det_seg_tar}") + det_seg_data = self.extract_from_tar(det_seg_tar, 'det_seg') + + logger.info(f"Extracting from canny: {canny_tar}") + canny_data = self.extract_from_tar(canny_tar, 'canny') + + logger.info(f"Extracting from dino: {dino_tar}") + dino_data = self.extract_from_tar(dino_tar, 'dino') + + # Find common UIDs (grounding is optional) + common_uids = set(rgb_caption_data.keys()) & set(depth_data.keys()) & set(normal_data.keys()) & set(det_seg_data.keys()) & set(canny_data.keys()) & set(dino_data.keys()) + + if not common_uids: + logger.warning(f"No common UIDs found for {base_name}") + return None + + logger.info(f"Found {len(common_uids)} common UIDs") + + # Sort UIDs for consistent ordering + sorted_uids = sorted(common_uids) + + # Create samples for each UID + all_samples = [] + + for uid in sorted_uids: + rgb_info = rgb_caption_data[uid] + + # Skip if missing image or caption + if rgb_info['image'] is None or rgb_info['caption'] is None: + continue + + # Create base sample with all modalities + sample = { + 'uid': uid, + 'rgb': rgb_caption_data[uid]['image'], + 'caption': rgb_caption_data[uid]['caption'], + 'depth': depth_data[uid], + 'normal': normal_data[uid], + 'det_seg': det_seg_data[uid], + 'canny': canny_data[uid], + 'dino': dino_data[uid] + } + + # Add grounding data if available + if uid in grounding_data: + extracted_grounding = self.extract_grounding_data(grounding_data[uid]) + if extracted_grounding: + raw_image = Image.open(io.BytesIO(rgb_caption_data[uid]['image'])) + raw_image_size = raw_image.size + assert raw_image_size == (512, 512), f"Raw image size is {raw_image_size} but expected (512, 512) for {uid}" + grounding_samples = self.create_grounding_samples(extracted_grounding, uid) + if grounding_samples: + sample['grounding'] = grounding_samples + + # visualize_segmentation = sample['grounding'][1]['segmentation'] + # self.visualize_rle_mask(visualize_segmentation,save_path=f"visualize_{uid}_1.png") + all_samples.append(sample) + + if not all_samples: + logger.warning(f"No samples found for {base_name}") + return None + + # Create DataFrame + df = pd.DataFrame(all_samples) + + # Debug information + logger.info(f"DataFrame shape: {df.shape}") + if not df.empty: + logger.info(f"Sample UIDs: {df['uid'].head().tolist()}") + # Count grounding samples + grounding_counts = [] + for _, row in df.iterrows(): + if 'grounding' in row and row['grounding'] is not None and isinstance(row['grounding'], list): + grounding_counts.append(len(row['grounding'])) + else: + grounding_counts.append(0) + if grounding_counts: + logger.info(f"Grounding samples per row: {np.mean(grounding_counts):.2f} avg, {max(grounding_counts)} max") + else: + logger.info("No grounding samples found") + + # Count DINOv2 features + dino_counts = [] + for _, row in df.iterrows(): + if 'dino' in row and row['dino'] is not None: + dino_counts.append(1) + else: + dino_counts.append(0) + if dino_counts: + logger.info(f"DINOv2 features loaded: {sum(dino_counts)}/{len(dino_counts)} samples") + else: + logger.info("No DINOv2 features found") + + # Save to parquet + output_path = os.path.join(self.parquet_dir, f"{base_name}.parquet") + + df.to_parquet( + output_path, + index=False, + engine='pyarrow', + compression='snappy', + row_group_size=1000 + ) + logger.info(f"Saved {len(df)} grounding samples to {output_path}") + + return output_path + + def process_all_tars(self): + """Process all tar files and create corresponding parquet files""" + tar_files = self.get_tar_files() + + if not tar_files: + logger.error("No tar files found in rgb_caption directory") + return + + tar_files = tar_files[1373:] + logger.info(f"Found {len(tar_files)} tar files to process") + + processed_files = [] + for tar_file in tar_files: + try: + output_path = self.process_tar_file(tar_file) + if output_path: + processed_files.append(output_path) + except Exception as e: + logger.error(f"Error processing {tar_file}: {e}") + + logger.info(f"Successfully processed {len(processed_files)} files") + return processed_files + +def main(): + import argparse + + parser = argparse.ArgumentParser(description='Generate parquet files with grounding data') + parser.add_argument('--base_dir', type=str, default='./datasets/blip3o', + help='Base directory (default: ./datasets/blip3o)') + parser.add_argument('--visualize_mask', action='store_true', + help='Visualize RLE masks for debugging') + parser.add_argument('--visualize_tar', type=str, default=None, + help='Specific tar file to visualize (e.g., sa_000001.tar)') + parser.add_argument('--visualize_uid', type=str, default=None, + help='Specific UID to visualize (e.g., sa_1)') + parser.add_argument('--visualize_object_id', type=int, default=0, + help='Object ID to visualize (default: 0)') + + args = parser.parse_args() + + # Set the base directory + base_dir = args.base_dir + + # Create processor + processor = GroundingProcessor(base_dir) + + # Visualize mask if requested + if args.visualize_mask and args.visualize_tar: + logger.info(f"Visualizing mask for {args.visualize_tar}, object {args.visualize_object_id}") + + # Find the grounding tar file for this UID + grounding_tar = os.path.join(processor.grounding_dir, f"{args.visualize_tar}.tar") + if os.path.exists(grounding_tar): + grounding_data = processor.extract_from_tar(grounding_tar, 'grounding') + if args.visualize_uid in grounding_data: + extracted_grounding = processor.extract_grounding_data(grounding_data[args.visualize_uid]) + if extracted_grounding: + save_path = f"mask_visualization_{args.visualize_uid}.png" + processor.visualize_object_mask(extracted_grounding, args.visualize_uid, + args.visualize_object_id, save_path) + else: + logger.error(f"No grounding data found for {args.visualize_uid}") + else: + logger.error(f"UID {args.visualize_uid} not found in grounding tar") + else: + logger.error(f"Grounding tar not found: {grounding_tar}") + return + + # Process all tar files + processed_files = processor.process_all_tars() + + if processed_files: + logger.info(f"Successfully created {len(processed_files)} grounding parquet files:") + for file in processed_files: + logger.info(f" - {file}") + else: + logger.error("No grounding parquet files were created") + +if __name__ == "__main__": + main() diff --git a/data/any2any_preprocess/generate_parquet_json.py b/data/any2any_preprocess/generate_parquet_json.py new file mode 100644 index 0000000000000000000000000000000000000000..4d9e5a8dbc719bd760487553467e379fd8bd12cc --- /dev/null +++ b/data/any2any_preprocess/generate_parquet_json.py @@ -0,0 +1,69 @@ +import os +import json +import argparse +import pyarrow.parquet as pq +from pathlib import Path + +def get_parquet_info(file_path): + """Get information about a parquet file""" + try: + parquet_file = pq.ParquetFile(file_path) + num_row_groups = parquet_file.num_row_groups + + # Calculate total number of rows + total_rows = 0 + for i in range(num_row_groups): + total_rows += parquet_file.metadata.row_group(i).num_rows + + return { + "num_row_groups": num_row_groups, + "num_rows": total_rows + } + except Exception as e: + print(f"Error reading {file_path}: {e}") + return None + +def generate_parquet_info(parquet_dir=None, output_file=None): + """Generate information for all parquet files in the parquet folder""" + parquet_dir = Path(parquet_dir) if parquet_dir is not None else Path("./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind") + output_file = Path(output_file) if output_file is not None else Path("./datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json") + + # Create output directory if it doesn't exist + output_file.parent.mkdir(parents=True, exist_ok=True) + + # Get all parquet files + parquet_files = list(parquet_dir.glob("*.parquet")) + print(f"Found {len(parquet_files)} parquet files") + + # Process each file + parquet_info = {} + + for i, parquet_file in enumerate(parquet_files): + print(f"Processing {i+1}/{len(parquet_files)}: {parquet_file.name}") + + # Get relative path from current directory using parquet_dir + relative_path = str((parquet_dir / parquet_file.name)) + if not relative_path.startswith("./"): + relative_path = f"./{relative_path}" + + info = get_parquet_info(parquet_file) + if info: + parquet_info[relative_path] = info + print(f"Processed {parquet_file.name} successfully") + print(info) + else: + print(f"Failed to process {parquet_file.name}") + + # Save to JSON file + with open(output_file, 'w') as f: + json.dump(parquet_info, f, indent=2, sort_keys=True) + + print(f"Saved parquet information to {output_file}") + print(f"Processed {len(parquet_info)} files successfully") + +if __name__ == "__main__": + parser = argparse.ArgumentParser() + parser.add_argument("--parquet_dir", default=None) + parser.add_argument("--output_file", default=None) + args = parser.parse_args() + generate_parquet_info(parquet_dir=args.parquet_dir, output_file=args.output_file) diff --git a/data/any2any_preprocess/generate_parquet_vlm_sft.py b/data/any2any_preprocess/generate_parquet_vlm_sft.py new file mode 100644 index 0000000000000000000000000000000000000000..8f00a377ec09be11ec5542218bedfb0516b47d27 --- /dev/null +++ b/data/any2any_preprocess/generate_parquet_vlm_sft.py @@ -0,0 +1,278 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 +"""Bundle vlm_sft (llava-onevision style jsonl + loose image files) into +parquet shards loadable by SftParquetIterableDataset (data/vlm_dataset.py). + +Why: llava-onevision is ~4M small files, impractical to upload to / stream +from S3. The shards follow the blip3o convention: few large parquet files + +a parquet_info JSON, sharded by (file, row_group) at load time. + +Equivalence: the jsonl loader selects samples per subset via + rng = random.Random(); rng.seed(shuffle_seed); rng.shuffle(lines) + lines = lines[:num_used_data] +(SftJSONLIterableDataset.get_data_paths). This script replicates that +selection EXACTLY (taking shuffle_lines / shuffle_seed / num_used_data from +the same training yaml), so the parquet rows are precisely the records the +jsonl loader would have used, in the same shuffled order. + +Row schema: + record: str original jsonl line, verbatim + image_bytes: list raw image files (no re-encode), in the order + the jsonl loader's valid_paths would produce + +Skipped at conversion (mirroring the jsonl loader's runtime skips): + - records with 'video' (frame sampling can't be baked into bytes) + - records whose 'image' field resolves to zero existing files + +Usage (single process, all subsets of the group): + python3 data/any2any_preprocess/generate_parquet_vlm_sft.py \ + --config data/configs/modus_stage1.yaml --group vlm_sft \ + --out-dir ./datasets/llava_onevision_vqa_parquet + +Parallelize across subsets with disjoint --subsets lists (e.g. sbatch array); +each invocation only rewrites its own subsets' shards and merge-updates the +shared parquet_info JSON. Already-converted subsets are skipped unless +--overwrite is given. + +After conversion, point the training config at the new group: + vlm_sft_parquet: + dataset_names: + - llava_onevision_vqa + image_transform_args: { ...same as the old vlm_sft block... } + is_mandatory: true + weight: + (no num_used_data / shuffle_lines needed — selection is baked in) +""" + +import argparse +import json +import os +import random +import re +import sys +from concurrent.futures import ThreadPoolExecutor + +import pyarrow as pa +import pyarrow.parquet as pq +import yaml + +sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..', '..')) +from data.dataset_info import DATASET_INFO # noqa: E402 +from data.parquet_utils import apply_data_root_override, read_file_bytes # noqa: E402 + +SCHEMA = pa.schema([ + pa.field('record', pa.string()), + pa.field('image_bytes', pa.list_(pa.binary())), +]) + + +def sanitize(name): + # subset names contain '(', ',', ')' etc. — make a filesystem-safe stem + return re.sub(r'[^0-9A-Za-z_.-]+', '_', name).strip('_') + + +def _read_image_bytes(path): + if path.startswith('s3://'): + return read_file_bytes(path) + with open(path, 'rb') as f: + return f.read() + + +def _load_record_images(args): + """Worker: (raw_line, image_dir) -> (raw_line, image_bytes list, status). + status: 'ok' | 'skip_video' | 'skip_missing' | 'skip_badjson'.""" + raw_line, image_dir = args + try: + data_item = json.loads(raw_line) + except Exception: + return raw_line, None, 'skip_badjson' + if 'video' in data_item: + return raw_line, None, 'skip_video' + image_bytes = [] + if 'image' in data_item: + images = data_item['image'] if isinstance(data_item['image'], list) else [data_item['image']] + for img_name in images: + if not (isinstance(img_name, str) and img_name.strip() != ''): + continue + img_path = os.path.join(image_dir, img_name) + try: + image_bytes.append(_read_image_bytes(img_path)) + except (OSError, IOError): + continue # mirrors the jsonl loader dropping invalid paths + if len(image_bytes) == 0: + return raw_line, None, 'skip_missing' + return raw_line, image_bytes, 'ok' + + +def select_lines(jsonl_path, num_used_data, shuffle_lines, shuffle_seed): + """Replicates SftJSONLIterableDataset.get_data_paths line selection.""" + jsonl_path = apply_data_root_override(jsonl_path) + if jsonl_path.startswith('s3://'): + raw_data = read_file_bytes(jsonl_path).decode('utf-8').splitlines(keepends=True) + else: + with open(jsonl_path, 'r') as f: + raw_data = f.readlines() + if shuffle_lines: + rng = random.Random() + rng.seed(shuffle_seed) + rng.shuffle(raw_data) + return raw_data[:num_used_data] + + +def convert_subset(subset, jsonl_path, image_dir, num_used_data, shuffle_lines, + shuffle_seed, train_dir, rows_per_file, row_group_size, + io_threads, info_key_dir): + """Convert one subset to parquet shards. Returns (shard_info, stats): + shard_info: {info_key: {'num_row_groups': int, 'num_rows': int}}.""" + image_dir = apply_data_root_override(image_dir) + lines = select_lines(jsonl_path, num_used_data, shuffle_lines, shuffle_seed) + print(f'[convert] {subset}: selected {len(lines)} lines (quota {num_used_data})') + + stem = sanitize(subset) + stats = {'ok': 0, 'skip_video': 0, 'skip_missing': 0, 'skip_badjson': 0} + shard_info = {} + part = 0 + records, images = [], [] + + def flush(): + nonlocal part, records, images + if not records: + return + fname = f'{stem}__part{part:04d}.parquet' + out_path = os.path.join(train_dir, fname) + table = pa.Table.from_arrays( + [pa.array(records, type=pa.string()), + pa.array(images, type=pa.list_(pa.binary()))], + schema=SCHEMA, + ) + pq.write_table(table, out_path, compression='snappy', + row_group_size=row_group_size) + meta = pq.ParquetFile(out_path).metadata + shard_info[os.path.join(info_key_dir, fname)] = { + 'num_row_groups': meta.num_row_groups, + 'num_rows': meta.num_rows, + } + part += 1 + records, images = [], [] + + with ThreadPoolExecutor(max_workers=io_threads) as ex: + # batch the submissions: Executor.map submits everything up front and + # holds completed results until iterated, so mapping the whole subset + # at once would keep every image of the subset in memory. + for start in range(0, len(lines), rows_per_file): + chunk = lines[start:start + rows_per_file] + for raw_line, image_bytes, status in ex.map( + _load_record_images, ((l, image_dir) for l in chunk) + ): + stats[status] += 1 + if status != 'ok': + continue + records.append(raw_line) + images.append(image_bytes) + if len(records) >= rows_per_file: + flush() + flush() + return shard_info, stats + + +def main(): + # DATASET_INFO uses './datasets/...' paths relative to the repo root; + # run from there regardless of the caller's cwd (e.g. container default + # workdir). Pass absolute --config/--out-dir or repo-root-relative ones. + os.chdir(os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..'))) + + parser = argparse.ArgumentParser(description=__doc__) + parser.add_argument('--config', required=True, + help='training data yaml (e.g. data/configs/modus_stage1.yaml)') + parser.add_argument('--group', default='vlm_sft', + help='dataset group in the yaml / DATASET_INFO') + parser.add_argument('--out-dir', default='./datasets/llava_onevision_vqa_parquet') + parser.add_argument('--subsets', nargs='*', default=None, + help='only convert these subsets (default: all in the yaml)') + parser.add_argument('--rows-per-file', type=int, default=5000) + parser.add_argument('--row-group-size', type=int, default=200) + parser.add_argument('--io-threads', type=int, default=16) + parser.add_argument('--overwrite', action='store_true', + help='re-convert subsets whose shards already exist') + args = parser.parse_args() + + with open(args.config, 'r') as f: + cfg = yaml.safe_load(f)[args.group] + dataset_names = cfg['dataset_names'] + num_used_data = cfg['num_used_data'] + shuffle_lines = cfg.get('shuffle_lines', False) + shuffle_seed = cfg.get('shuffle_seed', 0) + if len(dataset_names) != len(num_used_data): + # The jsonl loader zips the two lists, silently truncating the longer + # one (this happens in the real configs: subsets commented out of + # dataset_names leave stale num_used_data rows). Replicate that + # pairing exactly — equivalence with current training behavior. + print(f'[warn] dataset_names ({len(dataset_names)}) and num_used_data ' + f'({len(num_used_data)}) differ; zip-truncating like the jsonl loader') + + stems = [sanitize(s) for s in dataset_names] + assert len(set(stems)) == len(stems), 'sanitized subset names collide' + + train_dir = os.path.join(args.out_dir, 'train') + info_dir = os.path.join(args.out_dir, 'parquet_info') + os.makedirs(train_dir, exist_ok=True) + os.makedirs(info_dir, exist_ok=True) + info_path = os.path.join(info_dir, 'llava_onevision_vqa.json') + # info keys use the configured-style relative path; loaders fall back to + # basename matching anyway, so the prefix only matters cosmetically. + info_key_dir = train_dir + + selected = args.subsets if args.subsets else dataset_names + unknown = [s for s in selected if s not in dataset_names] + assert not unknown, f'subsets not in the yaml group: {unknown}' + + totals = {'ok': 0, 'skip_video': 0, 'skip_missing': 0, 'skip_badjson': 0} + for subset, n_used in zip(dataset_names, num_used_data): + if subset not in selected: + continue + stem = sanitize(subset) + # A subset counts as done only if its shards are in the info JSON, + # which is merge-updated AFTER the whole subset finishes. Files on + # disk without an info entry are partial output of an interrupted + # run — delete and re-convert. + done_in_info = set() + if os.path.exists(info_path) and not args.overwrite: + with open(info_path, 'r') as f: + done_in_info = {os.path.basename(k) for k in json.load(f) + if os.path.basename(k).startswith(f'{stem}__part')} + existing = [f for f in os.listdir(train_dir) + if f.startswith(f'{stem}__part') and f.endswith('.parquet')] + if done_in_info and set(existing) >= done_in_info: + print(f'[skip] {subset}: {len(done_in_info)} shard(s) already converted') + continue + for f in existing: + os.remove(os.path.join(train_dir, f)) + + meta_info = DATASET_INFO[args.group][subset] + shard_info, stats = convert_subset( + subset, meta_info['jsonl_path'], meta_info['data_dir'], n_used, + shuffle_lines, shuffle_seed, train_dir, args.rows_per_file, + args.row_group_size, args.io_threads, info_key_dir, + ) + for k in totals: + totals[k] += stats[k] + print(f'[done] {subset}: {stats}') + + # merge-update the shared parquet_info JSON after each subset so + # partial runs / parallel invocations stay resumable. + merged = {} + if os.path.exists(info_path): + with open(info_path, 'r') as f: + merged = json.load(f) + merged.update(shard_info) + tmp_path = info_path + f'.tmp.{os.getpid()}' + with open(tmp_path, 'w') as f: + json.dump(merged, f, indent=1) + os.replace(tmp_path, info_path) + + print(f'[all done] totals: {totals}') + print(f'parquet_info: {info_path}') + + +if __name__ == '__main__': + main() diff --git a/data/any2any_preprocess/hf_upload.py b/data/any2any_preprocess/hf_upload.py new file mode 100644 index 0000000000000000000000000000000000000000..a06881e4110fc1f55fc6928ec4022eb339393365 --- /dev/null +++ b/data/any2any_preprocess/hf_upload.py @@ -0,0 +1,26 @@ +"""Upload a folder to a HuggingFace dataset repo. + +Token is read from the file at $HF_TOKEN_FILE (never passed on the command line +so it does not appear in logs / process listings). + +Usage: + HF_TOKEN_FILE=/users/mye/.hf_token python hf_upload.py +""" +import os +import sys + +from huggingface_hub import HfApi + +repo_id = sys.argv[1] +folder = sys.argv[2] +token = open(os.environ['HF_TOKEN_FILE']).read().strip() + +api = HfApi(token=token) +api.create_repo(repo_id, repo_type='dataset', exist_ok=True) +api.upload_folder( + repo_id=repo_id, + repo_type='dataset', + folder_path=folder, + commit_message='Add MODUS 16-mod preview (500 SA-1B samples + hero + card)', +) +print(f'DONE: https://huggingface.co/datasets/{repo_id}', flush=True) diff --git a/data/any2any_preprocess/parquet_visualize.py b/data/any2any_preprocess/parquet_visualize.py new file mode 100644 index 0000000000000000000000000000000000000000..cd9c0a9ea7a3b170584f9d9e4b3f385b55332511 --- /dev/null +++ b/data/any2any_preprocess/parquet_visualize.py @@ -0,0 +1,408 @@ +import pandas as pd +import pyarrow as pa +import pyarrow.parquet as pq +import os +import numpy as np +from pathlib import Path +from PIL import Image, ImageDraw, ImageFont +import json +import io +import matplotlib.pyplot as plt +import matplotlib.patches as patches +from matplotlib.patches import Rectangle +import cv2 + +def make_json_serializable(obj): + """ + Convert numpy arrays and other non-serializable objects to JSON-serializable format. + """ + if isinstance(obj, np.ndarray): + return obj.tolist() + elif isinstance(obj, dict): + return {key: make_json_serializable(value) for key, value in obj.items()} + elif isinstance(obj, list): + return [make_json_serializable(item) for item in obj] + elif isinstance(obj, (np.integer, np.floating)): + return obj.item() + elif hasattr(obj, 'tolist'): # Handle other numpy-like objects + return obj.tolist() + elif hasattr(obj, 'item'): # Handle other numpy scalar types + return obj.item() + else: + return obj + +def decode_rle_to_mask(rle_counts, size): + """ + Decode RLE (Run Length Encoding) to binary mask. + This is a simplified RLE decoder for COCO format. + + Args: + rle_counts (str): RLE encoded string + size (list): [width, height] of the mask + + Returns: + numpy.ndarray: Binary mask of shape (height, width) + """ + try: + # Try to use pycocotools if available + import pycocotools.mask as mask_util + + # Create RLE dict + rle = { + 'counts': rle_counts, + 'size': size + } + + # Decode to binary mask + binary_mask = mask_util.decode(rle) + return binary_mask + except ImportError: + # Fallback: create a simple mask visualization without decoding + print("Warning: pycocotools not available, creating placeholder mask") + height, width = size[1], size[0] # size is [width, height] + return np.zeros((height, width), dtype=np.uint8) + +def simple_rle_decode(rle_counts, size): + """ + Simple RLE decoder for COCO format masks. + This is a basic implementation that should work for most cases. + """ + try: + height, width = size[1], size[0] # size is [width, height] + mask = np.zeros(height * width, dtype=np.uint8) + + # Parse the RLE counts + counts = [] + current_num = "" + for char in rle_counts: + if char.isdigit() or char in '-+': + current_num += char + else: + if current_num: + counts.append(int(current_num)) + current_num = "" + if current_num: + counts.append(int(current_num)) + + # Decode RLE + pos = 0 + for i, count in enumerate(counts): + if i % 2 == 0: # Even indices are background (0) + pos += count + else: # Odd indices are foreground (1) + mask[pos:pos+count] = 1 + pos += count + + # Reshape to 2D + mask = mask.reshape((height, width)) + return mask + except Exception as e: + print(f"Error in simple RLE decode: {e}") + height, width = size[1], size[0] + return np.zeros((height, width), dtype=np.uint8) + +def visualize_detection_data(det_data, rgb_image, output_dir, filename_base): + """ + Visualize detection data with bounding boxes and masks overlaid on RGB image. + + Args: + det_data (dict): Detection data containing instances + rgb_image (PIL.Image): RGB image to overlay on + output_dir (str): Output directory + filename_base (str): Base filename for saving + """ + try: + # Make a deep copy of the original data to avoid modifying it + import copy + original_det_data = make_json_serializable(copy.deepcopy(det_data)) + # Convert PIL image to numpy array + img_array = np.array(rgb_image) + height, width = img_array.shape[:2] + + # Create figure with subplots + fig, axes = plt.subplots(1, 3, figsize=(18, 6)) + + # Original image + axes[0].imshow(img_array) + axes[0].set_title('Original Image') + axes[0].axis('off') + + # Image with bounding boxes + axes[1].imshow(img_array) + axes[1].set_title('Bounding Boxes') + axes[1].axis('off') + + # Image with masks + axes[2].imshow(img_array) + axes[2].set_title('Segmentation Masks') + axes[2].axis('off') + + # Colors for different categories + colors = ['red', 'blue', 'green', 'yellow', 'purple', 'orange', 'cyan', 'magenta'] + + # Process each instance + for i, instance in enumerate(det_data.get('instances', [])): + color = colors[i % len(colors)] + category = instance.get('category', 'unknown') + score = instance.get('score', 0.0) + bbox = instance.get('bbox', []) + + # Draw bounding box + if len(bbox) == 4: + x1, y1, x2, y2 = bbox + rect = Rectangle((x1, y1), x2-x1, y2-y1, + linewidth=2, edgecolor=color, facecolor='none') + axes[1].add_patch(rect) + + # Add label + label = f"{category}: {score:.2f}" + axes[1].text(x1, y1-5, label, color=color, fontsize=8, + bbox=dict(boxstyle="round,pad=0.3", facecolor='white', alpha=0.7)) + + # Draw segmentation mask + segmentation = instance.get('segmentation', {}) + mask_drawn = False + + if 'counts' in segmentation and 'size' in segmentation: + # Try multiple decoding methods + mask = None + + # Method 1: Try pycocotools + try: + mask = decode_rle_to_mask(segmentation['counts'], segmentation['size']) + if mask.size > 0 and np.any(mask): + print(f"Successfully decoded mask for {category} using pycocotools") + except: + pass + + # Method 2: Try simple RLE decoder + if mask is None or not np.any(mask): + try: + mask = simple_rle_decode(segmentation['counts'], segmentation['size']) + if mask.size > 0 and np.any(mask): + print(f"Successfully decoded mask for {category} using simple decoder") + except Exception as e: + print(f"Simple RLE decode failed for {category}: {e}") + + # If we have a valid mask, visualize it + if mask is not None and mask.size > 0 and np.any(mask): + # Create a more visible mask visualization + # Method 1: Colored overlay + mask_colored = np.zeros((height, width, 4)) + color_rgb = np.array(plt.cm.colors.to_rgb(color)) * 255 + mask_colored[:, :, :3] = color_rgb + mask_colored[:, :, 3] = mask * 0.6 # More opaque + + # Apply mask overlay + axes[2].imshow(mask_colored.astype(np.uint8), alpha=0.7) + + # Method 2: Also draw contour + from matplotlib.patches import Polygon + contours, _ = cv2.findContours(mask.astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) + for contour in contours: + if len(contour) > 2: + contour = contour.reshape(-1, 2) + polygon = Polygon(contour, fill=False, edgecolor=color, linewidth=2) + axes[2].add_patch(polygon) + + mask_drawn = True + + # Fallback: if no mask was drawn, create a simple mask from bounding box + if not mask_drawn and len(bbox) == 4: + x1, y1, x2, y2 = bbox + # Create a simple rectangular mask + mask = np.zeros((height, width), dtype=np.uint8) + x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2) + # Ensure coordinates are within bounds + x1, y1 = max(0, x1), max(0, y1) + x2, y2 = min(width, x2), min(height, y2) + + if x2 > x1 and y2 > y1: + mask[y1:y2, x1:x2] = 1 + + # Create colored mask overlay + mask_colored = np.zeros((height, width, 4)) + color_rgb = np.array(plt.cm.colors.to_rgb(color)) * 255 + mask_colored[:, :, :3] = color_rgb + mask_colored[:, :, 3] = mask * 0.4 # Semi-transparent + + # Apply mask overlay + axes[2].imshow(mask_colored.astype(np.uint8), alpha=0.6) + + # Also draw the bounding box outline + rect = Rectangle((x1, y1), x2-x1, y2-y1, + linewidth=2, edgecolor=color, facecolor='none') + axes[2].add_patch(rect) + + # Save the visualization + output_path = os.path.join(output_dir, f"{filename_base}_detection_visualization.png") + plt.tight_layout() + plt.savefig(output_path, dpi=150, bbox_inches='tight') + plt.close() + + print(f" Saved detection visualization: {filename_base}_detection_visualization.png") + + # Also save the JSON data for reference + json_path = os.path.join(output_dir, f"{filename_base}_det_seg.json") + try: + with open(json_path, 'w') as f: + json.dump(original_det_data, f, indent=2) + print(f" Saved detection JSON: {filename_base}_det_seg.json") + except Exception as json_error: + print(f" JSON save error: {json_error}") + # Try to save a simplified version + try: + simplified_data = { + 'image_id': original_det_data.get('image_id', 'unknown'), + 'instances': [] + } + for instance in original_det_data.get('instances', []): + simplified_instance = { + 'category': instance.get('category', 'unknown'), + 'score': float(instance.get('score', 0.0)), + 'bbox': [float(x) for x in instance.get('bbox', [])], + 'area': float(instance.get('area', 0.0)) + } + simplified_data['instances'].append(simplified_instance) + + with open(json_path, 'w') as f: + json.dump(simplified_data, f, indent=2) + print(f" Saved simplified detection JSON: {filename_base}_det_seg.json") + except Exception as e2: + print(f" Failed to save even simplified JSON: {e2}") + + except Exception as e: + print(f" Error visualizing detection data: {e}") + +def visualize_parquet_examples(input_file, output_dir, max_rows=None): + """ + Visualize examples from a parquet file by saving each row as separate files. + Saves images as PNG and text data as TXT files with uid_column_name naming format. + + Args: + input_file (str): Path to the input parquet file + output_dir (str): Directory to save the visualization files + max_rows (int): Maximum number of rows to process (None for all rows) + """ + + # Create output directory if it doesn't exist + os.makedirs(output_dir, exist_ok=True) + + print(f"Processing {input_file}...") + + # Read the parquet file + df = pd.read_parquet(input_file) + print(f"Total rows in file: {len(df)}") + print(f"Columns: {list(df.columns)}") + + # Limit rows if max_rows is specified + if max_rows is not None: + df = df.head(max_rows) + print(f"Processing only first {max_rows} rows") + + # Display first few rows to understand the data structure + print("\nFirst few rows:") + print(df.head(3)) + + # Process each row + for index, row in df.iterrows(): + print(f"Processing row {index}...") + + filename_base = None + + # Process each column in the row + for col_name, value in row.items(): + if col_name == 'uid': + filename_base = value + elif col_name in ['rgb', 'depth', 'normal'] and filename_base is not None: + # Handle image data (binary) + if value is not None and isinstance(value, bytes): + try: + # Convert binary data to PIL Image + image = Image.open(io.BytesIO(value)) + + # Create filename + filename = f"{filename_base}_{col_name}.png" + filepath = os.path.join(output_dir, filename) + + # Save as PNG + image.save(filepath, 'PNG') + print(f" Saved {col_name} image: {filename}") + + except Exception as e: + print(f" Error processing {col_name} image: {e}") + + elif col_name == 'caption' and filename_base is not None: + # Handle text data + if value is not None: + try: + filename = f"{filename_base}_captions.txt" + filepath = os.path.join(output_dir, filename) + + # Save text data + with open(filepath, 'w', encoding='utf-8') as f: + if isinstance(value, str): + f.write(value) + else: + f.write(str(value)) + print(f" Saved caption: {filename}") + + except Exception as e: + print(f" Error processing caption: {e}") + elif col_name == 'det_seg' and filename_base is not None: + # Handle detection maps (JSON format) + if value is not None: + try: + # Get the RGB image for visualization + rgb_image = None + if 'rgb' in row and row['rgb'] is not None: + rgb_image = Image.open(io.BytesIO(row['rgb'])) + + # Visualize detection data with bounding boxes and masks + if rgb_image is not None: + visualize_detection_data(value, rgb_image, output_dir, filename_base) + else: + # If no RGB image, just save the JSON + filename = f"{filename_base}_det_seg.json" + filepath = os.path.join(output_dir, filename) + with open(filepath, 'w') as f: + serializable_data = make_json_serializable(value) + json.dump(serializable_data, f, indent=2) + print(f" Saved detection JSON: {filename}") + + except Exception as e: + print(f" Error processing detection data: {e}") + + + + print(f"\nVisualization completed! Files saved to: {output_dir}") + + # List the created files + created_files = os.listdir(output_dir) + print(f"Created {len(created_files)} files:") + for file in sorted(created_files)[:10]: # Show first 10 files + print(f" {file}") + if len(created_files) > 10: + print(f" ... and {len(created_files) - 10} more files") + +def main(): + # Configuration + input_file = "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg/sa_000002.parquet" + output_dir = "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_visualize" + max_rows = 30 # Process only first 30 rows + + # Check if input file exists + if not os.path.exists(input_file): + print(f"Error: Input file {input_file} not found!") + return + + # Create output directory + os.makedirs(output_dir, exist_ok=True) + + # Visualize the parquet examples + visualize_parquet_examples(input_file, output_dir, max_rows) + + print("\nVisualization completed successfully!") + +if __name__ == "__main__": + main() diff --git a/data/any2any_preprocess/process_grounding.py b/data/any2any_preprocess/process_grounding.py new file mode 100644 index 0000000000000000000000000000000000000000..3cc5406a8d3defdab0b2145e6e53bae4e9d0b80d --- /dev/null +++ b/data/any2any_preprocess/process_grounding.py @@ -0,0 +1,346 @@ +import os +import tarfile +import json +import glob +import io +from tqdm import tqdm +import logging + +# Set up logging +logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s') +logger = logging.getLogger(__name__) + +class GroundingProcessor: + def __init__(self, base_dir): + self.base_dir = base_dir + self.rgb_caption_dir = os.path.join(base_dir, 'datasets/blip3o/datasets') + self.grounding_source_dir = os.path.join(base_dir, 'datasets/glamm') + self.grounding_output_dir = os.path.join(base_dir, 'datasets/blip3o/datasets_grounding') + self.grounding_cache_dir = os.path.join(base_dir, 'datasets/blip3o/grounding_cache') + + # Create output directories if they don't exist + os.makedirs(self.grounding_output_dir, exist_ok=True) + os.makedirs(self.grounding_cache_dir, exist_ok=True) + + def get_rgb_tar_files(self): + """Get all RGB tar files from datasets directory""" + tar_files = glob.glob(os.path.join(self.rgb_caption_dir, '*.tar')) + return sorted(tar_files) + + def get_grounding_tar_files(self): + """Get all grounding tar files from part directories""" + grounding_tars = [] + for part in ['part_1', 'part_2', 'part_3', 'part_4']: + part_dir = os.path.join(self.grounding_source_dir, part) + if os.path.exists(part_dir): + part_tars = glob.glob(os.path.join(part_dir, '*.tar.gz')) + grounding_tars.extend(part_tars) + return sorted(grounding_tars) + + def extract_uids_from_rgb_tar(self, tar_path): + """Extract all UIDs from RGB tar file""" + uids = set() + + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if member.isfile(): + filename = member.name + uid = os.path.splitext(filename)[0] # Remove extension + uids.add(uid) + except Exception as e: + logger.error(f"Error extracting UIDs from {tar_path}: {e}") + return set() + + return uids + + def build_grounding_index(self): + """Build an index of all grounding data: uid -> (tar_path, member_name)""" + logger.info("Building grounding data index...") + grounding_index = {} + + grounding_tars = self.get_grounding_tar_files() + + for tar_path in tqdm(grounding_tars, desc="Indexing grounding tars"): + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if member.isfile() and member.name.endswith('.json'): + uid = os.path.splitext(member.name)[0] + grounding_index[uid] = (tar_path, member.name) + except Exception as e: + logger.warning(f"Error indexing {tar_path}: {e}") + continue + + logger.info(f"Built index with {len(grounding_index)} grounding entries") + return grounding_index + + def pre_extract_all_grounding_data_to_disk(self): + """Pre-extract all grounding data to disk cache for fastest access""" + logger.info("Pre-extracting all grounding data to disk cache...") + + grounding_tars = self.get_grounding_tar_files() + cache_index = {} + + for tar_path in tqdm(grounding_tars, desc="Pre-extracting grounding data to disk"): + try: + with tarfile.open(tar_path, 'r') as tar: + for member in tar.getmembers(): + if member.isfile() and member.name.endswith('.json'): + uid = os.path.splitext(member.name)[0] + + # Extract JSON content + f = tar.extractfile(member) + if f is not None: + content = f.read() + json_str = content.decode('utf-8') + json_data = json.loads(json_str) + + # Save to disk cache + cache_file = os.path.join(self.grounding_cache_dir, f"{uid}.json") + with open(cache_file, 'w') as cache_f: + json.dump(json_data, cache_f, indent=2) + + cache_index[uid] = cache_file + except Exception as e: + logger.warning(f"Error pre-extracting from {tar_path}: {e}") + continue + + # Save index file + index_file = os.path.join(self.grounding_cache_dir, "index.json") + with open(index_file, 'w') as f: + json.dump(cache_index, f, indent=2) + + logger.info(f"Pre-extracted {len(cache_index)} grounding entries to disk cache") + return cache_index + + def load_grounding_cache_index(self): + """Load the grounding cache index""" + index_file = os.path.join(self.grounding_cache_dir, "index.json") + if os.path.exists(index_file): + with open(index_file, 'r') as f: + return json.load(f) + return {} + + def load_grounding_data_from_cache(self, uids): + """Load grounding data from disk cache for specific UIDs""" + uid_to_grounding = {} + + for uid in uids: + cache_file = os.path.join(self.grounding_cache_dir, f"{uid}.json") + if os.path.exists(cache_file): + try: + with open(cache_file, 'r') as f: + json_data = json.load(f) + uid_to_grounding[uid] = json_data + except Exception as e: + logger.warning(f"Error loading {cache_file}: {e}") + continue + + return uid_to_grounding + + def find_grounding_data_for_uids_fast(self, uids, grounding_data): + """Find grounding JSON data for given UIDs using pre-extracted data - FASTEST""" + uid_to_grounding = {} + + for uid in uids: + if uid in grounding_data: + uid_to_grounding[uid] = grounding_data[uid] + + return uid_to_grounding + + def find_grounding_data_for_uids(self, uids, grounding_index): + """Find grounding JSON data for given UIDs using pre-built index with batch processing""" + uid_to_grounding = {} + + # Group UIDs by tar_path to minimize tar file opens + tar_to_uids = {} + for uid in uids: + if uid in grounding_index: + tar_path, member_name = grounding_index[uid] + if tar_path not in tar_to_uids: + tar_to_uids[tar_path] = [] + tar_to_uids[tar_path].append((uid, member_name)) + + # Process each tar file once, extracting all needed UIDs + for tar_path, uid_members in tar_to_uids.items(): + try: + with tarfile.open(tar_path, 'r') as tar: + for uid, member_name in uid_members: + try: + member = tar.getmember(member_name) + f = tar.extractfile(member) + if f is not None: + content = f.read() + json_str = content.decode('utf-8') + json_data = json.loads(json_str) + uid_to_grounding[uid] = json_data + except Exception as e: + logger.warning(f"Error extracting {uid} from {tar_path}: {e}") + continue + except Exception as e: + logger.warning(f"Error opening {tar_path}: {e}") + continue + + return uid_to_grounding + + def create_grounding_tar(self, rgb_tar_path, uid_to_grounding): + """Create a grounding tar file with the same structure as RGB tar""" + + # Extract base name (e.g., 'sa_000000' from 'sa_000000.tar') + base_name = os.path.splitext(os.path.basename(rgb_tar_path))[0] + output_tar_path = os.path.join(self.grounding_output_dir, f"{base_name}.tar") + + logger.info(f"Creating grounding tar: {output_tar_path}") + + try: + with tarfile.open(output_tar_path, 'w') as output_tar: + for uid, grounding_data in uid_to_grounding.items(): + # Create JSON content + json_str = json.dumps(grounding_data, indent=2) + json_bytes = json_str.encode('utf-8') + + # Add to tar with same naming convention as RGB + tarinfo = tarfile.TarInfo(name=f"{uid}.json") + tarinfo.size = len(json_bytes) + output_tar.addfile(tarinfo, io.BytesIO(json_bytes)) + + logger.info(f"Created grounding tar with {len(uid_to_grounding)} UIDs: {output_tar_path}") + return output_tar_path + + except Exception as e: + logger.error(f"Error creating grounding tar {output_tar_path}: {e}") + return None + + def process_single_rgb_tar(self, rgb_tar_path, grounding_data=None, grounding_index=None, use_cache=False): + """Process a single RGB tar file and create corresponding grounding tar""" + + # Extract base name + base_name = os.path.splitext(os.path.basename(rgb_tar_path))[0] + + logger.info(f"Processing {base_name}") + + # Extract UIDs from RGB tar + uids = self.extract_uids_from_rgb_tar(rgb_tar_path) + + if not uids: + logger.warning(f"No UIDs found in {rgb_tar_path}") + return None + + logger.info(f"Found {len(uids)} UIDs in {base_name}") + + # Find grounding data for these UIDs + if use_cache: + # Use disk cache (fastest and memory efficient) + uid_to_grounding = self.load_grounding_data_from_cache(uids) + elif grounding_data is not None: + # Use pre-extracted data (fastest) + uid_to_grounding = self.find_grounding_data_for_uids_fast(uids, grounding_data) + elif grounding_index is not None: + # Use index-based lookup (faster than original) + uid_to_grounding = self.find_grounding_data_for_uids(uids, grounding_index) + else: + logger.error("No grounding data or index provided") + return None + + if not uid_to_grounding: + logger.warning(f"No grounding data found for UIDs in {base_name}") + return None + + logger.info(f"Found grounding data for {len(uid_to_grounding)}/{len(uids)} UIDs") + + # Create grounding tar file + output_path = self.create_grounding_tar(rgb_tar_path, uid_to_grounding) + + return output_path + + def process_all_rgb_tars(self, use_cache=True, pre_extract_cache=False): + """Process all RGB tar files and create corresponding grounding tars""" + rgb_tars = self.get_rgb_tar_files() + + if not rgb_tars: + logger.error("No RGB tar files found") + return + + logger.info(f"Found {len(rgb_tars)} RGB tar files to process") + + if use_cache: + # Check if cache exists + cache_index = self.load_grounding_cache_index() + + if not cache_index: + if pre_extract_cache: + logger.info("Pre-extracting grounding data to disk cache...") + self.pre_extract_all_grounding_data_to_disk() + else: + logger.error("No cache found. Use --pre_extract_cache to create cache first.") + return + + logger.info("Using disk cache method (fastest and memory efficient)") + processed_files = [] + for rgb_tar in tqdm(rgb_tars, desc="Processing RGB tars"): + try: + output_path = self.process_single_rgb_tar(rgb_tar, use_cache=True) + if output_path: + processed_files.append(output_path) + except Exception as e: + logger.error(f"Error processing {rgb_tar}: {e}") + else: + # Use index-based method (faster than original, less memory) + logger.info("Using index-based method (faster, less memory)") + grounding_index = self.build_grounding_index() + + processed_files = [] + for rgb_tar in tqdm(rgb_tars, desc="Processing RGB tars"): + try: + output_path = self.process_single_rgb_tar(rgb_tar, grounding_index=grounding_index) + if output_path: + processed_files.append(output_path) + except Exception as e: + logger.error(f"Error processing {rgb_tar}: {e}") + + logger.info(f"Successfully processed {len(processed_files)} grounding tar files") + return processed_files + +def main(): + import argparse + + parser = argparse.ArgumentParser(description='Process grounding data') + parser.add_argument('--use_cache', action='store_true', default=True, + help='Use disk cache method (fastest and memory efficient)') + parser.add_argument('--pre_extract_cache', action='store_true', + help='Pre-extract grounding data to disk cache') + parser.add_argument('--base_dir', type=str, default='./', + help='Base directory (default: ./)') + + args = parser.parse_args() + + # Set the base directory + base_dir = args.base_dir + + # Create processor + processor = GroundingProcessor(base_dir) + + # Process all RGB tar files + processed_files = processor.process_all_rgb_tars( + use_cache=args.use_cache, + pre_extract_cache=args.pre_extract_cache + ) + + if processed_files: + logger.info(f"Successfully created {len(processed_files)} grounding tar files:") + for file in processed_files: + logger.info(f" - {file}") + else: + logger.error("No grounding tar files were created") + +if __name__ == "__main__": + main() + + + +# This will take time but only needs to be done once +# python data/any2any_preprocess/process_grounding.py --pre_extract_cache + +# This will be extremely fast +# python data/any2any_preprocess/process_grounding.py --use_cache \ No newline at end of file diff --git a/data/any2any_preprocess/recompress_normal_jpeg.py b/data/any2any_preprocess/recompress_normal_jpeg.py new file mode 100644 index 0000000000000000000000000000000000000000..e38be021beaffc9076808e62cab2e79761b05cce --- /dev/null +++ b/data/any2any_preprocess/recompress_normal_jpeg.py @@ -0,0 +1,90 @@ +"""Recompress the `normal` column of the 16-mod parquet from PNG to JPEG q95. + +The `normal` column stores raw image bytes (Marigold normal maps, pass-through +PNG) and accounts for ~65% of on-disk size while being ~6x larger than the +JPEG-encoded `rgb` column. Re-encoding normal as JPEG q95 shrinks it to +roughly rgb size with negligible quality loss. + +Every other column is passed through untouched; the Arrow schema is identical +to the source, so downstream dataloader / HF viewer see no structural change. + +Usage: + python recompress_normal_jpeg.py --out_dir file1.parquet [file2 ...] +""" +import argparse +import io +import os + +import pyarrow as pa +import pyarrow.parquet as pq +from PIL import Image + +JPEG_QUALITY = 95 + + +def recompress_normal_bytes(b): + if b is None: + return None + if isinstance(b, memoryview): + b = b.tobytes() + img = Image.open(io.BytesIO(b)).convert('RGB') + out = io.BytesIO() + img.save(out, format='JPEG', quality=JPEG_QUALITY) + return out.getvalue() + + +def process_file(src, out_dir): + dst = os.path.join(out_dir, os.path.basename(src)) + pf = pq.ParquetFile(src) + schema = pf.schema_arrow + assert 'normal' in schema.names, f'no normal column in {src}' + norm_idx = schema.names.index('normal') + + reported_fmt = False + writer = pq.ParquetWriter(dst, schema, compression='snappy') + try: + for rg in range(pf.num_row_groups): + table = pf.read_row_group(rg) + normal_col = table.column('normal').to_pylist() + + if not reported_fmt: + for b in normal_col: + if b is not None: + bb = b.tobytes() if isinstance(b, memoryview) else b + fmt = Image.open(io.BytesIO(bb)).format + print(f' source normal format = {fmt}', flush=True) + reported_fmt = True + break + + new_normal = [recompress_normal_bytes(b) for b in normal_col] + new_col = pa.array(new_normal, type=schema.field('normal').type) + table = table.set_column(norm_idx, schema.field('normal'), new_col) + writer.write_table(table) + finally: + writer.close() + + s0, s1 = os.path.getsize(src), os.path.getsize(dst) + print(f' {os.path.basename(src)}: {s0/1e9:.2f} GB -> {s1/1e9:.2f} GB ' + f'({100*(1-s1/s0):.0f}% smaller)', flush=True) + return s0, s1 + + +def main(): + ap = argparse.ArgumentParser() + ap.add_argument('--out_dir', required=True) + ap.add_argument('files', nargs='+') + args = ap.parse_args() + os.makedirs(args.out_dir, exist_ok=True) + + tot0 = tot1 = 0 + for f in args.files: + print(f'[{os.path.basename(f)}]', flush=True) + s0, s1 = process_file(f, args.out_dir) + tot0 += s0 + tot1 += s1 + print(f'TOTAL: {tot0/1e9:.2f} GB -> {tot1/1e9:.2f} GB ' + f'({100*(1-tot1/tot0):.0f}% smaller)', flush=True) + + +if __name__ == '__main__': + main() diff --git a/data/any2any_preprocess/run_full_rebuild.py b/data/any2any_preprocess/run_full_rebuild.py new file mode 100644 index 0000000000000000000000000000000000000000..fcb6761cbec7984a49fc2b9d6d725db4b885c115 --- /dev/null +++ b/data/any2any_preprocess/run_full_rebuild.py @@ -0,0 +1,82 @@ +"""Slurm driver: rebuild a strided slice of the full dataset. + +Robust against memory leaks: each small chunk of files is processed by a FRESH +subprocess (build_full_release.py --workers 1) that exits afterwards, so the OS +reclaims all memory — no accumulation across the run. `concurrency` such +subprocesses run at once. Resumable via process_one's skip. +""" +import argparse +import os +import subprocess +import sys +from concurrent.futures import ThreadPoolExecutor, as_completed + +SRC = ('datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding' + '_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet') +OUT = 'datasets/blip3o/modus_full' +WORKER = 'data/any2any_preprocess/build_full_release.py' +CHUNK = 4 + + +def config_of(fname): + if fname.startswith('sa_'): + return 'sa1b' + if fname.startswith('webdataset_JDB_'): + return 'journeydb' + if fname.startswith('webdataset_shard_'): + return 'cc12m' + return None + + +def run_chunk(cfg, files): + cmd = [sys.executable, WORKER, '--config', cfg, + '--out_dir', os.path.join(OUT, cfg), '--workers', '1'] + files + r = subprocess.run(cmd, capture_output=True, text=True) + return cfg, len(files), r.returncode, (r.stderr or '')[-300:] + + +def main(): + ap = argparse.ArgumentParser() + ap.add_argument('--num-tasks', type=int, required=True) + ap.add_argument('--task-id', type=int, required=True) + ap.add_argument('--concurrency', type=int, default=48) + args = ap.parse_args() + + for cfg in ('sa1b', 'journeydb', 'cc12m'): + os.makedirs(os.path.join(OUT, cfg), exist_ok=True) + + items = [] + for fn in sorted(os.listdir(SRC)): + if fn.endswith('.parquet') and config_of(fn): + items.append((config_of(fn), os.path.join(SRC, fn))) + mine = items[args.task_id::args.num_tasks] + + # group into per-config chunks + chunks = [] + bycfg = {} + for cfg, src in mine: + bycfg.setdefault(cfg, []).append(src) + for cfg, fs in bycfg.items(): + for i in range(0, len(fs), CHUNK): + chunks.append((cfg, fs[i:i + CHUNK])) + + print(f'task {args.task_id}/{args.num_tasks}: {len(mine)} files in ' + f'{len(chunks)} chunks, concurrency={args.concurrency}', flush=True) + done_files = fail = 0 + with ThreadPoolExecutor(max_workers=args.concurrency) as ex: + futs = [ex.submit(run_chunk, cfg, fs) for cfg, fs in chunks] + for i, fu in enumerate(as_completed(futs), 1): + cfg, n, rc, err = fu.result() + if rc == 0: + done_files += n + else: + fail += n + print(f' CHUNK FAIL {cfg} rc={rc}: {err}', flush=True) + if i % 20 == 0: + print(f'[{i}/{len(chunks)} chunks] files_ok={done_files} ' + f'fail={fail}', flush=True) + print(f'TASK COMPLETE: {done_files} files ok, {fail} failed', flush=True) + + +if __name__ == '__main__': + main() diff --git a/data/any2any_preprocess/upload_full.py b/data/any2any_preprocess/upload_full.py new file mode 100644 index 0000000000000000000000000000000000000000..e36fc9c1632afdc5ff5ec559cc91f1c19fd22fe4 --- /dev/null +++ b/data/any2any_preprocess/upload_full.py @@ -0,0 +1,26 @@ +"""Resumable upload of the full-release folder to the HF dataset repo. + +Uses upload_large_folder (xet, multi-commit, resumable). Uploads folder_path +contents to the repo root, preserving the sa1b/ journeydb/ cc12m/ structure. +Re-running skips already-uploaded files. + +Usage: + HF_TOKEN_FILE=/users/mye/.hf_token python upload_full.py [allow_glob] +""" +import os +import sys + +from huggingface_hub import HfApi + +repo_id = sys.argv[1] +folder = sys.argv[2] +allow = list(sys.argv[3:]) # zero or more allow_patterns +token = open(os.environ['HF_TOKEN_FILE']).read().strip() + +api = HfApi(token=token) +api.create_repo(repo_id, repo_type='dataset', exist_ok=True) +kw = dict(repo_id=repo_id, repo_type='dataset', folder_path=folder, print_report=True) +if allow: + kw['allow_patterns'] = allow +api.upload_large_folder(**kw) +print(f'UPLOAD PASS DONE: {folder} {allow} -> {repo_id}', flush=True) diff --git a/data/any2any_preprocess/vqa_convert_parquet_to_jsonl.py b/data/any2any_preprocess/vqa_convert_parquet_to_jsonl.py new file mode 100644 index 0000000000000000000000000000000000000000..024c3631ea72b57e7ba290d02b177d466e4887b1 --- /dev/null +++ b/data/any2any_preprocess/vqa_convert_parquet_to_jsonl.py @@ -0,0 +1,312 @@ +#!/usr/bin/env python3 +""" +Convert LLaVA OneVision parquet files to JSONL format matching llava_ov_si.jsonl + +Single-folder usage (backwards compatible): + python vqa_convert_parquet_to_jsonl.py --image-dir [--max-rows N] + +Multi-folder usage (process all immediate subfolders of ): + python vqa_convert_parquet_to_jsonl.py dummy.jsonl --process-all --output-root [--max-rows N] + +Notes: +- In multi-folder mode, outputs are written per subfolder under //{images,label/labels.jsonl} +- The script prints the sorted folder index and name, and a global image counter every N (default 1000) +""" + +import argparse +import json +import os +import glob +from pathlib import Path +import pandas as pd +from PIL import Image +import io +from tqdm import tqdm +def _save_pil_image_as_jpeg(pil_image: Image.Image, image_path: str): + """ + Ensure the PIL image is compatible with JPEG (no alpha), then save. + """ + try: + # Convert to RGB if image has alpha channel or unsupported mode for JPEG + if pil_image.mode not in ("RGB", "L"): + pil_image = pil_image.convert("RGB") + pil_image.save(image_path, format="JPEG") + except Exception: + # As a fallback, force convert to RGB and retry + pil_image = pil_image.convert("RGB") + pil_image.save(image_path, format="JPEG") + + + +def convert_parquet_to_jsonl( + parquet_dir: str, + output_jsonl: str, + image_dir: str = None, + max_rows: int = None, + sample_id_offset: int = 0, + progress: dict | None = None, +): + """ + Convert parquet files to JSONL format compatible with llava_ov_si.jsonl + + Args: + parquet_dir: Directory containing parquet files (can be subdirectory) + output_jsonl: Output JSONL file path + image_dir: Directory to save images (optional, if None saves with dataset) + max_rows: Maximum number of rows to process (for testing) + sample_id_offset: Starting ID offset (for merging multiple datasets) + progress: Optional dict to track global progress across folders. Expected keys: + {"count": int, "next_milestone": int, "interval": int} + """ + + # Find all parquet files in the directory + parquet_pattern = os.path.join(parquet_dir, "train-*.parquet") + parquet_files = sorted(glob.glob(parquet_pattern)) + + if not parquet_files: + print(f"Error: No parquet files found in {parquet_dir}") + return + + print(f"Found {len(parquet_files)} parquet file(s)") + + # Create image directory if specified + if image_dir: + os.makedirs(image_dir, exist_ok=True) + + all_entries = [] + current_id = sample_id_offset + + for parquet_file in parquet_files: + print(f"\nProcessing {parquet_file}...") + df = pd.read_parquet(parquet_file) + + for idx, row in tqdm(df.iterrows(), total=len(df)): + if max_rows and len(all_entries) >= max_rows: + break + + # Extract conversations - handle numpy array conversion + conversations = row["conversations"] + if hasattr(conversations, "tolist"): + conversations = conversations.tolist() + + # Handle image - extract from binary data and save + image_filename = None + if row["image"] is not None: + try: + # The image data is stored as binary bytes + image_data = row["image"] + + # Generate filename from ID + image_filename = f"{current_id}.jpg" + + if image_dir: + image_path = os.path.join(image_dir, image_filename) + else: + # Save in same directory as parquet file + image_dir_local = os.path.dirname(parquet_file) + image_path = os.path.join( + image_dir_local, image_filename + ) + + # Convert image data to PIL Image and save + if isinstance(image_data, dict): + # Image is stored as a dict with 'bytes' key containing image data + if ( + "bytes" in image_data + and image_data["bytes"] is not None + ): + image_bytes = image_data["bytes"] + pil_image = Image.open(io.BytesIO(image_bytes)) + _save_pil_image_as_jpeg(pil_image, image_path) + else: + print( + f"Warning: Dict image data doesn't contain 'bytes' key for row {idx}" + ) + continue + elif isinstance(image_data, bytes): + # Try to open as PIL Image from bytes + pil_image = Image.open(io.BytesIO(image_data)) + _save_pil_image_as_jpeg(pil_image, image_path) + elif isinstance(image_data, str): + # If it's a string, try to decode it + image_bytes = image_data.encode( + "latin-1" + ) # Convert string to bytes + pil_image = Image.open(io.BytesIO(image_bytes)) + _save_pil_image_as_jpeg(pil_image, image_path) + else: + print( + f"Warning: Unknown image data type {type(image_data)} for row {idx}" + ) + continue + + except Exception as e: + print(f"Error processing image for row {idx}: {e}") + continue + + # Create JSONL entry matching llava_ov_si.jsonl format + entry = { + "id": current_id, + "image": image_filename, + "conversations": conversations, + } + + all_entries.append(entry) + current_id += 1 + + # Update global progress if provided + if progress is not None: + progress["count"] += 1 + if progress["count"] >= progress.get("next_milestone", 1000): + print( + f"[global] Processed {progress['count']} images total" + ) + interval = progress.get("interval", 1000) + progress["next_milestone"] = progress["count"] + interval + + if max_rows and len(all_entries) >= max_rows: + break + + if max_rows and len(all_entries) >= max_rows: + break + + # Write JSONL file + print(f"\nWriting {len(all_entries)} entries to {output_jsonl}...") + with open(output_jsonl, "w", encoding="utf-8") as f: + for entry in all_entries: + f.write(json.dumps(entry, ensure_ascii=False) + "\n") + + print(f"✓ Converted {len(all_entries)} samples to {output_jsonl}") + if image_dir: + print(f"✓ Images saved to {image_dir}") + + +def main(): + parser = argparse.ArgumentParser( + description="Convert LLaVA OneVision parquet files to JSONL format" + ) + parser.add_argument( + "parquet_dir", + help="Directory containing parquet files, or a root directory with subfolders", + ) + parser.add_argument("output_jsonl", help="Output JSONL file path (single-folder mode)") + parser.add_argument( + "--image-dir", + default=None, + help="Directory to save images (default: same as parquet directory)", + ) + parser.add_argument( + "--max-rows", + type=int, + default=None, + help="Maximum number of rows to process (for testing)", + ) + parser.add_argument( + "--id-offset", + type=int, + default=0, + help="Starting ID offset (for merging datasets)", + ) + parser.add_argument( + "--process-all", + action="store_true", + help="Process all immediate subfolders in parquet_dir and write per-folder outputs under --output-root", + ) + parser.add_argument( + "--output-root", + default=None, + help="Base output directory when using --process-all", + ) + parser.add_argument( + "--print-every", + type=int, + default=1000, + help="Global image progress interval for multi-folder mode", + ) + parser.add_argument( + "--start-index", + type=int, + default=1, + help="1-based index of subfolder to start processing from (resume)", + ) + + args = parser.parse_args() + + if args.process_all: + if not args.output_root: + raise SystemExit("--output-root is required when using --process-all") + + # Discover immediate subfolders and sort + if not os.path.isdir(args.parquet_dir): + raise SystemExit(f"Input root '{args.parquet_dir}' is not a directory") + + subfolders = [ + d + for d in sorted(os.listdir(args.parquet_dir)) + if os.path.isdir(os.path.join(args.parquet_dir, d)) + ] + + # Filter to only those having parquet files + filtered_subfolders = [] + for d in subfolders: + pattern = os.path.join(args.parquet_dir, d, "train-*.parquet") + if glob.glob(pattern): + filtered_subfolders.append(d) + subfolders = filtered_subfolders + + total = len(subfolders) + print(f"Found {total} subfolder(s) to process under {args.parquet_dir}") + + # Compute starting index (1-based) and slice subfolders for resume + start_index = max(1, int(args.start_index)) if args.start_index else 1 + if start_index > total: + print(f"Start index {start_index} is beyond total {total}; nothing to do.") + return + subfolders_to_process = subfolders[start_index - 1 :] + + # Prepare global progress + progress = { + "count": 0, + "next_milestone": args.print_every, + "interval": args.print_every, + } + # When resuming at folder index 41, hardcode the global counter baseline + if start_index == 41: + progress["count"] = 1380000 + progress["next_milestone"] = progress["count"] + progress["interval"] + + for idx, sub in enumerate(subfolders_to_process, start=start_index): + print(f"\n[{idx}/{total}] Processing folder: {sub}") + sub_in = os.path.join(args.parquet_dir, sub) + sub_out_images = os.path.join(args.output_root, sub, "images") + sub_out_label_dir = os.path.join(args.output_root, sub, "label") + os.makedirs(sub_out_images, exist_ok=True) + os.makedirs(sub_out_label_dir, exist_ok=True) + sub_out_jsonl = os.path.join(sub_out_label_dir, "labels.jsonl") + + convert_parquet_to_jsonl( + parquet_dir=sub_in, + output_jsonl=sub_out_jsonl, + image_dir=sub_out_images, + max_rows=args.max_rows, + sample_id_offset=args.id_offset, + progress=progress, + ) + else: + convert_parquet_to_jsonl( + parquet_dir=args.parquet_dir, + output_jsonl=args.output_jsonl, + image_dir=args.image_dir, + max_rows=args.max_rows, + sample_id_offset=args.id_offset, + ) + + +if __name__ == "__main__": + main() + + +# python data/any2any_preprocess/vqa_convert_parquet_to_jsonl.py datasets/llava_onevision/ai2d\(cauldron\,llava_format\)/ datasets/llava_onevision_vqa/label/ai2d_converted.jsonl --image-dir datasets/llava_onevision_vqa/images + +# python data/any2any_preprocess/vqa_convert_parquet_to_jsonl.py datasets/llava_onevision dummy.jsonl --process-all --output-root datasets/llava_onevision_vqa +# python data/any2any_preprocess/vqa_convert_parquet_to_jsonl.py datasets/llava_onevision dummy.jsonl --process-all --output-root datasets/llava_onevision_vqa --start-index 41 diff --git a/data/bundled_parquet_info/README.md b/data/bundled_parquet_info/README.md new file mode 100644 index 0000000000000000000000000000000000000000..f4ea6abeef51e717eb3a157b23a118a73eecaf5a --- /dev/null +++ b/data/bundled_parquet_info/README.md @@ -0,0 +1,43 @@ +# bundled_parquet_info — repo-tracked parquet metadata (auto-fallback) + +Repo-tracked copies of the parquet-info JSONs used by BAGEL training. +**The code reads this directory automatically**: `data/dataset_base.py` +falls back to `data/bundled_parquet_info/` whenever the +configured live path (`./datasets/blip3o/parquet_info/…`, a symlink chain +that only exists on the original cluster) is missing. When the live path +exists it still wins — behavior on the original cluster is unchanged. + +## Files + +| File | Files listed | Rows | Used by | +|---|---|---|---| +| `…_grounding_canny_dino_global_clip448_imagebind.json` | 2891 (1000 `sa_*` + 1891 `webdataset_*`) | 29.2M | 13mod: all target groups except grounding (any2rgb / depth / normal / caption / canny / dino / dinolocal / clip / imagebind / imagebindlocal) | +| `…_grounding2_canny_dino_global_clip448_imagebind.json` | 1000 (`sa_*` only) | 11.1M | 13mod: `unified_any2grounding` only | +| `…_clip448_imagebind_samseg_samedge_cocodet.json` | — | — | 16mod runs (adds cocodet / samseg / samedge) | +| `llava_onevision_vqa.json` | — | — | VLM-SFT (llava-onevision) | + +**Why grounding has two JSONs:** grounding annotations (GLaMM phrase+bbox, +matched by UID) only exist for the SA-1B portion of the parquet set. The +`webdataset_*` shards have no `grounding` column at all (verified via +parquet footer schema). So when grounding is the generation TARGET, the +loader must restrict itself to the `sa_*` files — that restricted file +list is the `grounding2` JSON. Both JSONs point into the SAME `data_dir`. + +## Setting up on a new machine + +1. Get the parquet data itself (≈ several TB, NOT in this repo): + `parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/` + (2891 parquet files). +2. Place (or symlink) it at + `datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/` + relative to the repo root. +3. parquet-info JSONs: **no action needed** — the loader automatically + falls back to this directory when the live + `datasets/blip3o/parquet_info/` path is absent + (`data/dataset_base.py`, "Fall back to the copy bundled in the repo"). +4. Note the JSON keys are relative paths + (`./datasets/blip3o/parquet_.../sa_000000.parquet`), so always launch + training from the repo root. + +If the parquet set ever changes, regenerate with +`data/any2any_preprocess/generate_parquet_json.py` and refresh these copies. diff --git a/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding2_canny_dino_global_clip448_imagebind.json b/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding2_canny_dino_global_clip448_imagebind.json new file mode 100644 index 0000000000000000000000000000000000000000..0a0c84013027548f866bd341801284da86acadd1 --- /dev/null +++ b/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding2_canny_dino_global_clip448_imagebind.json @@ -0,0 +1,4002 @@ +{ + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000000.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000001.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000002.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000003.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000004.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000005.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000006.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000007.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000008.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000009.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000010.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000011.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000012.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000013.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000014.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000015.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000016.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000017.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000018.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000019.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000020.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000021.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000022.parquet": { + "num_row_groups": 12, + "num_rows": 11113 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000023.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000024.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000025.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000026.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000027.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000028.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000029.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000030.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000031.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000032.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000033.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000034.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000035.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000036.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000037.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000038.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000039.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000040.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000041.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000042.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000043.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000044.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000045.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000046.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000047.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000048.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000049.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000050.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000051.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000052.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000053.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000054.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000055.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000056.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000057.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000058.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000059.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000060.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000061.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000062.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000063.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000064.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000065.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000066.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000067.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000068.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000069.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000070.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000071.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000072.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000073.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000074.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000075.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000076.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000077.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000078.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000079.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000080.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000081.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000082.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000083.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000084.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000085.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000086.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000087.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000088.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000089.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000090.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000091.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000092.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000093.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000094.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000095.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000096.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000097.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000098.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000099.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000100.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000101.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000102.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000103.parquet": { + "num_row_groups": 12, + "num_rows": 11111 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000104.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000105.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000106.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000107.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000108.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000109.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000110.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000111.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000112.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000113.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000114.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000115.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000116.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000117.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000118.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000119.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000120.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000121.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000122.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000123.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000124.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000125.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000126.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000127.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000128.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000129.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000130.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000131.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000132.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000133.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000134.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000135.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000136.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000137.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000138.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000139.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000140.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000141.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000142.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000143.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000144.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000145.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000146.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000147.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000148.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000149.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000150.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000151.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000152.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000153.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000154.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000155.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000156.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000157.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000158.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000159.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000160.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000161.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000162.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000163.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000164.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000165.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000166.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000167.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000168.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000169.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000170.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000171.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000172.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000173.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000174.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000175.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000176.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000177.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000178.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000179.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000180.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000181.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000182.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000183.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000184.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000185.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000186.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000187.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000188.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000189.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000190.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000191.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000192.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000193.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000194.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000195.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000196.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000197.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000198.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000199.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000200.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000201.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000202.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000203.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000204.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000205.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000206.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000207.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000208.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000209.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000210.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000211.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000212.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000213.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000214.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000215.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000216.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000217.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000218.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000219.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000220.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000221.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000222.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000223.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000224.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000225.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000226.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000227.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000228.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000229.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000230.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000231.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000232.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000233.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000234.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000235.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000236.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000237.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000238.parquet": { + "num_row_groups": 12, + "num_rows": 11108 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000239.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000240.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000241.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000242.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000243.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000244.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000245.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000246.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000247.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000248.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000249.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000250.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000251.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000252.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000253.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000254.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000255.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000256.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000257.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000258.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000259.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000260.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000261.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000262.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000263.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000264.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000265.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000266.parquet": { + "num_row_groups": 12, + "num_rows": 11110 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000267.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000268.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000269.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000270.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000271.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000272.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000273.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000274.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000275.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000276.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000277.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000278.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000279.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000280.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000281.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000282.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000283.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000284.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000285.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000286.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000287.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000288.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000289.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000290.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000291.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000292.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000293.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000294.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000295.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000296.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000297.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000298.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000299.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000300.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000301.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000302.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000303.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000304.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000305.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000306.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000307.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000308.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000309.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000310.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000311.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000312.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000313.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000314.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000315.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000316.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000317.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000318.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000319.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000320.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000321.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000322.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000323.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000324.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000325.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000326.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000327.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000328.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000329.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000330.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000331.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000332.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000333.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000334.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000335.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000336.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000337.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000338.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000339.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000340.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000341.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000342.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000343.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000344.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000345.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000346.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000347.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000348.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000349.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000350.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000351.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000352.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000353.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000354.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000355.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000356.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000357.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000358.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000359.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000360.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000361.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000362.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000363.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000364.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000365.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000366.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000367.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000368.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000369.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000370.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000371.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000372.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000373.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000374.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000375.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000376.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000377.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000378.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000379.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000380.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000381.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000382.parquet": { + "num_row_groups": 12, + "num_rows": 11148 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000383.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000384.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000385.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000386.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000387.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000388.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000389.parquet": { + "num_row_groups": 12, + "num_rows": 11106 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000390.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000391.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000392.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000393.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000394.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000395.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000396.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000397.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000398.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000399.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000400.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000401.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000402.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000403.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000404.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000405.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000406.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000407.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000408.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000409.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000410.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000411.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000412.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000413.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000414.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000415.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000416.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000417.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000418.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000419.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000420.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000421.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000422.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000423.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000424.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000425.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000426.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000427.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000428.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000429.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000430.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000431.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000432.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000433.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000434.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000435.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000436.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000437.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000438.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000439.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000440.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000441.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000442.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000443.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000444.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000445.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000446.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000447.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000448.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000449.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000450.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000451.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000452.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000453.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000454.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000455.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000456.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000457.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000458.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000459.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000460.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000461.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000462.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000463.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000464.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000465.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000466.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000467.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000468.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000469.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000470.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000471.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000472.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000473.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000474.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000475.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000476.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000477.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000478.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000479.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000480.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000481.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000482.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000483.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000484.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000485.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000486.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000487.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000488.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000489.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000490.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000491.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000492.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000493.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000494.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000495.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000496.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000497.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000498.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000499.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000500.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000501.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000502.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000503.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000504.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000505.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000506.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000507.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000508.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000509.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000510.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000511.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000512.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000513.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000514.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000515.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000516.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000517.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000518.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000519.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000520.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000521.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000522.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000523.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000524.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000525.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000526.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000527.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000528.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000529.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000530.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000531.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000532.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000533.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000534.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000535.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000536.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000537.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000538.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000539.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000540.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000541.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000542.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000543.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000544.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000545.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000546.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000547.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000548.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000549.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000550.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000551.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000552.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000553.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000554.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000555.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000556.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000557.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000558.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000559.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000560.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000561.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000562.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000563.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000564.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000565.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000566.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000567.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000568.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000569.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000570.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000571.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000572.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000573.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000574.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000575.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000576.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000577.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000578.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000579.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000580.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000581.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000582.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000583.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000584.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000585.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000586.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000587.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000588.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000589.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000590.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000591.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000592.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000593.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000594.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000595.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000596.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000597.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000598.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000599.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000600.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000601.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000602.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000603.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000604.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000605.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000606.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000607.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000608.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000609.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000610.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000611.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000612.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000613.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000614.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000615.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000616.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000617.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000618.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000619.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000620.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000621.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000622.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000623.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000624.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000625.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000626.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000627.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000628.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000629.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000630.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000631.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000632.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000633.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000634.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000635.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000636.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000637.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000638.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000639.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000640.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000641.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000642.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000643.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000644.parquet": { + "num_row_groups": 12, + "num_rows": 11113 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000645.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000646.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000647.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000648.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000649.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000650.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000651.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000652.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000653.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000654.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000655.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000656.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000657.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000658.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000659.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000660.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000661.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000662.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000663.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000664.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000665.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000666.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000667.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000668.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000669.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000670.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000671.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000672.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000673.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000674.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000675.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000676.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000677.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000678.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000679.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000680.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000681.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000682.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000683.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000684.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000685.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000686.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000687.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000688.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000689.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000690.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000691.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000692.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000693.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000694.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000695.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000696.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000697.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000698.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000699.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000700.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000701.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000702.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000703.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000704.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000705.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000706.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000707.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000708.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000709.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000710.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000711.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000712.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000713.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000714.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000715.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000716.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000717.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000718.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000719.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000720.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000721.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000722.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000723.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000724.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000725.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000726.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000727.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000728.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000729.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000730.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000731.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000732.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000733.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000734.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000735.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000736.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000737.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000738.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000739.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000740.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000741.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000742.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000743.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000744.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000745.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000746.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000747.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000748.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000749.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000750.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000751.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000752.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000753.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000754.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000755.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000756.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000757.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000758.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000759.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000760.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000761.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000762.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000763.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000764.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000765.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000766.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000767.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000768.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000769.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000770.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000771.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000772.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000773.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000774.parquet": { + "num_row_groups": 12, + "num_rows": 11153 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000775.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000776.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000777.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000778.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000779.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000780.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000781.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000782.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000783.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000784.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000785.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000786.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000787.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000788.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000789.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000790.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000791.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000792.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000793.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000794.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000795.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000796.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000797.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000798.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000799.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000800.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000801.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000802.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000803.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000804.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000805.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000806.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000807.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000808.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000809.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000810.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000811.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000812.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000813.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000814.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000815.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000816.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000817.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000818.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000819.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000820.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000821.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000822.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000823.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000824.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000825.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000826.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000827.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000828.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000829.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000830.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000831.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000832.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000833.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000834.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000835.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000836.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000837.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000838.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000839.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000840.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000841.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000842.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000843.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000844.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000845.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000846.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000847.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000848.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000849.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000850.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000851.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000852.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000853.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000854.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000855.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000856.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000857.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000858.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000859.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000860.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000861.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000862.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000863.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000864.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000865.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000866.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000867.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000868.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000869.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000870.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000871.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000872.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000873.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000874.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000875.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000876.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000877.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000878.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000879.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000880.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000881.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000882.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000883.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000884.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000885.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000886.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000887.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000888.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000889.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000890.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000891.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000892.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000893.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000894.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000895.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000896.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000897.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000898.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000899.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000900.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000901.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000902.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000903.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000904.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000905.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000906.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000907.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000908.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000909.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000910.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000911.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000912.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000913.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000914.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000915.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000916.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000917.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000918.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000919.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000920.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000921.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000922.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000923.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000924.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000925.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000926.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000927.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000928.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000929.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000930.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000931.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000932.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000933.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000934.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000935.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000936.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000937.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000938.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000939.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000940.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000941.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000942.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000943.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000944.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000945.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000946.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000947.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000948.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000949.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000950.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000951.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000952.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000953.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000954.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000955.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000956.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000957.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000958.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000959.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000960.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000961.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000962.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000963.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000964.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000965.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000966.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000967.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000968.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000969.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000970.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000971.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000972.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000973.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000974.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000975.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000976.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000977.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000978.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000979.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000980.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000981.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000982.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000983.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000984.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000985.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000986.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000987.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000988.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000989.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000990.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000991.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000992.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000993.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000994.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000995.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000996.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000997.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000998.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000999.parquet": { + "num_row_groups": 11, + "num_rows": 10496 + } +} \ No newline at end of file diff --git a/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json b/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json new file mode 100644 index 0000000000000000000000000000000000000000..edf3918ab4a71d56c95a9e844c6c251efb6d52f8 --- /dev/null +++ b/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json @@ -0,0 +1,11566 @@ +{ + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000000.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000001.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000002.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000003.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000004.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000005.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000006.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000007.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000008.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000009.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000010.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000011.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000012.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000013.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000014.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000015.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000016.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000017.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000018.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000019.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000020.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000021.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000022.parquet": { + "num_row_groups": 12, + "num_rows": 11113 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000023.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000024.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000025.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000026.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000027.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000028.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000029.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000030.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000031.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000032.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000033.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000034.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000035.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000036.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000037.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000038.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000039.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000040.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000041.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000042.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000043.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000044.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000045.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000046.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000047.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000048.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000049.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000050.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000051.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000052.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000053.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000054.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000055.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000056.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000057.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000058.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000059.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000060.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000061.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000062.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000063.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000064.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000065.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000066.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000067.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000068.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000069.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000070.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000071.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000072.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000073.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000074.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000075.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000076.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000077.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000078.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000079.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000080.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000081.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000082.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000083.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000084.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000085.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000086.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000087.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000088.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000089.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000090.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000091.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000092.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000093.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000094.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000095.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000096.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000097.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000098.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000099.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000100.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000101.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000102.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000103.parquet": { + "num_row_groups": 12, + "num_rows": 11111 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000104.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000105.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000106.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000107.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000108.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000109.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000110.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000111.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000112.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000113.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000114.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000115.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000116.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000117.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000118.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000119.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000120.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000121.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000122.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000123.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000124.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000125.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000126.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000127.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000128.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000129.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000130.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000131.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000132.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000133.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000134.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000135.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000136.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000137.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000138.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000139.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000140.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000141.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000142.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000143.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000144.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000145.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000146.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000147.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000148.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000149.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000150.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000151.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000152.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000153.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000154.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000155.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000156.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000157.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000158.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000159.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000160.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000161.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000162.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000163.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000164.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000165.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000166.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000167.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000168.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000169.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000170.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000171.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000172.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000173.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000174.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000175.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000176.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000177.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000178.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000179.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000180.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000181.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000182.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000183.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000184.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000185.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000186.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000187.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000188.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000189.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000190.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000191.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000192.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000193.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000194.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000195.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000196.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000197.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000198.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000199.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000200.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000201.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000202.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000203.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000204.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000205.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000206.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000207.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000208.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000209.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000210.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000211.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000212.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000213.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000214.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000215.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000216.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000217.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000218.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000219.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000220.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000221.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000222.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000223.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000224.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000225.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000226.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000227.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000228.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000229.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000230.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000231.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000232.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000233.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000234.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000235.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000236.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000237.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000238.parquet": { + "num_row_groups": 12, + "num_rows": 11108 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000239.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000240.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000241.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000242.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000243.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000244.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000245.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000246.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000247.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000248.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000249.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000250.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000251.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000252.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000253.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000254.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000255.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000256.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000257.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000258.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000259.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000260.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000261.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000262.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000263.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000264.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000265.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000266.parquet": { + "num_row_groups": 12, + "num_rows": 11110 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000267.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000268.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000269.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000270.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000271.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000272.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000273.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000274.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000275.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000276.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000277.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000278.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000279.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000280.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000281.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000282.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000283.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000284.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000285.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000286.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000287.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000288.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000289.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000290.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000291.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000292.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000293.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000294.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000295.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000296.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000297.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000298.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000299.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000300.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000301.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000302.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000303.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000304.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000305.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000306.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000307.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000308.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000309.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000310.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000311.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000312.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000313.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000314.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000315.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000316.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000317.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000318.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000319.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000320.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000321.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000322.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000323.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000324.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000325.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000326.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000327.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000328.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000329.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000330.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000331.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000332.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000333.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000334.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000335.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000336.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000337.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000338.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000339.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000340.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000341.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000342.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000343.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000344.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000345.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000346.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000347.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000348.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000349.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000350.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000351.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000352.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000353.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000354.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000355.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000356.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000357.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000358.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000359.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000360.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000361.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000362.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000363.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000364.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000365.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000366.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000367.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000368.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000369.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000370.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000371.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000372.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000373.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000374.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000375.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000376.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000377.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000378.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000379.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000380.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000381.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000382.parquet": { + "num_row_groups": 12, + "num_rows": 11148 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000383.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000384.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000385.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000386.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000387.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000388.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000389.parquet": { + "num_row_groups": 12, + "num_rows": 11106 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000390.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000391.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000392.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000393.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000394.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000395.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000396.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000397.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000398.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000399.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000400.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000401.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000402.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000403.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000404.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000405.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000406.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000407.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000408.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000409.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000410.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000411.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000412.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000413.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000414.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000415.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000416.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000417.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000418.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000419.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000420.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000421.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000422.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000423.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000424.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000425.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000426.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000427.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000428.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000429.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000430.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000431.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000432.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000433.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000434.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000435.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000436.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000437.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000438.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000439.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000440.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000441.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000442.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000443.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000444.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000445.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000446.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000447.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000448.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000449.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000450.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000451.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000452.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000453.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000454.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000455.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000456.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000457.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000458.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000459.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000460.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000461.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000462.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000463.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000464.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000465.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000466.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000467.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000468.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000469.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000470.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000471.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000472.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000473.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000474.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000475.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000476.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000477.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000478.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000479.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000480.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000481.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000482.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000483.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000484.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000485.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000486.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000487.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000488.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000489.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000490.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000491.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000492.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000493.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000494.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000495.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000496.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000497.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000498.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000499.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000500.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000501.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000502.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000503.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000504.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000505.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000506.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000507.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000508.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000509.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000510.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000511.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000512.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000513.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000514.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000515.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000516.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000517.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000518.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000519.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000520.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000521.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000522.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000523.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000524.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000525.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000526.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000527.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000528.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000529.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000530.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000531.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000532.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000533.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000534.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000535.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000536.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000537.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000538.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000539.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000540.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000541.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000542.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000543.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000544.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000545.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000546.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000547.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000548.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000549.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000550.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000551.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000552.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000553.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000554.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000555.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000556.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000557.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000558.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000559.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000560.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000561.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000562.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000563.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000564.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000565.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000566.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000567.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000568.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000569.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000570.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000571.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000572.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000573.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000574.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000575.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000576.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000577.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000578.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000579.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000580.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000581.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000582.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000583.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000584.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000585.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000586.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000587.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000588.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000589.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000590.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000591.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000592.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000593.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000594.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000595.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000596.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000597.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000598.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000599.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000600.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000601.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000602.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000603.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000604.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000605.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000606.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000607.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000608.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000609.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000610.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000611.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000612.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000613.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000614.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000615.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000616.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000617.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000618.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000619.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000620.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000621.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000622.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000623.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000624.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000625.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000626.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000627.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000628.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000629.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000630.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000631.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000632.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000633.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000634.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000635.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000636.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000637.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000638.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000639.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000640.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000641.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000642.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000643.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000644.parquet": { + "num_row_groups": 12, + "num_rows": 11113 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000645.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000646.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000647.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000648.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000649.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000650.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000651.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000652.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000653.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000654.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000655.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000656.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000657.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000658.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000659.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000660.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000661.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000662.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000663.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000664.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000665.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000666.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000667.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000668.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000669.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000670.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000671.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000672.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000673.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000674.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000675.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000676.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000677.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000678.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000679.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000680.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000681.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000682.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000683.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000684.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000685.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000686.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000687.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000688.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000689.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000690.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000691.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000692.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000693.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000694.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000695.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000696.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000697.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000698.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000699.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000700.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000701.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000702.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000703.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000704.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000705.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000706.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000707.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000708.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000709.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000710.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000711.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000712.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000713.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000714.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000715.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000716.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000717.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000718.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000719.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000720.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000721.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000722.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000723.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000724.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000725.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000726.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000727.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000728.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000729.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000730.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000731.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000732.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000733.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000734.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000735.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000736.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000737.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000738.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000739.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000740.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000741.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000742.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000743.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000744.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000745.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000746.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000747.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000748.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000749.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000750.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000751.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000752.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000753.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000754.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000755.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000756.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000757.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000758.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000759.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000760.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000761.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000762.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000763.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000764.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000765.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000766.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000767.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000768.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000769.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000770.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000771.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000772.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000773.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000774.parquet": { + "num_row_groups": 12, + "num_rows": 11153 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000775.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000776.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000777.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000778.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000779.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000780.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000781.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000782.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000783.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000784.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000785.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000786.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000787.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000788.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000789.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000790.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000791.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000792.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000793.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000794.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000795.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000796.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000797.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000798.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000799.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000800.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000801.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000802.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000803.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000804.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000805.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000806.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000807.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000808.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000809.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000810.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000811.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000812.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000813.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000814.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000815.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000816.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000817.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000818.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000819.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000820.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000821.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000822.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000823.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000824.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000825.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000826.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000827.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000828.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000829.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000830.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000831.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000832.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000833.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000834.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000835.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000836.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000837.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000838.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000839.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000840.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000841.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000842.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000843.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000844.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000845.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000846.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000847.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000848.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000849.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000850.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000851.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000852.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000853.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000854.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000855.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000856.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000857.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000858.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000859.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000860.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000861.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000862.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000863.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000864.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000865.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000866.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000867.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000868.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000869.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000870.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000871.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000872.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000873.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000874.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000875.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000876.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000877.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000878.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000879.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000880.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000881.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000882.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000883.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000884.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000885.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000886.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000887.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000888.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000889.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000890.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000891.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000892.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000893.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000894.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000895.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000896.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000897.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000898.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000899.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000900.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000901.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000902.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000903.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000904.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000905.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000906.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000907.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000908.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000909.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000910.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000911.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000912.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000913.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000914.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000915.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000916.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000917.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000918.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000919.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000920.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000921.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000922.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000923.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000924.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000925.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000926.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000927.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000928.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000929.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000930.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000931.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000932.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000933.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000934.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000935.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000936.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000937.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000938.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000939.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000940.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000941.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000942.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000943.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000944.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000945.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000946.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000947.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000948.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000949.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000950.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000951.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000952.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000953.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000954.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000955.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000956.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000957.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000958.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000959.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000960.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000961.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000962.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000963.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000964.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000965.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000966.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000967.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000968.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000969.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000970.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000971.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000972.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000973.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000974.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000975.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000976.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000977.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000978.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000979.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000980.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000981.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000982.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000983.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000984.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000985.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000986.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000987.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000988.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000989.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000990.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000991.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000992.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000993.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000994.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000995.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000996.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000997.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000998.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/sa_000999.parquet": { + "num_row_groups": 11, + "num_rows": 10496 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_1.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_10.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_100.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_101.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_102.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_103.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_104.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_105.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_106.parquet": { + "num_row_groups": 10, + "num_rows": 9949 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_107.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_108.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_109.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_11.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_110.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_111.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_112.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_113.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_114.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_115.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_116.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_117.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_118.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_119.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_12.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_120.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_121.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_122.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_123.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_124.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_125.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_126.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_127.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_128.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_129.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_13.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_130.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_131.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_132.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_133.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_134.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_135.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_136.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_137.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_138.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_139.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_14.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_140.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_141.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_142.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_143.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_144.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_145.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_146.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_147.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_148.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_149.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_15.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_150.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_151.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_152.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_153.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_154.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_155.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_156.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_157.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_158.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_159.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_16.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_160.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_161.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_162.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_163.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_164.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_165.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_166.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_167.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_168.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_169.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_17.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_170.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_171.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_172.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_173.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_174.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_175.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_176.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_177.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_178.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_179.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_18.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_180.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_181.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_182.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_183.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_184.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_185.parquet": { + "num_row_groups": 10, + "num_rows": 9956 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_186.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_187.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_188.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_189.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_19.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_190.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_191.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_192.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_193.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_194.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_195.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_196.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_197.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_198.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_199.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_2.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_20.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_200.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_201.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_202.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_203.parquet": { + "num_row_groups": 10, + "num_rows": 9952 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_204.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_205.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_206.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_207.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_208.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_209.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_21.parquet": { + "num_row_groups": 10, + "num_rows": 9955 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_210.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_211.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_212.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_213.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_214.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_215.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_216.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_217.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_218.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_219.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_22.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_220.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_221.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_222.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_223.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_224.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_225.parquet": { + "num_row_groups": 10, + "num_rows": 9954 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_226.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_227.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_228.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_229.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_23.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_230.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_231.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_232.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_233.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_234.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_235.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_236.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_237.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_238.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_239.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_24.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_240.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_241.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_242.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_243.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_244.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_245.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_246.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_247.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_248.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_249.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_25.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_250.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_251.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_252.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_253.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_254.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_255.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_256.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_257.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_258.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_259.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_26.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_260.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_261.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_262.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_263.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_264.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_265.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_266.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_267.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_268.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_269.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_27.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_270.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_271.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_272.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_273.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_274.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_275.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_276.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_277.parquet": { + "num_row_groups": 10, + "num_rows": 9946 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_278.parquet": { + "num_row_groups": 10, + "num_rows": 9954 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_279.parquet": { + "num_row_groups": 10, + "num_rows": 9953 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_28.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_280.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_281.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_282.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_283.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_284.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_285.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_286.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_287.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_288.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_289.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_29.parquet": { + "num_row_groups": 10, + "num_rows": 9953 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_290.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_291.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_292.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_293.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_294.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_295.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_296.parquet": { + "num_row_groups": 10, + "num_rows": 9953 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_297.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_298.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_299.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_3.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_30.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_300.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_301.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_302.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_303.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_304.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_305.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_306.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_307.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_308.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_309.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_31.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_310.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_311.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_312.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_313.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_314.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_315.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_316.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_317.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_318.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_319.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_32.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_320.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_321.parquet": { + "num_row_groups": 10, + "num_rows": 9953 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_322.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_323.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_324.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_325.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_326.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_327.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_328.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_329.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_33.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_330.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_331.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_332.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_333.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_334.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_335.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_336.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_337.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_338.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_339.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_34.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_340.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_341.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_342.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_343.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_344.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_345.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_346.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_347.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_348.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_349.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_35.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_350.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_351.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_352.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_353.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_354.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_355.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_356.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_357.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_358.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_359.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_36.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_360.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_361.parquet": { + "num_row_groups": 10, + "num_rows": 9956 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_362.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_363.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_364.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_365.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_366.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_367.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_368.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_369.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_37.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_370.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_371.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_372.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_373.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_374.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_375.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_376.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_377.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_378.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_379.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_38.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_380.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_381.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_382.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_383.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_384.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_385.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_386.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_387.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_388.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_389.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_39.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_390.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_391.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_392.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_393.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_394.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_395.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_396.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_397.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_398.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_399.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_4.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_40.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_400.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_401.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_402.parquet": { + "num_row_groups": 10, + "num_rows": 9956 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_403.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_404.parquet": { + "num_row_groups": 10, + "num_rows": 9958 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_405.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_406.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_407.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_408.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_409.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_41.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_410.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_411.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_412.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_413.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_414.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_415.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_416.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_417.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_418.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_419.parquet": { + "num_row_groups": 10, + "num_rows": 9716 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_42.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_43.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_44.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_45.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_46.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_47.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_48.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_49.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_5.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_50.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_51.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_52.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_53.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_54.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_55.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_56.parquet": { + "num_row_groups": 10, + "num_rows": 9952 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_57.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_58.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_59.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_6.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_60.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_61.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_62.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_63.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_64.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_65.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_66.parquet": { + "num_row_groups": 10, + "num_rows": 9936 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_67.parquet": { + "num_row_groups": 10, + "num_rows": 9929 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_68.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_69.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_7.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_70.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_71.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_72.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_73.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_74.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_75.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_76.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_77.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_78.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_79.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_8.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_80.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_81.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_82.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_83.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_84.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_85.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_86.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_87.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_88.parquet": { + "num_row_groups": 10, + "num_rows": 9949 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_89.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_9.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_90.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_91.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_92.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_93.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_94.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_95.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_96.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_97.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_98.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_JDB_99.parquet": { + "num_row_groups": 10, + "num_rows": 9958 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_000.parquet": { + "num_row_groups": 10, + "num_rows": 9780 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_001.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_002.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_003.parquet": { + "num_row_groups": 10, + "num_rows": 9773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_004.parquet": { + "num_row_groups": 5, + "num_rows": 4947 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_006.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_007.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_008.parquet": { + "num_row_groups": 10, + "num_rows": 9789 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_009.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_010.parquet": { + "num_row_groups": 7, + "num_rows": 6635 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_012.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_013.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_014.parquet": { + "num_row_groups": 10, + "num_rows": 9713 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_015.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_016.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_017.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_018.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_019.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_020.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_021.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_022.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_023.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_024.parquet": { + "num_row_groups": 6, + "num_rows": 5378 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_027.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_028.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_029.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_030.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_031.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_032.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_033.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_034.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_035.parquet": { + "num_row_groups": 5, + "num_rows": 4731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_036.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_037.parquet": { + "num_row_groups": 7, + "num_rows": 6180 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_039.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_040.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_041.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_042.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_043.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_044.parquet": { + "num_row_groups": 5, + "num_rows": 4971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_045.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_046.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_047.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_048.parquet": { + "num_row_groups": 9, + "num_rows": 8996 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_051.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_052.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_053.parquet": { + "num_row_groups": 5, + "num_rows": 4792 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_054.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_055.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_056.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_057.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_058.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_059.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_060.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_061.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_062.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_063.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_064.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_065.parquet": { + "num_row_groups": 4, + "num_rows": 3913 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_066.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_067.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_068.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_069.parquet": { + "num_row_groups": 10, + "num_rows": 9781 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_070.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_071.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_072.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_073.parquet": { + "num_row_groups": 6, + "num_rows": 5429 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_075.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_076.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_077.parquet": { + "num_row_groups": 10, + "num_rows": 9213 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_078.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_079.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_080.parquet": { + "num_row_groups": 1, + "num_rows": 554 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_081.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_082.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_083.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_084.parquet": { + "num_row_groups": 5, + "num_rows": 4672 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_087.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_088.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_089.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_090.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_091.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_092.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_093.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_094.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_095.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_096.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_097.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_098.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_099.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_100.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1000.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1001.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1002.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1003.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1004.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1005.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1006.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1007.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1008.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1009.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_101.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1010.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1011.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1012.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1013.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1014.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1015.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1016.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1017.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1018.parquet": { + "num_row_groups": 7, + "num_rows": 6906 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_102.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1020.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1021.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1022.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1023.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1024.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1025.parquet": { + "num_row_groups": 1, + "num_rows": 429 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1026.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1027.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1028.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1029.parquet": { + "num_row_groups": 10, + "num_rows": 9717 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_103.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1030.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1031.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1032.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1033.parquet": { + "num_row_groups": 10, + "num_rows": 9722 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1034.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1035.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1036.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1037.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1038.parquet": { + "num_row_groups": 8, + "num_rows": 7517 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_104.parquet": { + "num_row_groups": 1, + "num_rows": 705 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1041.parquet": { + "num_row_groups": 4, + "num_rows": 3042 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1044.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1045.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1046.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1047.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1048.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1049.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_105.parquet": { + "num_row_groups": 9, + "num_rows": 8703 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1050.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1051.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1052.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1053.parquet": { + "num_row_groups": 2, + "num_rows": 1531 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1056.parquet": { + "num_row_groups": 4, + "num_rows": 3281 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1059.parquet": { + "num_row_groups": 10, + "num_rows": 9715 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1060.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1061.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1062.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1063.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1064.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1065.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1066.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1067.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1068.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1069.parquet": { + "num_row_groups": 6, + "num_rows": 5668 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1071.parquet": { + "num_row_groups": 5, + "num_rows": 4624 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1074.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1075.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1076.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1077.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1078.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1079.parquet": { + "num_row_groups": 10, + "num_rows": 9722 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_108.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1080.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1081.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1082.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1083.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1084.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1085.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1086.parquet": { + "num_row_groups": 4, + "num_rows": 3101 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1089.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_109.parquet": { + "num_row_groups": 5, + "num_rows": 4974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1090.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1091.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1092.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1093.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1094.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1095.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1096.parquet": { + "num_row_groups": 9, + "num_rows": 8375 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1098.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1099.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1100.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1101.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1102.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1103.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1104.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1105.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1106.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1107.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1108.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1109.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_111.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1110.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1111.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1112.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1113.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1114.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1115.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1116.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1117.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1118.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1119.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_112.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1120.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1121.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1122.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1123.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1124.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1125.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1126.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1127.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1128.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1129.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_113.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1130.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1131.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1132.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1133.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1134.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1135.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1136.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1137.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1138.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1139.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_114.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1140.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1141.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1142.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1143.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1144.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1145.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1146.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1147.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1148.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1149.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_115.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1150.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1151.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1152.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1153.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1154.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1155.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1156.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1157.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1158.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1159.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_116.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1160.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1161.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1162.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1163.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1164.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1165.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1166.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1167.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1168.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1169.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_117.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1170.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1171.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1172.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1173.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1174.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1175.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1176.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1177.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1178.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1179.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_118.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1180.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1181.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1182.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1183.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1184.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1185.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1186.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1187.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1188.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1189.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_119.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1190.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1191.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1192.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1193.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1194.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1195.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1196.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1197.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1198.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1199.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_120.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1200.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1201.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1202.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1203.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1204.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1205.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1206.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1207.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1208.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1209.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_121.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1210.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1211.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1212.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1213.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1214.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1215.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1216.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1217.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1218.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1219.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_122.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1220.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1221.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1222.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1223.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1224.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1225.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1226.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1227.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1228.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1229.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_123.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1230.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1231.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1232.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1233.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1234.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1235.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1236.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1237.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1238.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1239.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_124.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1240.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1241.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1242.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1243.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1244.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1245.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1246.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1247.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1248.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1249.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_125.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1250.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1251.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1252.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1253.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1254.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1255.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1256.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1257.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1258.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1259.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_126.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1260.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1261.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1262.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1263.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1264.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1265.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1266.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1267.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1268.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1269.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_127.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1270.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1271.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1272.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1273.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1274.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1275.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1276.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1277.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1278.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1279.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_128.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1280.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1281.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1282.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1283.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1284.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1285.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1286.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1287.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1288.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1289.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_129.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1290.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1291.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1292.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1293.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1294.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1295.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1296.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1297.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1298.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1299.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_130.parquet": { + "num_row_groups": 3, + "num_rows": 2020 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1300.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1301.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1302.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1303.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1304.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1305.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1306.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1307.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1308.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1309.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1310.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1311.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1312.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1313.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1314.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1315.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1316.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1317.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1318.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1319.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_132.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1320.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1321.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1322.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1323.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1324.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1325.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1326.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1327.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1328.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1329.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_133.parquet": { + "num_row_groups": 10, + "num_rows": 9720 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1330.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1331.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1332.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1333.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1334.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1335.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1336.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1337.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1338.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1339.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_134.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1340.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1341.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1342.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1343.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1344.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1345.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1346.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1347.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1348.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1349.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_135.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1350.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1351.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1352.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1353.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1354.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1355.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1356.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1357.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1358.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1359.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_136.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1360.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1361.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1362.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1363.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1364.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1365.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1366.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1367.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1368.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1369.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_137.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1370.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1371.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1372.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1373.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1374.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1375.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1376.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1377.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1378.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1379.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_138.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1380.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1381.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1382.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1383.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1384.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1385.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1386.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1387.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1388.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1389.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_139.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1390.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1391.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1392.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1393.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1394.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1395.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1396.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1397.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1398.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1399.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_140.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1400.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1401.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1402.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1403.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1404.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1405.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1406.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1407.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1408.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1409.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_141.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1410.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1411.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1412.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1413.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1414.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1415.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1416.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1417.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1418.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1419.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_142.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1420.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1421.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1422.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1423.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1424.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1425.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1426.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1427.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1428.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1429.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_143.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1430.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1431.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1432.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1433.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1434.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1435.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1436.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1437.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1438.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1439.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_144.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1440.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1441.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1442.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1443.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1444.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1445.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1446.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1447.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1448.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1449.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_145.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1450.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1451.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1452.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1453.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1454.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1455.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1456.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1457.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1458.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1459.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_146.parquet": { + "num_row_groups": 1, + "num_rows": 780 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1460.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1461.parquet": { + "num_row_groups": 10, + "num_rows": 9993 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1462.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1463.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1464.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1465.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1466.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1467.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1468.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1469.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_147.parquet": { + "num_row_groups": 5, + "num_rows": 4475 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1470.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1471.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1472.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1473.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1474.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1475.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1476.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1477.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1478.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1479.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1480.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1481.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1482.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1483.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1484.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1485.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1486.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1487.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1488.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1489.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1490.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1491.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1492.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1493.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1494.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1495.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1496.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1497.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1498.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1499.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_150.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1500.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1501.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1502.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1503.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1504.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1505.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1506.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1507.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1508.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1509.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_151.parquet": { + "num_row_groups": 10, + "num_rows": 9782 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1510.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1511.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1512.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1513.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1514.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1515.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1516.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1517.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1518.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1519.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_152.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1520.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1521.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1522.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1523.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1524.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1525.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1526.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1527.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1528.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1529.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_153.parquet": { + "num_row_groups": 7, + "num_rows": 6457 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1530.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1531.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1532.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1533.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1534.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1535.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1536.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1537.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1538.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1539.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1540.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1541.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1542.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1543.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1544.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1545.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1546.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1547.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1548.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1549.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1550.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1551.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1552.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1553.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1554.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1555.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1556.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1557.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1558.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1559.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_156.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1560.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1561.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1562.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1563.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1564.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1565.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1566.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1567.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1568.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1569.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_157.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1570.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1571.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1572.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1573.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1574.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1575.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1576.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1577.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1578.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1579.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_158.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1580.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1581.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1582.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1583.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1584.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1585.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1586.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1587.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1588.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1589.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_159.parquet": { + "num_row_groups": 10, + "num_rows": 9795 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1590.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1591.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1592.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1593.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1594.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1595.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1596.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_1597.parquet": { + "num_row_groups": 9, + "num_rows": 8956 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_160.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_161.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_162.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_163.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_164.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_165.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_166.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_167.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_168.parquet": { + "num_row_groups": 10, + "num_rows": 9696 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_169.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_170.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_171.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_172.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_173.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_174.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_175.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_176.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_177.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_178.parquet": { + "num_row_groups": 8, + "num_rows": 7121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_180.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_181.parquet": { + "num_row_groups": 9, + "num_rows": 8926 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_183.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_184.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_185.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_186.parquet": { + "num_row_groups": 10, + "num_rows": 9720 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_187.parquet": { + "num_row_groups": 4, + "num_rows": 3230 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_189.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_190.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_191.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_192.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_193.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_194.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_195.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_196.parquet": { + "num_row_groups": 9, + "num_rows": 8369 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_198.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_199.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_200.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_201.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_202.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_203.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_204.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_205.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_206.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_207.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_208.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_209.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_210.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_211.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_212.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_213.parquet": { + "num_row_groups": 5, + "num_rows": 4216 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_216.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_217.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_218.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_219.parquet": { + "num_row_groups": 10, + "num_rows": 9790 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_220.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_221.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_222.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_223.parquet": { + "num_row_groups": 5, + "num_rows": 4315 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_225.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_226.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_227.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_228.parquet": { + "num_row_groups": 7, + "num_rows": 6321 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_231.parquet": { + "num_row_groups": 7, + "num_rows": 6690 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_234.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_235.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_236.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_237.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_238.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_239.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_240.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_241.parquet": { + "num_row_groups": 10, + "num_rows": 9701 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_242.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_243.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_244.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_245.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_246.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_247.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_248.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_249.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_250.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_251.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_252.parquet": { + "num_row_groups": 10, + "num_rows": 9715 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_253.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_254.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_255.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_256.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_257.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_258.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_259.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_260.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_261.parquet": { + "num_row_groups": 10, + "num_rows": 9424 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_264.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_265.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_266.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_267.parquet": { + "num_row_groups": 10, + "num_rows": 9719 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_268.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_269.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_270.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_271.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_272.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_273.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_274.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_275.parquet": { + "num_row_groups": 8, + "num_rows": 7713 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_276.parquet": { + "num_row_groups": 2, + "num_rows": 1695 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_279.parquet": { + "num_row_groups": 10, + "num_rows": 9790 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_280.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_281.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_282.parquet": { + "num_row_groups": 7, + "num_rows": 6657 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_285.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_286.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_287.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_288.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_289.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_290.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_291.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_292.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_293.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_294.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_295.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_296.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_297.parquet": { + "num_row_groups": 10, + "num_rows": 9783 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_298.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_299.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_300.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_301.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_302.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_303.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_304.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_305.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_306.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_307.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_308.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_309.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_310.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_311.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_312.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_313.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_314.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_315.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_316.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_317.parquet": { + "num_row_groups": 10, + "num_rows": 9020 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_318.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_319.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_320.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_321.parquet": { + "num_row_groups": 8, + "num_rows": 7635 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_324.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_325.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_326.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_327.parquet": { + "num_row_groups": 7, + "num_rows": 6026 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_330.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_331.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_332.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_333.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_334.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_335.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_336.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_337.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_338.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_339.parquet": { + "num_row_groups": 6, + "num_rows": 5086 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_342.parquet": { + "num_row_groups": 10, + "num_rows": 9722 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_343.parquet": { + "num_row_groups": 10, + "num_rows": 9719 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_344.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_345.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_346.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_347.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_348.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_349.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_350.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_351.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_352.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_353.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_354.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_355.parquet": { + "num_row_groups": 10, + "num_rows": 9795 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_356.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_357.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_358.parquet": { + "num_row_groups": 3, + "num_rows": 2126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_360.parquet": { + "num_row_groups": 5, + "num_rows": 4564 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_363.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_364.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_365.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_366.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_367.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_368.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_369.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_370.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_371.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_372.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_373.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_374.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_375.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_376.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_377.parquet": { + "num_row_groups": 6, + "num_rows": 5062 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_378.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_379.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_380.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_381.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_382.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_383.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_384.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_385.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_386.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_387.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_388.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_389.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_390.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_391.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_392.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_393.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_394.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_395.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_396.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_397.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_398.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_399.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_400.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_401.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_402.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_403.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_404.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_405.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_406.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_407.parquet": { + "num_row_groups": 9, + "num_rows": 8643 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_408.parquet": { + "num_row_groups": 10, + "num_rows": 9773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_409.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_410.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_411.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_412.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_413.parquet": { + "num_row_groups": 10, + "num_rows": 9786 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_414.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_415.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_416.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_417.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_418.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_419.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_420.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_421.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_422.parquet": { + "num_row_groups": 1, + "num_rows": 95 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_423.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_424.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_425.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_426.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_427.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_428.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_429.parquet": { + "num_row_groups": 10, + "num_rows": 9719 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_430.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_431.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_432.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_433.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_434.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_435.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_436.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_437.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_438.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_439.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_440.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_441.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_442.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_443.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_444.parquet": { + "num_row_groups": 1, + "num_rows": 223 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_447.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_448.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_449.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_450.parquet": { + "num_row_groups": 5, + "num_rows": 4030 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_453.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_454.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_455.parquet": { + "num_row_groups": 2, + "num_rows": 1446 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_456.parquet": { + "num_row_groups": 10, + "num_rows": 9786 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_457.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_458.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_459.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_460.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_461.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_462.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_463.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_464.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_465.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_466.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_467.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_468.parquet": { + "num_row_groups": 1, + "num_rows": 694 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_471.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_472.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_473.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_474.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_475.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_476.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_477.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_478.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_479.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_480.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_481.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_482.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_483.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_484.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_485.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_486.parquet": { + "num_row_groups": 10, + "num_rows": 9795 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_487.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_488.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_489.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_490.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_491.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_492.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_493.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_494.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_495.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_496.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_497.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_498.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_499.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_500.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_501.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_502.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_503.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_504.parquet": { + "num_row_groups": 4, + "num_rows": 3866 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_507.parquet": { + "num_row_groups": 1, + "num_rows": 413 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_510.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_511.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_512.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_513.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_514.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_515.parquet": { + "num_row_groups": 10, + "num_rows": 9777 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_516.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_517.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_518.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_519.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_520.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_521.parquet": { + "num_row_groups": 5, + "num_rows": 4880 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_522.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_523.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_524.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_525.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_526.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_527.parquet": { + "num_row_groups": 10, + "num_rows": 9405 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_528.parquet": { + "num_row_groups": 9, + "num_rows": 8258 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_531.parquet": { + "num_row_groups": 5, + "num_rows": 4917 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_534.parquet": { + "num_row_groups": 8, + "num_rows": 7602 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_537.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_538.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_539.parquet": { + "num_row_groups": 4, + "num_rows": 3401 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_540.parquet": { + "num_row_groups": 8, + "num_rows": 7562 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_543.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_544.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_545.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_546.parquet": { + "num_row_groups": 10, + "num_rows": 9703 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_547.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_548.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_549.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_550.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_551.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_552.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_553.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_554.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_555.parquet": { + "num_row_groups": 10, + "num_rows": 9720 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_556.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_557.parquet": { + "num_row_groups": 10, + "num_rows": 9722 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_558.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_559.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_560.parquet": { + "num_row_groups": 10, + "num_rows": 9711 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_561.parquet": { + "num_row_groups": 5, + "num_rows": 4773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_564.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_565.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_566.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_567.parquet": { + "num_row_groups": 1, + "num_rows": 632 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_570.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_571.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_572.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_573.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_574.parquet": { + "num_row_groups": 7, + "num_rows": 6741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_576.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_577.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_578.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_579.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_580.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_581.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_582.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_583.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_584.parquet": { + "num_row_groups": 5, + "num_rows": 4751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_585.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_586.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_587.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_588.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_589.parquet": { + "num_row_groups": 8, + "num_rows": 7589 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_591.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_592.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_593.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_594.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_595.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_596.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_597.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_598.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_599.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_600.parquet": { + "num_row_groups": 1, + "num_rows": 230 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_603.parquet": { + "num_row_groups": 5, + "num_rows": 4186 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_606.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_607.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_608.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_609.parquet": { + "num_row_groups": 10, + "num_rows": 9710 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_610.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_611.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_612.parquet": { + "num_row_groups": 10, + "num_rows": 9714 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_613.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_614.parquet": { + "num_row_groups": 10, + "num_rows": 9773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_615.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_616.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_617.parquet": { + "num_row_groups": 2, + "num_rows": 1643 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_618.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_619.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_621.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_622.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_623.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_624.parquet": { + "num_row_groups": 3, + "num_rows": 2207 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_627.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_628.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_629.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_630.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_631.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_632.parquet": { + "num_row_groups": 10, + "num_rows": 9781 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_633.parquet": { + "num_row_groups": 8, + "num_rows": 7619 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_636.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_637.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_638.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_639.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_640.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_641.parquet": { + "num_row_groups": 10, + "num_rows": 9782 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_642.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_643.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_644.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_645.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_646.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_647.parquet": { + "num_row_groups": 2, + "num_rows": 1444 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_648.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_649.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_650.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_651.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_652.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_653.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_654.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_655.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_656.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_657.parquet": { + "num_row_groups": 2, + "num_rows": 1802 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_660.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_661.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_662.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_663.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_664.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_665.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_666.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_667.parquet": { + "num_row_groups": 3, + "num_rows": 2531 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_669.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_670.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_671.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_672.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_673.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_674.parquet": { + "num_row_groups": 4, + "num_rows": 3311 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_675.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_676.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_677.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_678.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_679.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_680.parquet": { + "num_row_groups": 3, + "num_rows": 2382 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_681.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_682.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_683.parquet": { + "num_row_groups": 5, + "num_rows": 4049 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_684.parquet": { + "num_row_groups": 9, + "num_rows": 8589 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_687.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_688.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_689.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_690.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_691.parquet": { + "num_row_groups": 10, + "num_rows": 9777 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_692.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_693.parquet": { + "num_row_groups": 6, + "num_rows": 5555 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_696.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_697.parquet": { + "num_row_groups": 8, + "num_rows": 7922 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_699.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_700.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_701.parquet": { + "num_row_groups": 10, + "num_rows": 9786 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_702.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_703.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_704.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_705.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_706.parquet": { + "num_row_groups": 5, + "num_rows": 4556 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_708.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_709.parquet": { + "num_row_groups": 10, + "num_rows": 9783 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_710.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_711.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_712.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_713.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_714.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_715.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_716.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_717.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_718.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_719.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_720.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_721.parquet": { + "num_row_groups": 10, + "num_rows": 9020 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_723.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_724.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_725.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_726.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_727.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_728.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_729.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_730.parquet": { + "num_row_groups": 9, + "num_rows": 8557 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_732.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_733.parquet": { + "num_row_groups": 4, + "num_rows": 3474 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_735.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_736.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_737.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_738.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_739.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_740.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_741.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_742.parquet": { + "num_row_groups": 10, + "num_rows": 9777 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_743.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_744.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_745.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_746.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_747.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_748.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_749.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_750.parquet": { + "num_row_groups": 10, + "num_rows": 9711 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_751.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_752.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_753.parquet": { + "num_row_groups": 10, + "num_rows": 9716 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_754.parquet": { + "num_row_groups": 7, + "num_rows": 6231 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_756.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_757.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_758.parquet": { + "num_row_groups": 10, + "num_rows": 9773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_759.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_760.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_761.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_762.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_763.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_764.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_765.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_766.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_767.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_768.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_769.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_770.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_771.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_772.parquet": { + "num_row_groups": 3, + "num_rows": 2203 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_774.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_775.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_776.parquet": { + "num_row_groups": 10, + "num_rows": 9782 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_777.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_778.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_779.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_780.parquet": { + "num_row_groups": 5, + "num_rows": 4194 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_783.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_784.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_785.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_786.parquet": { + "num_row_groups": 10, + "num_rows": 9106 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_789.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_790.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_791.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_792.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_793.parquet": { + "num_row_groups": 3, + "num_rows": 2448 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_795.parquet": { + "num_row_groups": 10, + "num_rows": 9793 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_796.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_797.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_798.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_799.parquet": { + "num_row_groups": 6, + "num_rows": 5964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_801.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_802.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_803.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_804.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_805.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_806.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_807.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_808.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_809.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_810.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_811.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_812.parquet": { + "num_row_groups": 2, + "num_rows": 1296 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_813.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_814.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_815.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_816.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_817.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_818.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_819.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_820.parquet": { + "num_row_groups": 10, + "num_rows": 9784 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_821.parquet": { + "num_row_groups": 5, + "num_rows": 4440 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_822.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_823.parquet": { + "num_row_groups": 7, + "num_rows": 6412 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_825.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_826.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_827.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_828.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_829.parquet": { + "num_row_groups": 3, + "num_rows": 2801 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_831.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_832.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_833.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_834.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_835.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_836.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_837.parquet": { + "num_row_groups": 10, + "num_rows": 9777 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_838.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_839.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_840.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_841.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_842.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_843.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_844.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_845.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_846.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_847.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_848.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_849.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_850.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_851.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_852.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_853.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_854.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_855.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_856.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_857.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_858.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_859.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_860.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_861.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_862.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_863.parquet": { + "num_row_groups": 10, + "num_rows": 9787 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_864.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_865.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_866.parquet": { + "num_row_groups": 10, + "num_rows": 9720 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_867.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_868.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_869.parquet": { + "num_row_groups": 4, + "num_rows": 3420 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_870.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_871.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_872.parquet": { + "num_row_groups": 10, + "num_rows": 9718 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_873.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_874.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_875.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_876.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_877.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_878.parquet": { + "num_row_groups": 5, + "num_rows": 4966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_879.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_880.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_881.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_882.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_883.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_884.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_885.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_886.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_887.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_888.parquet": { + "num_row_groups": 5, + "num_rows": 4910 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_891.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_892.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_893.parquet": { + "num_row_groups": 3, + "num_rows": 2022 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_894.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_895.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_896.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_897.parquet": { + "num_row_groups": 9, + "num_rows": 8747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_900.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_901.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_902.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_903.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_904.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_905.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_906.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_907.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_908.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_909.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_910.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_911.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_912.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_913.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_914.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_915.parquet": { + "num_row_groups": 7, + "num_rows": 6922 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_918.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_919.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_920.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_921.parquet": { + "num_row_groups": 8, + "num_rows": 7941 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_924.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_925.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_926.parquet": { + "num_row_groups": 4, + "num_rows": 3447 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_927.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_928.parquet": { + "num_row_groups": 1, + "num_rows": 51 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_930.parquet": { + "num_row_groups": 5, + "num_rows": 4302 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_933.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_934.parquet": { + "num_row_groups": 10, + "num_rows": 9694 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_935.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_936.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_937.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_938.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_939.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_940.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_941.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_942.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_943.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_944.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_945.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_946.parquet": { + "num_row_groups": 10, + "num_rows": 9782 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_947.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_948.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_949.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_950.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_951.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_952.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_953.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_954.parquet": { + "num_row_groups": 10, + "num_rows": 9781 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_955.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_956.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_957.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_958.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_959.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_960.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_961.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_962.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_963.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_964.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_965.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_966.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_967.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_968.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_969.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_970.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_971.parquet": { + "num_row_groups": 2, + "num_rows": 1699 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_972.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_973.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_974.parquet": { + "num_row_groups": 4, + "num_rows": 3975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_975.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_976.parquet": { + "num_row_groups": 10, + "num_rows": 9796 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_977.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_978.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_979.parquet": { + "num_row_groups": 10, + "num_rows": 9792 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_980.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_981.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_982.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_983.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_984.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_985.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_986.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_987.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_988.parquet": { + "num_row_groups": 4, + "num_rows": 3865 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_990.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_991.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_992.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_993.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_994.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_995.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_996.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_997.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_998.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind/webdataset_shard_999.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + } +} \ No newline at end of file diff --git a/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet.json b/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet.json new file mode 100644 index 0000000000000000000000000000000000000000..9751cd5305579a989c2c5911973cf1b5be346cd9 --- /dev/null +++ b/data/bundled_parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet.json @@ -0,0 +1,11554 @@ +{ + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000000.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000001.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000002.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000003.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000004.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000005.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000006.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000007.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000008.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000009.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000010.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000011.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000012.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000013.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000014.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000015.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000016.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000017.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000018.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000019.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000020.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000021.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000022.parquet": { + "num_row_groups": 12, + "num_rows": 11113 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000023.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000024.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000025.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000026.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000027.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000028.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000029.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000030.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000031.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000032.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000033.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000034.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000035.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000036.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000037.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000038.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000039.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000040.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000041.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000042.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000043.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000044.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000045.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000046.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000047.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000048.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000049.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000050.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000051.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000052.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000053.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000054.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000055.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000056.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000057.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000058.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000059.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000060.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000061.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000062.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000063.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000064.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000065.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000066.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000067.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000068.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000069.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000070.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000071.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000072.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000073.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000074.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000075.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000076.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000077.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000078.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000079.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000080.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000081.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000082.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000083.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000084.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000085.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000086.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000087.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000088.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000089.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000090.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000091.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000092.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000093.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000094.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000095.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000096.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000097.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000098.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000099.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000100.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000101.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000102.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000103.parquet": { + "num_row_groups": 12, + "num_rows": 11111 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000104.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000105.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000106.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000107.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000108.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000109.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000110.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000111.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000112.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000113.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000114.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000115.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000116.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000117.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000118.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000119.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000120.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000121.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000122.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000123.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000124.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000125.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000126.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000127.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000128.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000129.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000130.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000131.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000132.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000133.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000134.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000135.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000136.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000137.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000138.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000139.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000140.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000141.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000142.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000143.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000144.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000145.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000146.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000147.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000148.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000149.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000150.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000151.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000152.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000153.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000154.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000155.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000156.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000157.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000158.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000159.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000160.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000161.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000162.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000163.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000164.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000165.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000166.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000167.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000168.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000169.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000170.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000171.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000172.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000173.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000174.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000175.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000176.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000177.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000178.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000179.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000180.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000181.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000182.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000183.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000184.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000185.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000186.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000187.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000188.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000189.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000190.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000191.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000192.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000193.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000194.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000195.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000196.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000197.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000198.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000199.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000200.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000201.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000202.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000203.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000204.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000205.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000206.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000207.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000208.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000209.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000210.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000211.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000212.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000213.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000214.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000215.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000216.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000217.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000218.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000219.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000220.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000221.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000222.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000223.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000224.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000225.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000226.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000227.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000228.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000229.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000230.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000231.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000232.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000233.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000234.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000235.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000236.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000237.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000238.parquet": { + "num_row_groups": 12, + "num_rows": 11108 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000239.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000240.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000241.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000242.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000243.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000244.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000245.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000246.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000247.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000248.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000249.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000250.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000251.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000252.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000253.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000254.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000255.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000256.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000257.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000258.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000259.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000260.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000261.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000262.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000263.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000264.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000265.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000266.parquet": { + "num_row_groups": 12, + "num_rows": 11110 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000267.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000268.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000269.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000270.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000271.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000272.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000273.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000274.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000275.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000276.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000277.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000278.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000279.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000280.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000281.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000282.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000283.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000284.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000285.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000286.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000287.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000288.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000289.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000290.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000291.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000292.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000293.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000294.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000295.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000296.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000297.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000298.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000299.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000300.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000301.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000302.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000303.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000304.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000305.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000306.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000307.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000308.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000309.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000310.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000311.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000312.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000313.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000314.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000315.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000316.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000317.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000318.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000319.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000320.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000321.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000322.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000323.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000324.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000325.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000326.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000327.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000328.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000329.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000330.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000331.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000332.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000333.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000334.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000335.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000336.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000337.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000338.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000339.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000340.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000341.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000342.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000343.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000344.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000345.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000346.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000347.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000348.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000349.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000350.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000351.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000352.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000353.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000354.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000355.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000356.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000357.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000358.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000359.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000360.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000361.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000362.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000363.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000364.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000365.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000366.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000367.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000368.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000369.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000370.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000371.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000372.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000373.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000374.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000375.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000376.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000377.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000378.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000379.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000380.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000381.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000382.parquet": { + "num_row_groups": 12, + "num_rows": 11148 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000383.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000384.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000385.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000386.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000387.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000388.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000389.parquet": { + "num_row_groups": 12, + "num_rows": 11106 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000390.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000391.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000392.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000393.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000394.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000395.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000396.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000397.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000398.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000399.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000400.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000401.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000402.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000403.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000404.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000405.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000406.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000407.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000408.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000409.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000410.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000411.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000412.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000413.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000414.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000415.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000416.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000417.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000418.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000419.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000420.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000421.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000422.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000423.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000424.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000425.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000426.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000427.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000428.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000429.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000430.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000431.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000432.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000433.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000434.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000435.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000436.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000437.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000438.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000439.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000440.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000441.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000442.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000443.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000444.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000445.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000446.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000447.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000448.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000449.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000450.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000451.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000452.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000453.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000454.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000455.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000456.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000457.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000458.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000459.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000460.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000461.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000462.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000463.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000464.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000465.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000466.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000467.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000468.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000469.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000470.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000471.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000472.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000473.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000474.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000475.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000476.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000477.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000478.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000479.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000480.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000481.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000482.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000483.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000484.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000485.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000486.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000487.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000488.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000489.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000490.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000491.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000492.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000493.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000494.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000495.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000496.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000497.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000498.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000499.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000500.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000501.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000502.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000503.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000504.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000505.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000506.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000507.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000508.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000509.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000510.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000511.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000512.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000513.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000514.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000515.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000516.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000517.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000518.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000519.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000520.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000521.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000522.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000523.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000524.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000525.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000526.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000527.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000528.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000529.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000530.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000531.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000532.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000533.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000534.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000535.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000536.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000537.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000538.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000539.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000540.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000541.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000542.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000543.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000544.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000545.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000546.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000547.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000548.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000549.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000550.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000551.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000552.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000553.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000554.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000555.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000556.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000557.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000558.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000559.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000560.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000561.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000562.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000563.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000564.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000565.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000566.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000567.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000568.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000569.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000570.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000571.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000572.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000573.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000574.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000575.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000576.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000577.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000578.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000579.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000580.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000581.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000582.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000583.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000584.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000585.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000586.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000587.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000588.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000589.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000590.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000591.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000592.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000593.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000594.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000595.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000596.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000597.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000598.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000599.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000600.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000601.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000602.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000603.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000604.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000605.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000606.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000607.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000608.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000609.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000610.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000611.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000612.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000613.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000614.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000615.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000616.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000617.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000618.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000619.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000620.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000621.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000622.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000623.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000624.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000625.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000626.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000627.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000628.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000629.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000630.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000631.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000632.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000633.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000634.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000635.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000636.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000637.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000638.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000639.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000640.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000641.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000642.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000643.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000644.parquet": { + "num_row_groups": 12, + "num_rows": 11113 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000645.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000646.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000647.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000648.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000649.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000650.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000651.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000652.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000653.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000654.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000655.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000656.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000657.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000658.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000659.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000660.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000661.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000662.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000663.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000664.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000665.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000666.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000667.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000668.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000669.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000670.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000671.parquet": { + "num_row_groups": 12, + "num_rows": 11143 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000672.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000673.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000674.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000675.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000676.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000677.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000678.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000679.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000680.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000681.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000682.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000683.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000684.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000685.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000686.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000687.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000688.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000689.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000690.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000691.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000692.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000693.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000694.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000695.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000696.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000697.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000698.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000699.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000700.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000701.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000702.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000703.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000704.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000705.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000706.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000707.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000708.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000709.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000710.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000711.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000712.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000713.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000714.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000715.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000716.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000717.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000718.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000719.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000720.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000721.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000722.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000723.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000724.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000725.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000726.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000727.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000728.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000729.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000730.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000731.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000732.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000733.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000734.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000735.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000736.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000737.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000738.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000739.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000740.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000741.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000742.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000743.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000744.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000745.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000746.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000747.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000748.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000749.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000750.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000751.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000752.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000753.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000754.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000755.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000756.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000757.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000758.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000759.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000760.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000761.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000762.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000763.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000764.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000765.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000766.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000767.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000768.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000769.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000770.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000771.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000772.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000773.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000774.parquet": { + "num_row_groups": 12, + "num_rows": 11153 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000775.parquet": { + "num_row_groups": 12, + "num_rows": 11112 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000776.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000777.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000778.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000779.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000780.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000781.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000782.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000783.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000784.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000785.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000786.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000787.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000788.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000789.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000790.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000791.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000792.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000793.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000794.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000795.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000796.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000797.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000798.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000799.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000800.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000801.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000802.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000803.parquet": { + "num_row_groups": 12, + "num_rows": 11141 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000804.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000805.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000806.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000807.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000808.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000809.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000810.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000811.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000812.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000813.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000814.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000815.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000816.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000817.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000818.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000819.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000820.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000821.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000822.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000823.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000824.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000825.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000826.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000827.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000828.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000829.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000830.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000831.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000832.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000833.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000834.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000835.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000836.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000837.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000838.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000839.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000840.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000841.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000842.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000843.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000844.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000845.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000846.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000847.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000848.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000849.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000850.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000851.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000852.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000853.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000854.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000855.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000856.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000857.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000858.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000859.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000860.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000861.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000862.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000863.parquet": { + "num_row_groups": 12, + "num_rows": 11146 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000864.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000865.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000866.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000867.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000868.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000869.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000870.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000871.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000872.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000873.parquet": { + "num_row_groups": 12, + "num_rows": 11142 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000874.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000875.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000876.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000877.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000878.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000879.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000880.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000881.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000882.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000883.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000884.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000885.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000886.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000887.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000888.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000889.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000890.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000891.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000892.parquet": { + "num_row_groups": 12, + "num_rows": 11115 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000893.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000894.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000895.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000896.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000897.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000898.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000899.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000900.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000901.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000902.parquet": { + "num_row_groups": 12, + "num_rows": 11118 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000903.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000904.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000905.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000906.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000907.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000908.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000909.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000910.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000911.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000912.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000913.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000914.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000915.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000916.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000917.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000918.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000919.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000920.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000921.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000922.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000923.parquet": { + "num_row_groups": 12, + "num_rows": 11129 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000924.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000925.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000926.parquet": { + "num_row_groups": 12, + "num_rows": 11116 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000927.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000928.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000929.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000930.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000931.parquet": { + "num_row_groups": 12, + "num_rows": 11132 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000932.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000933.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000934.parquet": { + "num_row_groups": 12, + "num_rows": 11117 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000935.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000936.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000937.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000938.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000939.parquet": { + "num_row_groups": 12, + "num_rows": 11128 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000940.parquet": { + "num_row_groups": 12, + "num_rows": 11145 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000941.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000942.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000943.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000944.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000945.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000946.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000947.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000948.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000949.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000950.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000951.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000952.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000953.parquet": { + "num_row_groups": 12, + "num_rows": 11119 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000954.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000955.parquet": { + "num_row_groups": 12, + "num_rows": 11147 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000956.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000957.parquet": { + "num_row_groups": 12, + "num_rows": 11114 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000958.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000959.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000960.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000961.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000962.parquet": { + "num_row_groups": 12, + "num_rows": 11131 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000963.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000964.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000965.parquet": { + "num_row_groups": 12, + "num_rows": 11140 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000966.parquet": { + "num_row_groups": 12, + "num_rows": 11125 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000967.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000968.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000969.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000970.parquet": { + "num_row_groups": 12, + "num_rows": 11138 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000971.parquet": { + "num_row_groups": 12, + "num_rows": 11139 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000972.parquet": { + "num_row_groups": 12, + "num_rows": 11144 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000973.parquet": { + "num_row_groups": 12, + "num_rows": 11121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000974.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000975.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000976.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000977.parquet": { + "num_row_groups": 12, + "num_rows": 11137 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000978.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000979.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000980.parquet": { + "num_row_groups": 12, + "num_rows": 11120 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000981.parquet": { + "num_row_groups": 12, + "num_rows": 11122 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000982.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000983.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000984.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000985.parquet": { + "num_row_groups": 12, + "num_rows": 11133 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000986.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000987.parquet": { + "num_row_groups": 12, + "num_rows": 11130 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000988.parquet": { + "num_row_groups": 12, + "num_rows": 11135 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000989.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000990.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000991.parquet": { + "num_row_groups": 12, + "num_rows": 11127 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000992.parquet": { + "num_row_groups": 12, + "num_rows": 11136 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000993.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000994.parquet": { + "num_row_groups": 12, + "num_rows": 11123 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000995.parquet": { + "num_row_groups": 12, + "num_rows": 11126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000996.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000997.parquet": { + "num_row_groups": 12, + "num_rows": 11134 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/sa_000998.parquet": { + "num_row_groups": 12, + "num_rows": 11124 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_1.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_10.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_100.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_101.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_102.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_103.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_104.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_105.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_106.parquet": { + "num_row_groups": 10, + "num_rows": 9949 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_107.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_108.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_109.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_11.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_110.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_111.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_112.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_113.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_114.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_115.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_116.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_117.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_118.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_119.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_12.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_120.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_121.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_122.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_123.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_124.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_125.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_126.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_127.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_128.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_129.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_13.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_130.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_131.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_132.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_133.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_134.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_135.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_136.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_137.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_138.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_139.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_14.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_140.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_141.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_142.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_143.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_144.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_145.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_146.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_147.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_148.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_149.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_15.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_150.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_151.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_152.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_153.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_154.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_155.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_156.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_157.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_158.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_159.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_16.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_160.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_161.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_162.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_163.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_164.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_165.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_166.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_167.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_168.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_169.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_17.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_170.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_171.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_172.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_173.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_174.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_175.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_176.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_177.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_178.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_179.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_18.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_180.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_181.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_182.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_183.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_184.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_185.parquet": { + "num_row_groups": 10, + "num_rows": 9956 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_186.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_187.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_188.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_189.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_19.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_190.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_191.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_192.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_193.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_194.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_195.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_196.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_197.parquet": { + "num_row_groups": 10, + "num_rows": 9957 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_198.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_199.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_2.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_20.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_200.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_201.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_202.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_203.parquet": { + "num_row_groups": 10, + "num_rows": 9952 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_204.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_205.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_206.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_207.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_208.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_209.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_21.parquet": { + "num_row_groups": 10, + "num_rows": 9955 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_210.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_211.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_212.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_213.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_214.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_215.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_216.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_217.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_218.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_219.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_22.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_220.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_221.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_222.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_223.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_224.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_225.parquet": { + "num_row_groups": 10, + "num_rows": 9954 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_226.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_227.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_228.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_229.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_23.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_230.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_231.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_232.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_233.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_234.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_235.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_236.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_237.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_238.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_239.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_24.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_240.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_241.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_242.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_243.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_244.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_245.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_246.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_247.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_248.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_249.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_25.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_250.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_251.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_252.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_253.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_254.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_255.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_256.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_257.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_258.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_259.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_26.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_260.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_261.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_262.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_263.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_264.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_265.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_266.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_267.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_268.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_269.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_27.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_270.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_271.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_272.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_273.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_274.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_275.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_276.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_277.parquet": { + "num_row_groups": 10, + "num_rows": 9946 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_278.parquet": { + "num_row_groups": 10, + "num_rows": 9954 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_279.parquet": { + "num_row_groups": 10, + "num_rows": 9953 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_28.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_280.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_281.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_282.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_283.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_284.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_285.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_286.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_287.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_288.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_289.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_29.parquet": { + "num_row_groups": 10, + "num_rows": 9953 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_290.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_291.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_292.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_293.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_294.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_295.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_296.parquet": { + "num_row_groups": 10, + "num_rows": 9953 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_297.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_298.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_299.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_3.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_30.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_300.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_301.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_302.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_303.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_304.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_305.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_306.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_307.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_308.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_309.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_31.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_310.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_311.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_312.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_313.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_314.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_315.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_316.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_317.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_318.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_319.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_32.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_320.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_321.parquet": { + "num_row_groups": 10, + "num_rows": 9953 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_322.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_323.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_324.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_325.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_326.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_327.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_328.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_329.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_33.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_330.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_331.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_332.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_333.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_334.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_335.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_336.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_337.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_338.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_339.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_34.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_340.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_341.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_342.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_343.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_344.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_345.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_346.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_347.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_348.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_349.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_35.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_350.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_351.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_352.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_353.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_354.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_355.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_356.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_357.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_358.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_359.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_36.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_360.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_361.parquet": { + "num_row_groups": 10, + "num_rows": 9956 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_362.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_363.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_364.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_365.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_366.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_367.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_368.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_369.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_37.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_370.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_371.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_372.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_373.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_374.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_375.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_376.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_377.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_378.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_379.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_38.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_380.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_381.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_382.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_383.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_384.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_385.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_386.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_387.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_388.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_389.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_39.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_390.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_391.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_392.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_393.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_394.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_395.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_396.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_397.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_398.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_399.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_4.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_40.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_400.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_401.parquet": { + "num_row_groups": 10, + "num_rows": 9960 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_402.parquet": { + "num_row_groups": 10, + "num_rows": 9956 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_403.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_404.parquet": { + "num_row_groups": 10, + "num_rows": 9958 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_405.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_406.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_407.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_408.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_409.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_41.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_410.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_411.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_412.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_413.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_414.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_415.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_416.parquet": { + "num_row_groups": 10, + "num_rows": 9962 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_417.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_418.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_419.parquet": { + "num_row_groups": 10, + "num_rows": 9716 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_42.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_43.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_44.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_45.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_46.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_47.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_48.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_49.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_5.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_50.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_51.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_52.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_53.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_54.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_55.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_56.parquet": { + "num_row_groups": 10, + "num_rows": 9952 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_57.parquet": { + "num_row_groups": 10, + "num_rows": 9959 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_58.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_59.parquet": { + "num_row_groups": 10, + "num_rows": 9961 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_6.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_60.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_61.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_62.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_63.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_64.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_65.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_66.parquet": { + "num_row_groups": 10, + "num_rows": 9936 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_67.parquet": { + "num_row_groups": 10, + "num_rows": 9929 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_68.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_69.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_7.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_70.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_71.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_72.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_73.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_74.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_75.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_76.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_77.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_78.parquet": { + "num_row_groups": 10, + "num_rows": 9967 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_79.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_8.parquet": { + "num_row_groups": 10, + "num_rows": 9963 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_80.parquet": { + "num_row_groups": 10, + "num_rows": 9968 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_81.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_82.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_83.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_84.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_85.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_86.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_87.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_88.parquet": { + "num_row_groups": 10, + "num_rows": 9949 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_89.parquet": { + "num_row_groups": 10, + "num_rows": 9972 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_9.parquet": { + "num_row_groups": 10, + "num_rows": 9964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_90.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_91.parquet": { + "num_row_groups": 10, + "num_rows": 9966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_92.parquet": { + "num_row_groups": 10, + "num_rows": 9969 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_93.parquet": { + "num_row_groups": 10, + "num_rows": 9965 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_94.parquet": { + "num_row_groups": 10, + "num_rows": 9970 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_95.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_96.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_97.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_JDB_98.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_000.parquet": { + "num_row_groups": 10, + "num_rows": 9780 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_001.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_002.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_003.parquet": { + "num_row_groups": 10, + "num_rows": 9773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_004.parquet": { + "num_row_groups": 5, + "num_rows": 4947 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_006.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_007.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_008.parquet": { + "num_row_groups": 10, + "num_rows": 9789 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_009.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_010.parquet": { + "num_row_groups": 7, + "num_rows": 6635 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_012.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_013.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_014.parquet": { + "num_row_groups": 10, + "num_rows": 9713 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_015.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_016.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_017.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_018.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_019.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_020.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_021.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_022.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_023.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_024.parquet": { + "num_row_groups": 6, + "num_rows": 5378 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_027.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_028.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_029.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_030.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_031.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_032.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_033.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_034.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_035.parquet": { + "num_row_groups": 5, + "num_rows": 4731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_036.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_037.parquet": { + "num_row_groups": 7, + "num_rows": 6180 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_039.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_040.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_041.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_042.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_043.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_044.parquet": { + "num_row_groups": 5, + "num_rows": 4971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_045.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_046.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_047.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_048.parquet": { + "num_row_groups": 9, + "num_rows": 8996 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_051.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_052.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_053.parquet": { + "num_row_groups": 5, + "num_rows": 4792 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_054.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_055.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_056.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_057.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_058.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_059.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_060.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_061.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_062.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_063.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_064.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_065.parquet": { + "num_row_groups": 4, + "num_rows": 3913 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_066.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_067.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_068.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_069.parquet": { + "num_row_groups": 10, + "num_rows": 9781 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_070.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_071.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_072.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_073.parquet": { + "num_row_groups": 6, + "num_rows": 5429 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_075.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_076.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_077.parquet": { + "num_row_groups": 10, + "num_rows": 9213 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_078.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_079.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_080.parquet": { + "num_row_groups": 1, + "num_rows": 554 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_081.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_082.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_083.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_084.parquet": { + "num_row_groups": 5, + "num_rows": 4672 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_087.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_088.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_089.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_090.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_091.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_092.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_093.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_094.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_095.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_096.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_097.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_098.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_099.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_100.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1000.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1001.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1002.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1003.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1004.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1005.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1006.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1007.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1008.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1009.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_101.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1010.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1011.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1012.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1013.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1014.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1015.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1016.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1017.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1018.parquet": { + "num_row_groups": 7, + "num_rows": 6906 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_102.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1020.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1021.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1022.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1023.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1024.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1025.parquet": { + "num_row_groups": 1, + "num_rows": 429 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1026.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1027.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1028.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1029.parquet": { + "num_row_groups": 10, + "num_rows": 9717 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_103.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1030.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1031.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1032.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1033.parquet": { + "num_row_groups": 10, + "num_rows": 9722 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1034.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1035.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1036.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1037.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1038.parquet": { + "num_row_groups": 8, + "num_rows": 7517 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_104.parquet": { + "num_row_groups": 1, + "num_rows": 705 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1041.parquet": { + "num_row_groups": 4, + "num_rows": 3042 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1044.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1045.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1046.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1047.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1048.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1049.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_105.parquet": { + "num_row_groups": 9, + "num_rows": 8703 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1050.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1051.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1052.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1053.parquet": { + "num_row_groups": 2, + "num_rows": 1531 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1056.parquet": { + "num_row_groups": 4, + "num_rows": 3281 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1059.parquet": { + "num_row_groups": 10, + "num_rows": 9715 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1060.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1061.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1062.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1063.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1064.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1065.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1066.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1067.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1068.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1069.parquet": { + "num_row_groups": 6, + "num_rows": 5668 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1071.parquet": { + "num_row_groups": 5, + "num_rows": 4624 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1074.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1075.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1076.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1077.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1078.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1079.parquet": { + "num_row_groups": 10, + "num_rows": 9722 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_108.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1080.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1081.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1082.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1083.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1084.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1085.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1086.parquet": { + "num_row_groups": 4, + "num_rows": 3101 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1089.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_109.parquet": { + "num_row_groups": 5, + "num_rows": 4974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1090.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1091.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1092.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1093.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1094.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1095.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1096.parquet": { + "num_row_groups": 9, + "num_rows": 8375 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1098.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1099.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1100.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1101.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1102.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1103.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1104.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1105.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1106.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1107.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1108.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1109.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_111.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1110.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1111.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1112.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1113.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1114.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1115.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1116.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1117.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1118.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1119.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_112.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1120.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1121.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1122.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1123.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1124.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1125.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1126.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1127.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1128.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1129.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_113.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1130.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1131.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1132.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1133.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1134.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1135.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1136.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1137.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1138.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1139.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_114.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1140.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1141.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1142.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1143.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1144.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1145.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1146.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1147.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1148.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1149.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_115.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1150.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1151.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1152.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1153.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1154.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1155.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1156.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1157.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1158.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1159.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_116.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1160.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1161.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1162.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1163.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1164.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1165.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1166.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1167.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1168.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1169.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_117.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1170.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1171.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1172.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1173.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1174.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1175.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1176.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1177.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1178.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1179.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_118.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1180.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1181.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1182.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1183.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1184.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1185.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1186.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1187.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1188.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1189.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_119.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1190.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1191.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1192.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1193.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1194.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1195.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1196.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1197.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1198.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1199.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_120.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1200.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1201.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1202.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1203.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1204.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1205.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1206.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1207.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1208.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1209.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_121.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1210.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1211.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1212.parquet": { + "num_row_groups": 10, + "num_rows": 9971 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1213.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1214.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1215.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1216.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1217.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1218.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1219.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_122.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1220.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1221.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1222.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1223.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1224.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1225.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1226.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1227.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1228.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1229.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_123.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1230.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1231.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1232.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1233.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1234.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1235.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1236.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1237.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1238.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1239.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_124.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1240.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1241.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1242.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1243.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1244.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1245.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1246.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1247.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1248.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1249.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_125.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1250.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1251.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1252.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1253.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1254.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1255.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1256.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1257.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1258.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1259.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_126.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1260.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1261.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1262.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1263.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1264.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1265.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1266.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1267.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1268.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1269.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_127.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1270.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1271.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1272.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1273.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1274.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1275.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1276.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1277.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1278.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1279.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_128.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1280.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1281.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1282.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1283.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1284.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1285.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1286.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1287.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1288.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1289.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_129.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1290.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1291.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1292.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1293.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1294.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1295.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1296.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1297.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1298.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1299.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_130.parquet": { + "num_row_groups": 3, + "num_rows": 2020 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1300.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1301.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1302.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1303.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1304.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1305.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1306.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1307.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1308.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1309.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1310.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1311.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1312.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1313.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1314.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1315.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1316.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1317.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1318.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1319.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_132.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1320.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1321.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1322.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1323.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1324.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1325.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1326.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1327.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1328.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1329.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_133.parquet": { + "num_row_groups": 10, + "num_rows": 9720 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1330.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1331.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1332.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1333.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1334.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1335.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1336.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1337.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1338.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1339.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_134.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1340.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1341.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1342.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1343.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1344.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1345.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1346.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1347.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1348.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1349.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_135.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1350.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1351.parquet": { + "num_row_groups": 10, + "num_rows": 9973 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1352.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1353.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1354.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1355.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1356.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1357.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1358.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1359.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_136.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1360.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1361.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1362.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1363.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1364.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1365.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1366.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1367.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1368.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1369.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_137.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1370.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1371.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1372.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1373.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1374.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1375.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1376.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1377.parquet": { + "num_row_groups": 10, + "num_rows": 9976 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1378.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1379.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_138.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1380.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1381.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1382.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1383.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1384.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1385.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1386.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1387.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1388.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1389.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_139.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1390.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1391.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1392.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1393.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1394.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1395.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1396.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1397.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1398.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1399.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_140.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1400.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1401.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1402.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1403.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1404.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1405.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1406.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1407.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1408.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1409.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_141.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1410.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1411.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1412.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1413.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1414.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1415.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1416.parquet": { + "num_row_groups": 10, + "num_rows": 9974 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1417.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1418.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1419.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_142.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1420.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1421.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1422.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1423.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1424.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1425.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1426.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1427.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1428.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1429.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_143.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1430.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1431.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1432.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1433.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1434.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1435.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1436.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1437.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1438.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1439.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_144.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1440.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1441.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1442.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1443.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1444.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1445.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1446.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1447.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1448.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1449.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_145.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1450.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1451.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1452.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1453.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1454.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1455.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1456.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1457.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1458.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1459.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_146.parquet": { + "num_row_groups": 1, + "num_rows": 780 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1460.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1461.parquet": { + "num_row_groups": 10, + "num_rows": 9993 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1462.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1463.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1464.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1465.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1466.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1467.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1468.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1469.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_147.parquet": { + "num_row_groups": 5, + "num_rows": 4475 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1470.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1471.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1472.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1473.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1474.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1475.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1476.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1477.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1478.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1479.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1480.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1481.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1482.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1483.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1484.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1485.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1486.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1487.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1488.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1489.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1490.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1491.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1492.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1493.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1494.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1495.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1496.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1497.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1498.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1499.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_150.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1500.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1501.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1502.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1503.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1504.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1505.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1506.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1507.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1508.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1509.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_151.parquet": { + "num_row_groups": 10, + "num_rows": 9782 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1510.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1511.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1512.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1513.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1514.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1515.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1516.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1517.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1518.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1519.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_152.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1520.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1521.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1522.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1523.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1524.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1525.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1526.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1527.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1528.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1529.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_153.parquet": { + "num_row_groups": 7, + "num_rows": 6457 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1530.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1531.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1532.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1533.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1534.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1535.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1536.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1537.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1538.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1539.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1540.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1541.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1542.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1543.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1544.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1545.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1546.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1547.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1548.parquet": { + "num_row_groups": 10, + "num_rows": 9980 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1549.parquet": { + "num_row_groups": 10, + "num_rows": 9982 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1550.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1551.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1552.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1553.parquet": { + "num_row_groups": 10, + "num_rows": 9977 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1554.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1555.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1556.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1557.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1558.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1559.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_156.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1560.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1561.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1562.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1563.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1564.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1565.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1566.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1567.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1568.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1569.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_157.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1570.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1571.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1572.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1573.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1574.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1575.parquet": { + "num_row_groups": 10, + "num_rows": 9987 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1576.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1577.parquet": { + "num_row_groups": 10, + "num_rows": 9975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1578.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1579.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_158.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1580.parquet": { + "num_row_groups": 10, + "num_rows": 9988 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1581.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1582.parquet": { + "num_row_groups": 10, + "num_rows": 9992 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1583.parquet": { + "num_row_groups": 10, + "num_rows": 9985 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1584.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1585.parquet": { + "num_row_groups": 10, + "num_rows": 9984 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1586.parquet": { + "num_row_groups": 10, + "num_rows": 9991 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1587.parquet": { + "num_row_groups": 10, + "num_rows": 9978 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1588.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1589.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_159.parquet": { + "num_row_groups": 10, + "num_rows": 9795 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1590.parquet": { + "num_row_groups": 10, + "num_rows": 9989 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1591.parquet": { + "num_row_groups": 10, + "num_rows": 9983 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1592.parquet": { + "num_row_groups": 10, + "num_rows": 9990 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1593.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1594.parquet": { + "num_row_groups": 10, + "num_rows": 9981 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1595.parquet": { + "num_row_groups": 10, + "num_rows": 9979 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1596.parquet": { + "num_row_groups": 10, + "num_rows": 9986 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_1597.parquet": { + "num_row_groups": 9, + "num_rows": 8956 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_160.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_161.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_162.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_163.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_164.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_165.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_166.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_167.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_168.parquet": { + "num_row_groups": 10, + "num_rows": 9696 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_169.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_170.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_171.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_172.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_173.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_174.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_175.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_176.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_177.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_178.parquet": { + "num_row_groups": 8, + "num_rows": 7121 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_180.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_181.parquet": { + "num_row_groups": 9, + "num_rows": 8926 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_183.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_184.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_185.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_186.parquet": { + "num_row_groups": 10, + "num_rows": 9720 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_187.parquet": { + "num_row_groups": 4, + "num_rows": 3230 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_189.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_190.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_191.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_192.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_193.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_194.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_195.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_196.parquet": { + "num_row_groups": 9, + "num_rows": 8369 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_198.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_199.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_200.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_201.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_202.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_203.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_204.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_205.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_206.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_207.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_208.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_209.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_210.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_211.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_212.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_213.parquet": { + "num_row_groups": 5, + "num_rows": 4216 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_216.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_217.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_218.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_219.parquet": { + "num_row_groups": 10, + "num_rows": 9790 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_220.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_221.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_222.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_223.parquet": { + "num_row_groups": 5, + "num_rows": 4315 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_225.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_226.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_227.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_228.parquet": { + "num_row_groups": 7, + "num_rows": 6321 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_231.parquet": { + "num_row_groups": 7, + "num_rows": 6690 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_234.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_235.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_236.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_237.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_238.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_239.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_240.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_241.parquet": { + "num_row_groups": 10, + "num_rows": 9701 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_242.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_243.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_244.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_245.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_246.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_247.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_248.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_249.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_250.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_251.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_252.parquet": { + "num_row_groups": 10, + "num_rows": 9715 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_253.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_254.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_255.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_256.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_257.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_258.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_259.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_260.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_261.parquet": { + "num_row_groups": 10, + "num_rows": 9424 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_264.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_265.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_266.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_267.parquet": { + "num_row_groups": 10, + "num_rows": 9719 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_268.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_269.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_270.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_271.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_272.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_273.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_274.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_275.parquet": { + "num_row_groups": 8, + "num_rows": 7713 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_276.parquet": { + "num_row_groups": 2, + "num_rows": 1695 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_279.parquet": { + "num_row_groups": 10, + "num_rows": 9790 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_280.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_281.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_282.parquet": { + "num_row_groups": 7, + "num_rows": 6657 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_285.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_286.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_287.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_288.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_289.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_290.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_291.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_292.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_293.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_294.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_295.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_296.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_297.parquet": { + "num_row_groups": 10, + "num_rows": 9783 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_298.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_299.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_300.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_301.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_302.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_303.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_304.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_305.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_306.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_307.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_308.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_309.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_310.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_311.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_312.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_313.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_314.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_315.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_316.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_317.parquet": { + "num_row_groups": 10, + "num_rows": 9020 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_318.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_319.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_320.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_321.parquet": { + "num_row_groups": 8, + "num_rows": 7635 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_324.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_325.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_326.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_327.parquet": { + "num_row_groups": 7, + "num_rows": 6026 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_330.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_331.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_332.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_333.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_334.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_335.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_336.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_337.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_338.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_339.parquet": { + "num_row_groups": 6, + "num_rows": 5086 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_342.parquet": { + "num_row_groups": 10, + "num_rows": 9722 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_343.parquet": { + "num_row_groups": 10, + "num_rows": 9719 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_344.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_345.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_346.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_347.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_348.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_349.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_350.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_351.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_352.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_353.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_354.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_355.parquet": { + "num_row_groups": 10, + "num_rows": 9795 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_356.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_357.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_358.parquet": { + "num_row_groups": 3, + "num_rows": 2126 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_360.parquet": { + "num_row_groups": 5, + "num_rows": 4564 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_363.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_364.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_365.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_366.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_367.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_368.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_369.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_370.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_371.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_372.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_373.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_374.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_375.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_376.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_377.parquet": { + "num_row_groups": 6, + "num_rows": 5062 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_378.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_379.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_380.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_381.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_382.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_383.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_384.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_385.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_386.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_387.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_388.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_389.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_390.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_391.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_392.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_393.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_394.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_395.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_396.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_397.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_398.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_399.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_400.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_401.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_402.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_403.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_404.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_405.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_406.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_407.parquet": { + "num_row_groups": 9, + "num_rows": 8643 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_408.parquet": { + "num_row_groups": 10, + "num_rows": 9773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_409.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_410.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_411.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_412.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_413.parquet": { + "num_row_groups": 10, + "num_rows": 9786 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_414.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_415.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_416.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_417.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_418.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_419.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_420.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_421.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_422.parquet": { + "num_row_groups": 1, + "num_rows": 95 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_423.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_424.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_425.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_426.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_427.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_428.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_429.parquet": { + "num_row_groups": 10, + "num_rows": 9719 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_430.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_431.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_432.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_433.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_434.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_435.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_436.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_437.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_438.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_439.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_440.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_441.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_442.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_443.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_444.parquet": { + "num_row_groups": 1, + "num_rows": 223 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_447.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_448.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_449.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_450.parquet": { + "num_row_groups": 5, + "num_rows": 4030 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_453.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_454.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_455.parquet": { + "num_row_groups": 2, + "num_rows": 1446 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_456.parquet": { + "num_row_groups": 10, + "num_rows": 9786 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_457.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_458.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_459.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_460.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_461.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_462.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_463.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_464.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_465.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_466.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_467.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_468.parquet": { + "num_row_groups": 1, + "num_rows": 694 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_471.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_472.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_473.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_474.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_475.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_476.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_477.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_478.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_479.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_480.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_481.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_482.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_483.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_484.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_485.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_486.parquet": { + "num_row_groups": 10, + "num_rows": 9795 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_487.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_488.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_489.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_490.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_491.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_492.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_493.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_494.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_495.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_496.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_497.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_498.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_499.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_500.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_501.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_502.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_503.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_504.parquet": { + "num_row_groups": 4, + "num_rows": 3866 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_507.parquet": { + "num_row_groups": 1, + "num_rows": 413 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_510.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_511.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_512.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_513.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_514.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_515.parquet": { + "num_row_groups": 10, + "num_rows": 9777 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_516.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_517.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_518.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_519.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_520.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_521.parquet": { + "num_row_groups": 5, + "num_rows": 4880 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_522.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_523.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_524.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_525.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_526.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_527.parquet": { + "num_row_groups": 10, + "num_rows": 9405 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_528.parquet": { + "num_row_groups": 9, + "num_rows": 8258 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_531.parquet": { + "num_row_groups": 5, + "num_rows": 4917 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_534.parquet": { + "num_row_groups": 8, + "num_rows": 7602 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_537.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_538.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_539.parquet": { + "num_row_groups": 4, + "num_rows": 3401 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_540.parquet": { + "num_row_groups": 8, + "num_rows": 7562 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_543.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_544.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_545.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_546.parquet": { + "num_row_groups": 10, + "num_rows": 9703 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_547.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_548.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_549.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_550.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_551.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_552.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_553.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_554.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_555.parquet": { + "num_row_groups": 10, + "num_rows": 9720 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_556.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_557.parquet": { + "num_row_groups": 10, + "num_rows": 9722 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_558.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_559.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_560.parquet": { + "num_row_groups": 10, + "num_rows": 9711 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_561.parquet": { + "num_row_groups": 5, + "num_rows": 4773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_564.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_565.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_566.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_567.parquet": { + "num_row_groups": 1, + "num_rows": 632 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_570.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_571.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_572.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_573.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_574.parquet": { + "num_row_groups": 7, + "num_rows": 6741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_576.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_577.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_578.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_579.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_580.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_581.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_582.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_583.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_584.parquet": { + "num_row_groups": 5, + "num_rows": 4751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_585.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_586.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_587.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_588.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_589.parquet": { + "num_row_groups": 8, + "num_rows": 7589 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_591.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_592.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_593.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_594.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_595.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_596.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_597.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_598.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_599.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_600.parquet": { + "num_row_groups": 1, + "num_rows": 230 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_603.parquet": { + "num_row_groups": 5, + "num_rows": 4186 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_606.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_607.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_608.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_609.parquet": { + "num_row_groups": 10, + "num_rows": 9710 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_610.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_611.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_612.parquet": { + "num_row_groups": 10, + "num_rows": 9714 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_613.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_614.parquet": { + "num_row_groups": 10, + "num_rows": 9773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_615.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_616.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_617.parquet": { + "num_row_groups": 2, + "num_rows": 1643 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_618.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_619.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_621.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_622.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_623.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_624.parquet": { + "num_row_groups": 3, + "num_rows": 2207 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_627.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_628.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_629.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_630.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_631.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_632.parquet": { + "num_row_groups": 10, + "num_rows": 9781 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_633.parquet": { + "num_row_groups": 8, + "num_rows": 7619 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_636.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_637.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_638.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_639.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_640.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_641.parquet": { + "num_row_groups": 10, + "num_rows": 9782 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_642.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_643.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_644.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_645.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_646.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_647.parquet": { + "num_row_groups": 2, + "num_rows": 1444 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_648.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_649.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_650.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_651.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_652.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_653.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_654.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_655.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_656.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_657.parquet": { + "num_row_groups": 2, + "num_rows": 1802 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_660.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_661.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_662.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_663.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_664.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_665.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_666.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_667.parquet": { + "num_row_groups": 3, + "num_rows": 2531 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_669.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_670.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_671.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_672.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_673.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_674.parquet": { + "num_row_groups": 4, + "num_rows": 3311 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_675.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_676.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_677.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_678.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_679.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_680.parquet": { + "num_row_groups": 3, + "num_rows": 2382 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_681.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_682.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_683.parquet": { + "num_row_groups": 5, + "num_rows": 4049 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_684.parquet": { + "num_row_groups": 9, + "num_rows": 8589 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_687.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_688.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_689.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_690.parquet": { + "num_row_groups": 10, + "num_rows": 9778 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_691.parquet": { + "num_row_groups": 10, + "num_rows": 9777 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_692.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_693.parquet": { + "num_row_groups": 6, + "num_rows": 5555 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_696.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_697.parquet": { + "num_row_groups": 8, + "num_rows": 7922 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_699.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_700.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_701.parquet": { + "num_row_groups": 10, + "num_rows": 9786 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_702.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_703.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_704.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_705.parquet": { + "num_row_groups": 10, + "num_rows": 9768 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_706.parquet": { + "num_row_groups": 5, + "num_rows": 4556 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_708.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_709.parquet": { + "num_row_groups": 10, + "num_rows": 9783 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_710.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_711.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_712.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_713.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_714.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_715.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_716.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_717.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_718.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_719.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_720.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_721.parquet": { + "num_row_groups": 10, + "num_rows": 9020 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_723.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_724.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_725.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_726.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_727.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_728.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_729.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_730.parquet": { + "num_row_groups": 9, + "num_rows": 8557 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_732.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_733.parquet": { + "num_row_groups": 4, + "num_rows": 3474 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_735.parquet": { + "num_row_groups": 10, + "num_rows": 9723 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_736.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_737.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_738.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_739.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_740.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_741.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_742.parquet": { + "num_row_groups": 10, + "num_rows": 9777 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_743.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_744.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_745.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_746.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_747.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_748.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_749.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_750.parquet": { + "num_row_groups": 10, + "num_rows": 9711 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_751.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_752.parquet": { + "num_row_groups": 10, + "num_rows": 9762 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_753.parquet": { + "num_row_groups": 10, + "num_rows": 9716 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_754.parquet": { + "num_row_groups": 7, + "num_rows": 6231 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_756.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_757.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_758.parquet": { + "num_row_groups": 10, + "num_rows": 9773 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_759.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_760.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_761.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_762.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_763.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_764.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_765.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_766.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_767.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_768.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_769.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_770.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_771.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_772.parquet": { + "num_row_groups": 3, + "num_rows": 2203 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_774.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_775.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_776.parquet": { + "num_row_groups": 10, + "num_rows": 9782 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_777.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_778.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_779.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_780.parquet": { + "num_row_groups": 5, + "num_rows": 4194 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_783.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_784.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_785.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_786.parquet": { + "num_row_groups": 10, + "num_rows": 9106 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_789.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_790.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_791.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_792.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_793.parquet": { + "num_row_groups": 3, + "num_rows": 2448 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_795.parquet": { + "num_row_groups": 10, + "num_rows": 9793 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_796.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_797.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_798.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_799.parquet": { + "num_row_groups": 6, + "num_rows": 5964 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_801.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_802.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_803.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_804.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_805.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_806.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_807.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_808.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_809.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_810.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_811.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_812.parquet": { + "num_row_groups": 2, + "num_rows": 1296 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_813.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_814.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_815.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_816.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_817.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_818.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_819.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_820.parquet": { + "num_row_groups": 10, + "num_rows": 9784 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_821.parquet": { + "num_row_groups": 5, + "num_rows": 4440 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_822.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_823.parquet": { + "num_row_groups": 7, + "num_rows": 6412 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_825.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_826.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_827.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_828.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_829.parquet": { + "num_row_groups": 3, + "num_rows": 2801 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_831.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_832.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_833.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_834.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_835.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_836.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_837.parquet": { + "num_row_groups": 10, + "num_rows": 9777 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_838.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_839.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_840.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_841.parquet": { + "num_row_groups": 10, + "num_rows": 9766 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_842.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_843.parquet": { + "num_row_groups": 10, + "num_rows": 9735 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_844.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_845.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_846.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_847.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_848.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_849.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_850.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_851.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_852.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_853.parquet": { + "num_row_groups": 10, + "num_rows": 9775 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_854.parquet": { + "num_row_groups": 10, + "num_rows": 9734 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_855.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_856.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_857.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_858.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_859.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_860.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_861.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_862.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_863.parquet": { + "num_row_groups": 10, + "num_rows": 9787 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_864.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_865.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_866.parquet": { + "num_row_groups": 10, + "num_rows": 9720 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_867.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_868.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_869.parquet": { + "num_row_groups": 4, + "num_rows": 3420 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_870.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_871.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_872.parquet": { + "num_row_groups": 10, + "num_rows": 9718 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_873.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_874.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_875.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_876.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_877.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_878.parquet": { + "num_row_groups": 5, + "num_rows": 4966 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_879.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_880.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_881.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_882.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_883.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_884.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_885.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_886.parquet": { + "num_row_groups": 10, + "num_rows": 9739 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_887.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_888.parquet": { + "num_row_groups": 5, + "num_rows": 4910 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_891.parquet": { + "num_row_groups": 10, + "num_rows": 9737 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_892.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_893.parquet": { + "num_row_groups": 3, + "num_rows": 2022 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_894.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_895.parquet": { + "num_row_groups": 10, + "num_rows": 9761 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_896.parquet": { + "num_row_groups": 10, + "num_rows": 9727 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_897.parquet": { + "num_row_groups": 9, + "num_rows": 8747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_900.parquet": { + "num_row_groups": 10, + "num_rows": 9729 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_901.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_902.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_903.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_904.parquet": { + "num_row_groups": 10, + "num_rows": 9772 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_905.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_906.parquet": { + "num_row_groups": 10, + "num_rows": 9756 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_907.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_908.parquet": { + "num_row_groups": 10, + "num_rows": 9741 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_909.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_910.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_911.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_912.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_913.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_914.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_915.parquet": { + "num_row_groups": 7, + "num_rows": 6922 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_918.parquet": { + "num_row_groups": 10, + "num_rows": 9738 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_919.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_920.parquet": { + "num_row_groups": 10, + "num_rows": 9730 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_921.parquet": { + "num_row_groups": 8, + "num_rows": 7941 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_924.parquet": { + "num_row_groups": 10, + "num_rows": 9725 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_925.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_926.parquet": { + "num_row_groups": 4, + "num_rows": 3447 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_927.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_928.parquet": { + "num_row_groups": 1, + "num_rows": 51 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_930.parquet": { + "num_row_groups": 5, + "num_rows": 4302 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_933.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_934.parquet": { + "num_row_groups": 10, + "num_rows": 9694 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_935.parquet": { + "num_row_groups": 10, + "num_rows": 9771 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_936.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_937.parquet": { + "num_row_groups": 10, + "num_rows": 9726 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_938.parquet": { + "num_row_groups": 10, + "num_rows": 9742 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_939.parquet": { + "num_row_groups": 10, + "num_rows": 9763 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_940.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_941.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_942.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_943.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_944.parquet": { + "num_row_groups": 10, + "num_rows": 9740 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_945.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_946.parquet": { + "num_row_groups": 10, + "num_rows": 9782 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_947.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_948.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_949.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_950.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_951.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_952.parquet": { + "num_row_groups": 10, + "num_rows": 9744 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_953.parquet": { + "num_row_groups": 10, + "num_rows": 9724 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_954.parquet": { + "num_row_groups": 10, + "num_rows": 9781 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_955.parquet": { + "num_row_groups": 10, + "num_rows": 9743 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_956.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_957.parquet": { + "num_row_groups": 10, + "num_rows": 9757 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_958.parquet": { + "num_row_groups": 10, + "num_rows": 9753 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_959.parquet": { + "num_row_groups": 10, + "num_rows": 9728 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_960.parquet": { + "num_row_groups": 10, + "num_rows": 9754 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_961.parquet": { + "num_row_groups": 10, + "num_rows": 9752 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_962.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_963.parquet": { + "num_row_groups": 10, + "num_rows": 9769 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_964.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_965.parquet": { + "num_row_groups": 10, + "num_rows": 9731 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_966.parquet": { + "num_row_groups": 10, + "num_rows": 9776 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_967.parquet": { + "num_row_groups": 10, + "num_rows": 9755 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_968.parquet": { + "num_row_groups": 10, + "num_rows": 9759 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_969.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_970.parquet": { + "num_row_groups": 10, + "num_rows": 9779 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_971.parquet": { + "num_row_groups": 2, + "num_rows": 1699 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_972.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_973.parquet": { + "num_row_groups": 10, + "num_rows": 9749 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_974.parquet": { + "num_row_groups": 4, + "num_rows": 3975 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_975.parquet": { + "num_row_groups": 10, + "num_rows": 9750 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_976.parquet": { + "num_row_groups": 10, + "num_rows": 9796 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_977.parquet": { + "num_row_groups": 10, + "num_rows": 9736 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_978.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_979.parquet": { + "num_row_groups": 10, + "num_rows": 9792 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_980.parquet": { + "num_row_groups": 10, + "num_rows": 9765 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_981.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_982.parquet": { + "num_row_groups": 10, + "num_rows": 9745 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_983.parquet": { + "num_row_groups": 10, + "num_rows": 9747 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_984.parquet": { + "num_row_groups": 10, + "num_rows": 9767 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_985.parquet": { + "num_row_groups": 10, + "num_rows": 9732 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_986.parquet": { + "num_row_groups": 10, + "num_rows": 9751 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_987.parquet": { + "num_row_groups": 10, + "num_rows": 9721 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_988.parquet": { + "num_row_groups": 4, + "num_rows": 3865 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_990.parquet": { + "num_row_groups": 10, + "num_rows": 9746 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_991.parquet": { + "num_row_groups": 10, + "num_rows": 9733 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_992.parquet": { + "num_row_groups": 10, + "num_rows": 9760 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_993.parquet": { + "num_row_groups": 10, + "num_rows": 9774 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_994.parquet": { + "num_row_groups": 10, + "num_rows": 9770 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_995.parquet": { + "num_row_groups": 10, + "num_rows": 9764 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_996.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_998.parquet": { + "num_row_groups": 10, + "num_rows": 9758 + }, + "./datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet/webdataset_shard_999.parquet": { + "num_row_groups": 10, + "num_rows": 9748 + } +} \ No newline at end of file diff --git a/data/bundled_parquet_info/llava_onevision_vqa.json b/data/bundled_parquet_info/llava_onevision_vqa.json new file mode 100644 index 0000000000000000000000000000000000000000..6a98d5f74521e03269b6cc6f031fd4a9894c91ed --- /dev/null +++ b/data/bundled_parquet_info/llava_onevision_vqa.json @@ -0,0 +1,2450 @@ +{ + "./datasets/llava_onevision_vqa_parquet/train/ai2d_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 13, + "num_rows": 2429 + }, + "./datasets/llava_onevision_vqa_parquet/train/ai2d_gpt4v__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 4864 + }, + "./datasets/llava_onevision_vqa_parquet/train/ai2d_internvl__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ai2d_internvl__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ai2d_internvl__part0002.parquet": { + "num_row_groups": 13, + "num_rows": 2403 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_laion4v__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 4990 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_vflan4v__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_vflan4v__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_vflan4v__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/allava_instruct_vflan4v__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 4990 + }, + "./datasets/llava_onevision_vqa_parquet/train/aokvqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/aokvqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/aokvqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/aokvqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 8, + "num_rows": 1534 + }, + "./datasets/llava_onevision_vqa_parquet/train/chart2text_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chart2text_cauldron__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chart2text_cauldron__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chart2text_cauldron__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chart2text_cauldron__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chart2text_cauldron__part0005.parquet": { + "num_row_groups": 10, + "num_rows": 1956 + }, + "./datasets/llava_onevision_vqa_parquet/train/chartqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chartqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chartqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chartqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 17, + "num_rows": 3260 + }, + "./datasets/llava_onevision_vqa_parquet/train/chrome_writting__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/chrome_writting__part0001.parquet": { + "num_row_groups": 20, + "num_rows": 3825 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/clevr_cauldron_llava_format__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 4995 + }, + "./datasets/llava_onevision_vqa_parquet/train/CLEVR-Math_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/CLEVR-Math_MathV360K__part0001.parquet": { + "num_row_groups": 2, + "num_rows": 280 + }, + "./datasets/llava_onevision_vqa_parquet/train/diagram_image_to_text_cauldron__part0000.parquet": { + "num_row_groups": 2, + "num_rows": 295 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0018.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0019.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0020.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0021.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0022.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0023.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0024.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0025.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0026.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0027.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0028.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0029.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0030.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0031.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0032.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0033.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0034.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0035.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0036.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0037.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0038.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/dvqa_cauldron_llava_format__part0039.parquet": { + "num_row_groups": 25, + "num_rows": 4995 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0018.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/figureqa_cauldron_llava_format__part0019.parquet": { + "num_row_groups": 25, + "num_rows": 4995 + }, + "./datasets/llava_onevision_vqa_parquet/train/FigureQA_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/FigureQA_MathV360K__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/FigureQA_MathV360K__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/FigureQA_MathV360K__part0003.parquet": { + "num_row_groups": 13, + "num_rows": 2587 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_align__part0012.parquet": { + "num_row_groups": 2, + "num_rows": 242 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo170k_qa__part0013.parquet": { + "num_row_groups": 15, + "num_rows": 2823 + }, + "./datasets/llava_onevision_vqa_parquet/train/geo3k__part0000.parquet": { + "num_row_groups": 11, + "num_rows": 2091 + }, + "./datasets/llava_onevision_vqa_parquet/train/Geometry3K_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/Geometry3K_MathV360K__part0001.parquet": { + "num_row_groups": 24, + "num_rows": 4724 + }, + "./datasets/llava_onevision_vqa_parquet/train/geomverse_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/geomverse_cauldron__part0001.parquet": { + "num_row_groups": 22, + "num_rows": 4298 + }, + "./datasets/llava_onevision_vqa_parquet/train/GeoQA_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/GeoQA_MathV360K__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/GeoQA_MathV360K__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/GeoQA_MathV360K__part0003.parquet": { + "num_row_groups": 11, + "num_rows": 2162 + }, + "./datasets/llava_onevision_vqa_parquet/train/GEOS_MathV360K__part0000.parquet": { + "num_row_groups": 3, + "num_rows": 498 + }, + "./datasets/llava_onevision_vqa_parquet/train/hateful_memes_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hateful_memes_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 18, + "num_rows": 3495 + }, + "./datasets/llava_onevision_vqa_parquet/train/hitab_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 13, + "num_rows": 2495 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/hme100k__part0014.parquet": { + "num_row_groups": 23, + "num_rows": 4492 + }, + "./datasets/llava_onevision_vqa_parquet/train/iam_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/iam_cauldron__part0001.parquet": { + "num_row_groups": 4, + "num_rows": 658 + }, + "./datasets/llava_onevision_vqa_parquet/train/iconqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/iconqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/iconqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/iconqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/iconqa_cauldron_llava_format__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/iconqa_cauldron_llava_format__part0005.parquet": { + "num_row_groups": 12, + "num_rows": 2302 + }, + "./datasets/llava_onevision_vqa_parquet/train/IconQA_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/IconQA_MathV360K__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/IconQA_MathV360K__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/IconQA_MathV360K__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/IconQA_MathV360K__part0004.parquet": { + "num_row_groups": 13, + "num_rows": 2589 + }, + "./datasets/llava_onevision_vqa_parquet/train/iiit5k__part0000.parquet": { + "num_row_groups": 10, + "num_rows": 1990 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0018.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/image_textualization_filtered__part0019.parquet": { + "num_row_groups": 23, + "num_rows": 4573 + }, + "./datasets/llava_onevision_vqa_parquet/train/infographic_gpt4v__part0000.parquet": { + "num_row_groups": 10, + "num_rows": 1982 + }, + "./datasets/llava_onevision_vqa_parquet/train/infographic_vqa__part0000.parquet": { + "num_row_groups": 22, + "num_rows": 4394 + }, + "./datasets/llava_onevision_vqa_parquet/train/infographic_vqa_llava_format__part0000.parquet": { + "num_row_groups": 11, + "num_rows": 2113 + }, + "./datasets/llava_onevision_vqa_parquet/train/intergps_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 7, + "num_rows": 1275 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0018.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0019.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0020.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0021.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0022.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0023.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0024.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0025.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0026.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0027.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0028.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0029.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0030.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0031.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0032.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0033.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0034.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0035.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0036.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0037.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0038.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0039.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0040.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0041.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0042.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0043.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0044.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0045.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0046.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0047.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0048.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0049.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0050.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/k12_printing__part0051.parquet": { + "num_row_groups": 9, + "num_rows": 1636 + }, + "./datasets/llava_onevision_vqa_parquet/train/llavar_gpt4_20k__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llavar_gpt4_20k__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llavar_gpt4_20k__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llavar_gpt4_20k__part0003.parquet": { + "num_row_groups": 24, + "num_rows": 4790 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_12k_filtered__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_12k_filtered__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_12k_filtered__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_12k_filtered__part0003.parquet": { + "num_row_groups": 1, + "num_rows": 124 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_39k_filtered__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_39k_filtered__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_39k_filtered__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_39k_filtered__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_39k_filtered__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_39k_filtered__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_39k_filtered__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/llava_wild_4v_39k_filtered__part0007.parquet": { + "num_row_groups": 22, + "num_rows": 4362 + }, + "./datasets/llava_onevision_vqa_parquet/train/lrv_chart__part0000.parquet": { + "num_row_groups": 9, + "num_rows": 1776 + }, + "./datasets/llava_onevision_vqa_parquet/train/lrv_normal_filtered__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/lrv_normal_filtered__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/lrv_normal_filtered__part0002.parquet": { + "num_row_groups": 3, + "num_rows": 490 + }, + "./datasets/llava_onevision_vqa_parquet/train/mapqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mapqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mapqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mapqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mapqa_cauldron_llava_format__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mapqa_cauldron_llava_format__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mapqa_cauldron_llava_format__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mapqa_cauldron_llava_format__part0007.parquet": { + "num_row_groups": 13, + "num_rows": 2412 + }, + "./datasets/llava_onevision_vqa_parquet/train/MapQA_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/MapQA_MathV360K__part0001.parquet": { + "num_row_groups": 2, + "num_rows": 225 + }, + "./datasets/llava_onevision_vqa_parquet/train/MathV360K_TQA__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/MathV360K_TQA__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/MathV360K_TQA__part0002.parquet": { + "num_row_groups": 1, + "num_rows": 176 + }, + "./datasets/llava_onevision_vqa_parquet/train/MathV360K_VQA-AS__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/MathV360K_VQA-AS__part0001.parquet": { + "num_row_groups": 5, + "num_rows": 902 + }, + "./datasets/llava_onevision_vqa_parquet/train/MathV360K_VQA-RAD__part0000.parquet": { + "num_row_groups": 11, + "num_rows": 2125 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_metagen__part0017.parquet": { + "num_row_groups": 12, + "num_rows": 2348 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0018.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/mavis_math_rule_geo__part0019.parquet": { + "num_row_groups": 25, + "num_rows": 4990 + }, + "./datasets/llava_onevision_vqa_parquet/train/multihiertt_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/multihiertt_cauldron__part0001.parquet": { + "num_row_groups": 14, + "num_rows": 2614 + }, + "./datasets/llava_onevision_vqa_parquet/train/orand_car_a__part0000.parquet": { + "num_row_groups": 10, + "num_rows": 1999 + }, + "./datasets/llava_onevision_vqa_parquet/train/PMC-VQA_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/PMC-VQA_MathV360K__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/PMC-VQA_MathV360K__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/PMC-VQA_MathV360K__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/PMC-VQA_MathV360K__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/PMC-VQA_MathV360K__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/PMC-VQA_MathV360K__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/PMC-VQA_MathV360K__part0007.parquet": { + "num_row_groups": 5, + "num_rows": 948 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/raven_cauldron__part0008.parquet": { + "num_row_groups": 10, + "num_rows": 1995 + }, + "./datasets/llava_onevision_vqa_parquet/train/rendered_text_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/rendered_text_cauldron__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 4995 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_sqa_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_sqa_cauldron__part0001.parquet": { + "num_row_groups": 18, + "num_rows": 3509 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wikisql_cauldron__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 4984 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wtq_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wtq_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wtq_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wtq_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wtq_cauldron_llava_format__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wtq_cauldron_llava_format__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wtq_cauldron_llava_format__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/robut_wtq_cauldron_llava_format__part0007.parquet": { + "num_row_groups": 17, + "num_rows": 3241 + }, + "./datasets/llava_onevision_vqa_parquet/train/scienceqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 4971 + }, + "./datasets/llava_onevision_vqa_parquet/train/scienceqa_nona_context__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/scienceqa_nona_context__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/scienceqa_nona_context__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/scienceqa_nona_context__part0003.parquet": { + "num_row_groups": 22, + "num_rows": 4208 + }, + "./datasets/llava_onevision_vqa_parquet/train/screen2words_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/screen2words_cauldron__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/screen2words_cauldron__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/screen2words_cauldron__part0003.parquet": { + "num_row_groups": 4, + "num_rows": 725 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4o__part0011.parquet": { + "num_row_groups": 12, + "num_rows": 2284 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_coco__part0010.parquet": { + "num_row_groups": 1, + "num_rows": 17 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_knowledge__part0000.parquet": { + "num_row_groups": 10, + "num_rows": 1988 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_llava__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_llava__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_llava__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_llava__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_llava__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_llava__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 4990 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_sam__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sharegpt4v_sam__part0001.parquet": { + "num_row_groups": 20, + "num_rows": 3990 + }, + "./datasets/llava_onevision_vqa_parquet/train/sroie__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sroie__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sroie__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sroie__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sroie__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sroie__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/sroie__part0006.parquet": { + "num_row_groups": 19, + "num_rows": 3616 + }, + "./datasets/llava_onevision_vqa_parquet/train/st_vqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/st_vqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/st_vqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/st_vqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 12, + "num_rows": 2242 + }, + "./datasets/llava_onevision_vqa_parquet/train/Super-CLEVR_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/Super-CLEVR_MathV360K__part0001.parquet": { + "num_row_groups": 19, + "num_rows": 3642 + }, + "./datasets/llava_onevision_vqa_parquet/train/tabmwp_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tabmwp_cauldron__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tabmwp_cauldron__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tabmwp_cauldron__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tabmwp_cauldron__part0004.parquet": { + "num_row_groups": 14, + "num_rows": 2717 + }, + "./datasets/llava_onevision_vqa_parquet/train/TabMWP_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/TabMWP_MathV360K__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/TabMWP_MathV360K__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/TabMWP_MathV360K__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/TabMWP_MathV360K__part0004.parquet": { + "num_row_groups": 13, + "num_rows": 2452 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0018.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tallyqa_cauldron_llava_format__part0019.parquet": { + "num_row_groups": 19, + "num_rows": 3675 + }, + "./datasets/llava_onevision_vqa_parquet/train/textcaps__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textcaps__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textcaps__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textcaps__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textcaps__part0004.parquet": { + "num_row_groups": 10, + "num_rows": 1942 + }, + "./datasets/llava_onevision_vqa_parquet/train/textocr_gpt4v__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textocr_gpt4v__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textocr_gpt4v__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textocr_gpt4v__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textocr_gpt4v__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/textocr_gpt4v__part0005.parquet": { + "num_row_groups": 1, + "num_rows": 104 + }, + "./datasets/llava_onevision_vqa_parquet/train/tqa_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tqa_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tqa_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tqa_cauldron_llava_format__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tqa_cauldron_llava_format__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/tqa_cauldron_llava_format__part0005.parquet": { + "num_row_groups": 12, + "num_rows": 2302 + }, + "./datasets/llava_onevision_vqa_parquet/train/UniGeo_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/UniGeo_MathV360K__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/UniGeo_MathV360K__part0002.parquet": { + "num_row_groups": 10, + "num_rows": 1949 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_cap__part0018.parquet": { + "num_row_groups": 8, + "num_rows": 1434 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_ie__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_ie__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_ie__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/ureader_ie__part0003.parquet": { + "num_row_groups": 12, + "num_rows": 2322 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0018.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0019.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0020.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0021.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0022.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0023.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0024.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0025.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0026.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0027.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0028.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0029.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0030.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0031.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0032.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0033.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0034.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0035.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0036.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vision_flan_filtered__part0037.parquet": { + "num_row_groups": 6, + "num_rows": 1060 + }, + "./datasets/llava_onevision_vqa_parquet/train/vistext_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/vistext_cauldron__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 4964 + }, + "./datasets/llava_onevision_vqa_parquet/train/visual7w_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/visual7w_cauldron_llava_format__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/visual7w_cauldron_llava_format__part0002.parquet": { + "num_row_groups": 22, + "num_rows": 4361 + }, + "./datasets/llava_onevision_vqa_parquet/train/visualmrc_cauldron__part0000.parquet": { + "num_row_groups": 16, + "num_rows": 3022 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0002.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0003.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0004.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0005.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0006.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0007.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0008.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0009.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0010.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0011.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0012.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0013.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0014.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0015.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0016.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0017.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0018.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0019.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0020.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0021.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0022.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0023.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0024.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0025.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0026.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0027.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0028.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0029.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0030.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0031.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0032.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0033.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0034.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0035.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0036.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0037.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0038.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0039.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0040.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0041.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0042.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0043.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0044.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0045.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0046.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0047.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0048.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0049.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0050.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0051.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VisualWebInstruct_filtered__part0052.parquet": { + "num_row_groups": 18, + "num_rows": 3584 + }, + "./datasets/llava_onevision_vqa_parquet/train/VizWiz_MathV360K__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/VizWiz_MathV360K__part0001.parquet": { + "num_row_groups": 9, + "num_rows": 1604 + }, + "./datasets/llava_onevision_vqa_parquet/train/vqarad_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 2, + "num_rows": 308 + }, + "./datasets/llava_onevision_vqa_parquet/train/vsr_cauldron_llava_format__part0000.parquet": { + "num_row_groups": 11, + "num_rows": 2152 + }, + "./datasets/llava_onevision_vqa_parquet/train/websight_cauldron__part0000.parquet": { + "num_row_groups": 25, + "num_rows": 5000 + }, + "./datasets/llava_onevision_vqa_parquet/train/websight_cauldron__part0001.parquet": { + "num_row_groups": 25, + "num_rows": 4995 + } +} \ No newline at end of file diff --git a/data/configs/ablation_any2any_only.yaml b/data/configs/ablation_any2any_only.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8982538d6fc7e2303642909cf26947dee3de7dbf --- /dev/null +++ b/data/configs/ablation_any2any_only.yaml @@ -0,0 +1,130 @@ +# Dataset ablation: any-to-any only (MMMU lower bound). +# Keeps all unified_any2X groups from BLIP3O; vlm_sft removed. + +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2seg: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2canny: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2dino: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1000 + weight: 1 diff --git a/data/configs/ablation_vqa_only.yaml b/data/configs/ablation_vqa_only.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0f3ab6a4423c6ee58009f1f18d0413b7c4305e0e --- /dev/null +++ b/data/configs/ablation_vqa_only.yaml @@ -0,0 +1,193 @@ +# Dataset ablation: VQA-only (MMMU upper bound). +# Keeps only vlm_sft; all unified_any2X groups removed. +# Total samples: ~3,938,627 + +# Total samples across all vlm_sft subsets: 3,938,627. +vlm_sft: + dataset_names: + - ai2d(cauldron,llava_format) + - ai2d(gpt4v) + - ai2d(internvl) + - allava_instruct_laion4v + - allava_instruct_vflan4v + - aokvqa(cauldron,llava_format) + - chart2text(cauldron) + - chartqa(cauldron,llava_format) + - chrome_writting + - clevr(cauldron,llava_format) + - CLEVR-Math(MathV360K) + - diagram_image_to_text(cauldron) + - dvqa(cauldron,llava_format) + - figureqa(cauldron,llava_format) + - FigureQA(MathV360K) + - geo170k(align) + - geo170k(qa) + - geo3k + - Geometry3K(MathV360K) + - geomverse(cauldron) + - GeoQA+(MathV360K) + - GEOS(MathV360K) + - hateful_memes(cauldron,llava_format) + - hitab(cauldron,llava_format) + - hme100k + - iam(cauldron) + - iconqa(cauldron,llava_format) + - IconQA(MathV360K) + - iiit5k + - image_textualization(filtered) + - infographic(gpt4v) + - infographic_vqa + - infographic_vqa_llava_format + - intergps(cauldron,llava_format) + - k12_printing + - llavar_gpt4_20k + - llava_wild_4v_12k_filtered + - llava_wild_4v_39k_filtered + - lrv_chart + - lrv_normal(filtered) + - mapqa(cauldron,llava_format) + - MapQA(MathV360K) + - MathV360K_TQA + - MathV360K_VQA-AS + - MathV360K_VQA-RAD + - mavis_math_metagen + - mavis_math_rule_geo + - multihiertt(cauldron) + - orand_car_a + - PMC-VQA(MathV360K) + - raven(cauldron) + - rendered_text(cauldron) + - robut_sqa(cauldron) + - robut_wikisql(cauldron) + - robut_wtq(cauldron,llava_format) + - scienceqa(cauldron,llava_format) + - scienceqa(nona_context) + - screen2words(cauldron) + - sharegpt4o + - sharegpt4v(coco) + - sharegpt4v(knowledge) + - sharegpt4v(llava) + - sharegpt4v(sam) + - sroie + - st_vqa(cauldron,llava_format) + - Super-CLEVR(MathV360K) + - tabmwp(cauldron) + - TabMWP(MathV360K) + - tallyqa(cauldron,llava_format) + - textcaps + - textocr(gpt4v) + - tqa(cauldron,llava_format) + - UniGeo(MathV360K) + - ureader_cap + - ureader_ie + - vision_flan(filtered) + - vistext(cauldron) + - visual7w(cauldron,llava_format) + - visualmrc(cauldron) + - VisualWebInstruct(filtered) + - VizWiz(MathV360K) + - vqarad(cauldron,llava_format) + - vsr(cauldron,llava_format) + - websight(cauldron) + image_transform_args: + image_stride: 14 + max_image_size: 980 + min_image_size: 378 + max_pixels: 2_007_040 + frame_sampler_args: + max_num_frames: 12 + min_num_frames: 8 + is_mandatory: true + shuffle_lines: True + shuffle_seed: 0 + num_used_data: + - 2429 + - 4864 + - 12403 + - 49990 + - 19990 + - 16534 + - 26956 + - 18260 + - 8825 + - 69995 + - 5280 + - 295 + - 199995 + - 142985 + - 99995 + - 17587 + - 60242 + - 67823 + - 2091 + - 9724 + - 9298 + - 17162 + - 498 + - 8495 + - 2495 + - 74492 + - 5658 + - 27302 + - 22589 + - 1990 + - 99573 + - 1982 + - 4394 + - 2113 + - 1275 + - 256636 + - 19790 + - 15124 + - 39362 + - 1776 + - 10490 + - 299988 + - 299990 + - 299982 + - 37412 + - 5225 + - 29827 + - 10176 + - 5902 + - 2125 + - 87348 + - 99990 + - 7614 + - 1999 + - 35948 + - 41995 + - 9995 + - 8509 + - 74984 + - 38241 + - 4971 + - 19208 + - 15725 + - 57284 + - 50017 + - 1988 + - 29990 + - 8990 + - 33616 + - 17242 + - 8642 + - 22717 + - 22452 + - 98675 + - 21942 + - 25104 + - 27302 + - 11949 + - 91434 + - 17322 + - 186060 + - 9964 + - 14361 + - 3022 + - 263584 + - 6604 + - 308 + - 2152 + - 9995 + weight: 1 diff --git a/data/configs/any2any.yaml b/data/configs/any2any.yaml new file mode 100644 index 0000000000000000000000000000000000000000..b389ca052fe930a50e84404be3696155a8d871c1 --- /dev/null +++ b/data/configs/any2any.yaml @@ -0,0 +1,64 @@ +unified_any2rgb: + dataset_names: + - blip3o + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 \ No newline at end of file diff --git a/data/configs/any2any_8modalities_stage1.yaml b/data/configs/any2any_8modalities_stage1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..befc4addf968bfb1d770badd95aa9b39aa15bcbf --- /dev/null +++ b/data/configs/any2any_8modalities_stage1.yaml @@ -0,0 +1,49 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1000 + weight: 10 diff --git a/data/configs/any2any_9modalities_stage1.yaml b/data/configs/any2any_9modalities_stage1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f581a11ef684c633c5b90b75d5438c5529333918 --- /dev/null +++ b/data/configs/any2any_9modalities_stage1.yaml @@ -0,0 +1,65 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1000 + weight: 5 + +unified_any2dino: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 5 \ No newline at end of file diff --git a/data/configs/any2any_9modalities_stage1_toy.yaml b/data/configs/any2any_9modalities_stage1_toy.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e648f36f7fbdc44eb156a8de5c036c7dd42df0fb --- /dev/null +++ b/data/configs/any2any_9modalities_stage1_toy.yaml @@ -0,0 +1,65 @@ +unified_any2rgb: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 1 + + +unified_any2grounding: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 5 + +unified_any2dino: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 5 \ No newline at end of file diff --git a/data/configs/any2any_9modalities_stage1_toy_debug.yaml b/data/configs/any2any_9modalities_stage1_toy_debug.yaml new file mode 100644 index 0000000000000000000000000000000000000000..59b0262066df30968cbdb5fadfa37481f2f68d15 --- /dev/null +++ b/data/configs/any2any_9modalities_stage1_toy_debug.yaml @@ -0,0 +1,31 @@ +# unified_any2rgb: +# dataset_names: +# - blip3o_example_toydataset +# image_transform_args: +# image_stride: 16 +# max_image_size: 1024 +# min_image_size: 512 +# vit_image_transform_args: +# image_stride: 14 +# max_image_size: 518 +# min_image_size: 224 +# is_mandatory: true +# num_used_data: +# - 1 +# weight: 1 + +unified_any2dino: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 5 \ No newline at end of file diff --git a/data/configs/any2any_mandatory_rgb_caption_depth_normal_det.yaml b/data/configs/any2any_mandatory_rgb_caption_depth_normal_det.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7a5210e95ebd5b43ee2470ebcc4aa2f15a275226 --- /dev/null +++ b/data/configs/any2any_mandatory_rgb_caption_depth_normal_det.yaml @@ -0,0 +1,82 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2det: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + diff --git a/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg.yaml b/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e6b27e2d004f1dd0f5cdd9ebe48c4d2b5b0f81d8 --- /dev/null +++ b/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg.yaml @@ -0,0 +1,98 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2det: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2seg: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + diff --git a/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg_grounding.yaml b/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg_grounding.yaml new file mode 100644 index 0000000000000000000000000000000000000000..bb6a5787ebd3918712a85d9715bf91383cef1d18 --- /dev/null +++ b/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg_grounding.yaml @@ -0,0 +1,97 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2seg: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1000 + weight: 1 \ No newline at end of file diff --git a/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg_grounding_canny_dino.yaml b/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg_grounding_canny_dino.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8520c8332d09b9534228920e562476a60528ee13 --- /dev/null +++ b/data/configs/any2any_mandatory_rgb_caption_depth_normal_det_seg_grounding_canny_dino.yaml @@ -0,0 +1,130 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2seg: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1000 + weight: 1 + + +unified_any2canny: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2dino: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 \ No newline at end of file diff --git a/data/configs/any2any_rgb_caption_depth_normal_det_seg.yaml b/data/configs/any2any_rgb_caption_depth_normal_det_seg.yaml new file mode 100644 index 0000000000000000000000000000000000000000..896719549fcd463350d157067271ba6c6dd55270 --- /dev/null +++ b/data/configs/any2any_rgb_caption_depth_normal_det_seg.yaml @@ -0,0 +1,98 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + + +unified_any2det: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + +unified_any2seg: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + diff --git a/data/configs/bagel_stage3_exact3cond.yaml b/data/configs/bagel_stage3_exact3cond.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1842355e52d083de493a2f86239ba1c675c067c3 --- /dev/null +++ b/data/configs/bagel_stage3_exact3cond.yaml @@ -0,0 +1,111 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1000 + weight: 5 + +unified_any2dino: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 5 + +unified_any2dinolocal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 5 + +unified_any2clip: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 5 + +unified_any2imagebind: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 5 + +unified_any2imagebindlocal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 5 diff --git a/data/configs/example.yaml b/data/configs/example.yaml new file mode 100644 index 0000000000000000000000000000000000000000..7834e7bd0c3704a8a0edd966d91f410a669ebdcc --- /dev/null +++ b/data/configs/example.yaml @@ -0,0 +1,45 @@ +# t2i_pretrain: +# dataset_names: +# - t2i +# image_transform_args: +# image_stride: 16 +# max_image_size: 1024 +# min_image_size: 512 +# is_mandatory: true +# num_used_data: # The sum should be larger that NUM_GPUS x NUM_WORKERS +# - 10 +# weight: 1 + +# unified_edit: +# dataset_names: +# - seedxedit_multi +# image_transform_args: +# image_stride: 16 +# max_image_size: 1024 +# min_image_size: 512 +# vit_image_transform_args: +# image_stride: 14 +# max_image_size: 518 +# min_image_size: 224 +# is_mandatory: false +# num_used_data: +# - 10 +# weight: 1 + +vlm_sft: + dataset_names: + - llava_ov + image_transform_args: + image_stride: 14 + max_image_size: 980 + min_image_size: 378 + max_pixels: 2_007_040 + frame_sampler_args: + max_num_frames: 12 + min_num_frames: 8 + is_mandatory: true + shuffle_lines: True + shuffle_seed: 0 + num_used_data: + - 1000 + weight: 1 diff --git a/data/configs/example_any2any.yaml b/data/configs/example_any2any.yaml new file mode 100644 index 0000000000000000000000000000000000000000..8a2041ed1d82c4156c94a2b3144d9abcd5c110f7 --- /dev/null +++ b/data/configs/example_any2any.yaml @@ -0,0 +1,64 @@ +unified_any2rgb: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 1 + + +unified_any2caption: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_example_toydataset + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1 + weight: 1 \ No newline at end of file diff --git a/data/configs/modus_stage1.yaml b/data/configs/modus_stage1.yaml new file mode 100644 index 0000000000000000000000000000000000000000..57b3c6150c7a68ebba30d0ac16a3fc5568797ec3 --- /dev/null +++ b/data/configs/modus_stage1.yaml @@ -0,0 +1,245 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +# Total samples across all vlm_sft subsets: 3,938,627. +vlm_sft: + dataset_names: + - ai2d(cauldron,llava_format) + - ai2d(gpt4v) + - ai2d(internvl) + - allava_instruct_laion4v + - allava_instruct_vflan4v + - aokvqa(cauldron,llava_format) + - chart2text(cauldron) + - chartqa(cauldron,llava_format) + - chrome_writting + - clevr(cauldron,llava_format) + - CLEVR-Math(MathV360K) + - diagram_image_to_text(cauldron) + - dvqa(cauldron,llava_format) + # - Evol-Instruct-GPT4-Turbo + - figureqa(cauldron,llava_format) + - FigureQA(MathV360K) + - geo170k(align) + - geo170k(qa) + - geo3k + - Geometry3K(MathV360K) + - geomverse(cauldron) + - GeoQA+(MathV360K) + - GEOS(MathV360K) + - hateful_memes(cauldron,llava_format) + - hitab(cauldron,llava_format) + - hme100k + - iam(cauldron) + - iconqa(cauldron,llava_format) + - IconQA(MathV360K) + - iiit5k + - image_textualization(filtered) + - infographic(gpt4v) + - infographic_vqa + - infographic_vqa_llava_format + - intergps(cauldron,llava_format) + - k12_printing + - llavar_gpt4_20k + - llava_wild_4v_12k_filtered + - llava_wild_4v_39k_filtered + - lrv_chart + - lrv_normal(filtered) + # - magpie_pro(l3_80b_mt) + # - magpie_pro(l3_80b_st) + # - magpie_pro(qwen2_72b_st) + - mapqa(cauldron,llava_format) + - MapQA(MathV360K) + # - mathqa + - MathV360K_TQA + - MathV360K_VQA-AS + - MathV360K_VQA-RAD + - mavis_math_metagen + - mavis_math_rule_geo + - multihiertt(cauldron) + - orand_car_a + - PMC-VQA(MathV360K) + - raven(cauldron) + - rendered_text(cauldron) + - robut_sqa(cauldron) + - robut_wikisql(cauldron) + - robut_wtq(cauldron,llava_format) + - scienceqa(cauldron,llava_format) + - scienceqa(nona_context) + - screen2words(cauldron) + - sharegpt4o + - sharegpt4v(coco) + - sharegpt4v(knowledge) + - sharegpt4v(llava) + - sharegpt4v(sam) + - sroie + - st_vqa(cauldron,llava_format) + - Super-CLEVR(MathV360K) + - tabmwp(cauldron) + - TabMWP(MathV360K) + - tallyqa(cauldron,llava_format) + - textcaps + - textocr(gpt4v) + - tqa(cauldron,llava_format) + - UniGeo(MathV360K) + - ureader_cap + - ureader_ie + - vision_flan(filtered) + - vistext(cauldron) + - visual7w(cauldron,llava_format) + - visualmrc(cauldron) + - VisualWebInstruct(filtered) + - VizWiz(MathV360K) + - vqarad(cauldron,llava_format) + - vsr(cauldron,llava_format) + - websight(cauldron) + image_transform_args: + image_stride: 14 + max_image_size: 980 + min_image_size: 378 + max_pixels: 2_007_040 + frame_sampler_args: + max_num_frames: 12 + min_num_frames: 8 + is_mandatory: true + shuffle_lines: True + shuffle_seed: 0 + num_used_data: + - 2429 + - 4864 + - 12403 + - 49990 + - 19990 + - 16534 + - 26956 + - 18260 + - 8825 + - 69995 + - 5280 + - 295 + - 199995 + - 99995 + - 17587 + - 60242 + - 67823 + - 2091 + - 9724 + - 9298 + - 17162 + - 498 + - 8495 + - 2495 + - 74492 + - 5658 + - 27302 + - 22589 + - 1990 + - 99573 + - 1982 + - 4394 + - 2113 + - 1275 + - 256636 + - 19790 + - 15124 + - 39362 + - 1776 + - 10490 + - 37412 + - 5225 + - 10176 + - 5902 + - 2125 + - 87348 + - 99990 + - 7614 + - 1999 + - 35948 + - 41995 + - 9995 + - 8509 + - 74984 + - 38241 + - 4971 + - 19208 + - 15725 + - 57284 + - 50017 + - 1988 + - 29990 + - 8990 + - 33616 + - 17242 + - 8642 + - 22717 + - 22452 + - 98675 + - 21942 + - 25104 + - 27302 + - 11949 + - 91434 + - 17322 + - 186060 + - 9964 + - 14361 + - 3022 + - 263584 + - 6604 + - 308 + - 2152 + - 9995 + # 5 text-only subsets (Evol-Instruct/magpie_pro x3/mathqa) are + # excluded from dataset_names; their stale quotas were removed + # here too (they previously shifted every later subset's quota). + weight: 1 + +# ==== VQA Consistency Check ==== +# Datasets: 89 | Records: 3938627 | Image refs: 3938627 | Missing images: 1072772 | Video refs: 0 | Missing videos: 0 + + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1000 + weight: 5 + +unified_any2dino: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 5 diff --git a/data/configs/modus_stage2.yaml b/data/configs/modus_stage2.yaml new file mode 100644 index 0000000000000000000000000000000000000000..67a4f62fce17f3b202275ad2beb5c678fc151b40 --- /dev/null +++ b/data/configs/modus_stage2.yaml @@ -0,0 +1,329 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +# Total samples across all vlm_sft subsets: 3,938,627. +vlm_sft: + dataset_names: + - ai2d(cauldron,llava_format) + - ai2d(gpt4v) + - ai2d(internvl) + - allava_instruct_laion4v + - allava_instruct_vflan4v + - aokvqa(cauldron,llava_format) + - chart2text(cauldron) + - chartqa(cauldron,llava_format) + - chrome_writting + - clevr(cauldron,llava_format) + - CLEVR-Math(MathV360K) + - diagram_image_to_text(cauldron) + - dvqa(cauldron,llava_format) + # - Evol-Instruct-GPT4-Turbo + - figureqa(cauldron,llava_format) + - FigureQA(MathV360K) + - geo170k(align) + - geo170k(qa) + - geo3k + - Geometry3K(MathV360K) + - geomverse(cauldron) + - GeoQA+(MathV360K) + - GEOS(MathV360K) + - hateful_memes(cauldron,llava_format) + - hitab(cauldron,llava_format) + - hme100k + - iam(cauldron) + - iconqa(cauldron,llava_format) + - IconQA(MathV360K) + - iiit5k + - image_textualization(filtered) + - infographic(gpt4v) + - infographic_vqa + - infographic_vqa_llava_format + - intergps(cauldron,llava_format) + - k12_printing + - llavar_gpt4_20k + - llava_wild_4v_12k_filtered + - llava_wild_4v_39k_filtered + - lrv_chart + - lrv_normal(filtered) + # - magpie_pro(l3_80b_mt) + # - magpie_pro(l3_80b_st) + # - magpie_pro(qwen2_72b_st) + - mapqa(cauldron,llava_format) + - MapQA(MathV360K) + # - mathqa + - MathV360K_TQA + - MathV360K_VQA-AS + - MathV360K_VQA-RAD + - mavis_math_metagen + - mavis_math_rule_geo + - multihiertt(cauldron) + - orand_car_a + - PMC-VQA(MathV360K) + - raven(cauldron) + - rendered_text(cauldron) + - robut_sqa(cauldron) + - robut_wikisql(cauldron) + - robut_wtq(cauldron,llava_format) + - scienceqa(cauldron,llava_format) + - scienceqa(nona_context) + - screen2words(cauldron) + - sharegpt4o + - sharegpt4v(coco) + - sharegpt4v(knowledge) + - sharegpt4v(llava) + - sharegpt4v(sam) + - sroie + - st_vqa(cauldron,llava_format) + - Super-CLEVR(MathV360K) + - tabmwp(cauldron) + - TabMWP(MathV360K) + - tallyqa(cauldron,llava_format) + - textcaps + - textocr(gpt4v) + - tqa(cauldron,llava_format) + - UniGeo(MathV360K) + - ureader_cap + - ureader_ie + - vision_flan(filtered) + - vistext(cauldron) + - visual7w(cauldron,llava_format) + - visualmrc(cauldron) + - VisualWebInstruct(filtered) + - VizWiz(MathV360K) + - vqarad(cauldron,llava_format) + - vsr(cauldron,llava_format) + - websight(cauldron) + image_transform_args: + image_stride: 14 + max_image_size: 980 + min_image_size: 378 + max_pixels: 2_007_040 + frame_sampler_args: + max_num_frames: 12 + min_num_frames: 8 + is_mandatory: true + shuffle_lines: True + shuffle_seed: 0 + num_used_data: + - 2429 + - 4864 + - 12403 + - 49990 + - 19990 + - 16534 + - 26956 + - 18260 + - 8825 + - 69995 + - 5280 + - 295 + - 199995 + - 99995 + - 17587 + - 60242 + - 67823 + - 2091 + - 9724 + - 9298 + - 17162 + - 498 + - 8495 + - 2495 + - 74492 + - 5658 + - 27302 + - 22589 + - 1990 + - 99573 + - 1982 + - 4394 + - 2113 + - 1275 + - 256636 + - 19790 + - 15124 + - 39362 + - 1776 + - 10490 + - 37412 + - 5225 + - 10176 + - 5902 + - 2125 + - 87348 + - 99990 + - 7614 + - 1999 + - 35948 + - 41995 + - 9995 + - 8509 + - 74984 + - 38241 + - 4971 + - 19208 + - 15725 + - 57284 + - 50017 + - 1988 + - 29990 + - 8990 + - 33616 + - 17242 + - 8642 + - 22717 + - 22452 + - 98675 + - 21942 + - 25104 + - 27302 + - 11949 + - 91434 + - 17322 + - 186060 + - 9964 + - 14361 + - 3022 + - 263584 + - 6604 + - 308 + - 2152 + - 9995 + # 5 text-only subsets (Evol-Instruct/magpie_pro x3/mathqa) are + # excluded from dataset_names; their stale quotas were removed + # here too (they previously shifted every later subset's quota). + weight: 1 + +# ==== VQA Consistency Check ==== +# Datasets: 89 | Records: 3938627 | Image refs: 3938627 | Missing images: 1072772 | Video refs: 0 | Missing videos: 0 + + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 1000 + weight: 1 + +unified_any2dino: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + +unified_any2seg: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +unified_any2canny: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 diff --git a/data/configs/modus_stage3.yaml b/data/configs/modus_stage3.yaml new file mode 100644 index 0000000000000000000000000000000000000000..f61222bed0c184410bcee5c71e3b950e6cff261d --- /dev/null +++ b/data/configs/modus_stage3.yaml @@ -0,0 +1,329 @@ +unified_any2rgb: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 + + +# Total samples across all vlm_sft subsets: 3,938,627. +vlm_sft: + dataset_names: + - ai2d(cauldron,llava_format) + - ai2d(gpt4v) + - ai2d(internvl) + - allava_instruct_laion4v + - allava_instruct_vflan4v + - aokvqa(cauldron,llava_format) + - chart2text(cauldron) + - chartqa(cauldron,llava_format) + - chrome_writting + - clevr(cauldron,llava_format) + - CLEVR-Math(MathV360K) + - diagram_image_to_text(cauldron) + - dvqa(cauldron,llava_format) + # - Evol-Instruct-GPT4-Turbo + - figureqa(cauldron,llava_format) + - FigureQA(MathV360K) + - geo170k(align) + - geo170k(qa) + - geo3k + - Geometry3K(MathV360K) + - geomverse(cauldron) + - GeoQA+(MathV360K) + - GEOS(MathV360K) + - hateful_memes(cauldron,llava_format) + - hitab(cauldron,llava_format) + - hme100k + - iam(cauldron) + - iconqa(cauldron,llava_format) + - IconQA(MathV360K) + - iiit5k + - image_textualization(filtered) + - infographic(gpt4v) + - infographic_vqa + - infographic_vqa_llava_format + - intergps(cauldron,llava_format) + - k12_printing + - llavar_gpt4_20k + - llava_wild_4v_12k_filtered + - llava_wild_4v_39k_filtered + - lrv_chart + - lrv_normal(filtered) + # - magpie_pro(l3_80b_mt) + # - magpie_pro(l3_80b_st) + # - magpie_pro(qwen2_72b_st) + - mapqa(cauldron,llava_format) + - MapQA(MathV360K) + # - mathqa + - MathV360K_TQA + - MathV360K_VQA-AS + - MathV360K_VQA-RAD + - mavis_math_metagen + - mavis_math_rule_geo + - multihiertt(cauldron) + - orand_car_a + - PMC-VQA(MathV360K) + - raven(cauldron) + - rendered_text(cauldron) + - robut_sqa(cauldron) + - robut_wikisql(cauldron) + - robut_wtq(cauldron,llava_format) + - scienceqa(cauldron,llava_format) + - scienceqa(nona_context) + - screen2words(cauldron) + - sharegpt4o + - sharegpt4v(coco) + - sharegpt4v(knowledge) + - sharegpt4v(llava) + - sharegpt4v(sam) + - sroie + - st_vqa(cauldron,llava_format) + - Super-CLEVR(MathV360K) + - tabmwp(cauldron) + - TabMWP(MathV360K) + - tallyqa(cauldron,llava_format) + - textcaps + - textocr(gpt4v) + - tqa(cauldron,llava_format) + - UniGeo(MathV360K) + - ureader_cap + - ureader_ie + - vision_flan(filtered) + - vistext(cauldron) + - visual7w(cauldron,llava_format) + - visualmrc(cauldron) + - VisualWebInstruct(filtered) + - VizWiz(MathV360K) + - vqarad(cauldron,llava_format) + - vsr(cauldron,llava_format) + - websight(cauldron) + image_transform_args: + image_stride: 14 + max_image_size: 980 + min_image_size: 378 + max_pixels: 2_007_040 + frame_sampler_args: + max_num_frames: 12 + min_num_frames: 8 + is_mandatory: true + shuffle_lines: True + shuffle_seed: 0 + num_used_data: + - 2429 + - 4864 + - 12403 + - 49990 + - 19990 + - 16534 + - 26956 + - 18260 + - 8825 + - 69995 + - 5280 + - 295 + - 199995 + - 99995 + - 17587 + - 60242 + - 67823 + - 2091 + - 9724 + - 9298 + - 17162 + - 498 + - 8495 + - 2495 + - 74492 + - 5658 + - 27302 + - 22589 + - 1990 + - 99573 + - 1982 + - 4394 + - 2113 + - 1275 + - 256636 + - 19790 + - 15124 + - 39362 + - 1776 + - 10490 + - 37412 + - 5225 + - 10176 + - 5902 + - 2125 + - 87348 + - 99990 + - 7614 + - 1999 + - 35948 + - 41995 + - 9995 + - 8509 + - 74984 + - 38241 + - 4971 + - 19208 + - 15725 + - 57284 + - 50017 + - 1988 + - 29990 + - 8990 + - 33616 + - 17242 + - 8642 + - 22717 + - 22452 + - 98675 + - 21942 + - 25104 + - 27302 + - 11949 + - 91434 + - 17322 + - 186060 + - 9964 + - 14361 + - 3022 + - 263584 + - 6604 + - 308 + - 2152 + - 9995 + # 5 text-only subsets (Evol-Instruct/magpie_pro x3/mathqa) are + # excluded from dataset_names; their stale quotas were removed + # here too (they previously shifted every later subset's quota). + weight: 1 + +# ==== VQA Consistency Check ==== +# Datasets: 89 | Records: 3938627 | Image refs: 3938627 | Missing images: 1072772 | Video refs: 0 | Missing videos: 0 + + +unified_any2grounding: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 1000 + weight: 1 + +unified_any2dino: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + + + + +unified_any2caption: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + +unified_any2seg: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 + + +unified_any2canny: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: false + num_used_data: + - 2891 + weight: 1 diff --git a/data/configs/single_task_depth.yaml b/data/configs/single_task_depth.yaml new file mode 100644 index 0000000000000000000000000000000000000000..80c0e80df2a0c619aae251e7407a7b23308f1dda --- /dev/null +++ b/data/configs/single_task_depth.yaml @@ -0,0 +1,15 @@ +unified_any2depth: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 diff --git a/data/configs/single_task_normal.yaml b/data/configs/single_task_normal.yaml new file mode 100644 index 0000000000000000000000000000000000000000..77b1a98b2b36b601c89ecc14c14700b3f0ca9223 --- /dev/null +++ b/data/configs/single_task_normal.yaml @@ -0,0 +1,15 @@ +unified_any2normal: + dataset_names: + - blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino + image_transform_args: + image_stride: 16 + max_image_size: 1024 + min_image_size: 512 + vit_image_transform_args: + image_stride: 14 + max_image_size: 518 + min_image_size: 224 + is_mandatory: true + num_used_data: + - 2891 + weight: 1 diff --git a/data/data_utils.py b/data/data_utils.py new file mode 100644 index 0000000000000000000000000000000000000000..9dc69d5345a78a621f2bfa9923bb8627b3799c62 --- /dev/null +++ b/data/data_utils.py @@ -0,0 +1,509 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + + +import math +import random +from typing import Any, Dict, List, Optional, Tuple +from PIL import Image + +import torch +from torch.nn.attention.flex_attention import or_masks, and_masks + + +def create_sparse_mask(document_lens, split_lens, attn_modes, device): + def causal_mask(b, h, q_idx, kv_idx): + return q_idx >= kv_idx + + def full_and_noise_mask(b, h, q_idx, kv_idx): + return (full_and_noise_seq_id[q_idx] == full_and_noise_seq_id[kv_idx]) & (full_and_noise_seq_id[q_idx] >= 0) + + def remove_noise_mask(b, h, q_idx, kv_idx): + return (~((noise_seq_id[kv_idx] >= 0) & (noise_seq_id[q_idx] != noise_seq_id[kv_idx]))) + + def sample_mask(b, h, q_idx, kv_idx): + return document_id[q_idx] == document_id[kv_idx] + + full_and_noise_tmp = [] + noise_tmp = [] + + for i, (length, model) in enumerate(zip(split_lens, attn_modes)): + value = i if model in ['full', 'noise'] else -1 + full_and_noise_tmp.extend([value] * length) + value_noise = i if model == 'noise' else -1 + noise_tmp.extend([value_noise] * length) + + full_and_noise_seq_id = torch.Tensor(full_and_noise_tmp).to(device) + noise_seq_id = torch.Tensor(noise_tmp).to(device) + + document_id = torch.cat([torch.full((l,), i) for i, l in enumerate(document_lens, start=1)]).to(device) + + return and_masks(or_masks(causal_mask, full_and_noise_mask), remove_noise_mask, sample_mask) + + +def patchify(image, patch_size): + p = patch_size + c, h, w = image.shape + assert h % p == 0 and w % p == 0 + image = image.reshape(c, h // p, p, w // p, p) + image = torch.einsum("chpwq->hwpqc", image) + image = image.reshape(-1, p**2 * c) + return image + + +def get_flattened_position_ids_extrapolate(img_h, img_w, patch_size, max_num_patches_per_side): + num_patches_h, num_patches_w = img_h // patch_size, img_w // patch_size + coords_h = torch.arange(0, num_patches_h) + coords_w = torch.arange(0, num_patches_w) + pos_ids = (coords_h[:, None] * max_num_patches_per_side + coords_w).flatten() + return pos_ids + + +def get_flattened_position_ids_interpolate(img_h, img_w, patch_size, max_num_patches_per_side): + num_patches_h, num_patches_w = img_h // patch_size, img_w // patch_size + boundaries = torch.arange(1 / max_num_patches_per_side, 1.0, 1 / max_num_patches_per_side) + fractional_coords_h = torch.arange(0, 1 - 1e-6, 1 / num_patches_h) + fractional_coords_w = torch.arange(0, 1 - 1e-6, 1 / num_patches_w) + bucket_coords_h = torch.bucketize(fractional_coords_h, boundaries, right=True) + bucket_coords_w = torch.bucketize(fractional_coords_w, boundaries, right=True) + pos_ids = (bucket_coords_h[:, None] * max_num_patches_per_side + bucket_coords_w).flatten() + return pos_ids + + +def prepare_attention_mask_per_sample(split_lens, attn_modes, device="cpu"): + """ + nested_split_lens: A list of N lists of ints. Each int indicates the length of a split within + a sample, where each sample contains multiple splits with different attn modes. + nested_attn_modes: whether to use full attn in each split. + """ + sample_len = sum(split_lens) + attention_mask = torch.zeros((sample_len, sample_len), dtype=torch.bool, device=device) + + csum = 0 + for s, attn_mode in zip(split_lens, attn_modes): + assert attn_mode in ['causal', 'full', 'noise'] + if attn_mode == "causal": + attention_mask[csum:csum + s, csum:csum + s] = torch.ones((s, s), device=device).tril() + attention_mask[csum:csum + s, :csum] = 1 + else: + attention_mask[csum:csum + s, csum:csum + s] = torch.ones((s, s)) + attention_mask[csum:csum + s, :csum] = 1 + csum += s + + csum = 0 + for s, attn_mode in zip(split_lens, attn_modes): + if attn_mode == "noise": + attention_mask[:, csum : csum + s] = torch.zeros((sample_len, s)) + attention_mask[csum : csum + s, csum : csum + s] = torch.ones((s, s)) + csum += s + + attention_mask = torch.zeros_like(attention_mask, dtype=torch.float).masked_fill_( + ~attention_mask, float("-inf") + ) + + return attention_mask + + +def split_integer_exp_decay(S, ng_sample_decay=1.0): + if ng_sample_decay == 1.0: + N = random.randint(1, S) + else: + base = (1 - ng_sample_decay) / (1 - math.pow(ng_sample_decay, S)) + p = [base * math.pow(ng_sample_decay, i) for i in range(S)] + N = random.choices(list(range(1, S + 1)), p, k=1)[0] + cumsum = [0] + sorted(random.sample(range(1, S), N - 1)) + [S] + result = [cumsum[i+1] - cumsum[i] for i in range(len(cumsum) - 1)] + return result, cumsum + + +def pil_img2rgb(image): + if image.mode == "RGBA" or image.info.get("transparency", None) is not None: + image = image.convert("RGBA") + white = Image.new(mode="RGB", size=image.size, color=(255, 255, 255)) + white.paste(image, mask=image.split()[3]) + image = white + else: + image = image.convert("RGB") + + return image + + +def add_special_tokens(tokenizer): + all_special_tokens = [] + for k, v in tokenizer.special_tokens_map.items(): + if isinstance(v, str): + all_special_tokens.append(v) + elif isinstance(v, list): + all_special_tokens += v + + new_tokens = [] + + if '<|im_start|>' not in all_special_tokens: + new_tokens.append('<|im_start|>') + + if '<|im_end|>' not in all_special_tokens: + new_tokens.append('<|im_end|>') + + if '<|vision_start|>' not in all_special_tokens: + new_tokens.append('<|vision_start|>') + + if '<|vision_end|>' not in all_special_tokens: + new_tokens.append('<|vision_end|>') + + if '<|caption_start|>' not in all_special_tokens: + new_tokens.append('<|caption_start|>') + if '<|caption_end|>' not in all_special_tokens: + new_tokens.append('<|caption_end|>') + + if '<|depth_start|>' not in all_special_tokens: + new_tokens.append('<|depth_start|>') + if '<|depth_end|>' not in all_special_tokens: + new_tokens.append('<|depth_end|>') + + if '<|normal_start|>' not in all_special_tokens: + new_tokens.append('<|normal_start|>') + if '<|normal_end|>' not in all_special_tokens: + new_tokens.append('<|normal_end|>') + + num_new_tokens = tokenizer.add_tokens(new_tokens) + bos_token_id = tokenizer.convert_tokens_to_ids('<|im_start|>') + eos_token_id = tokenizer.convert_tokens_to_ids('<|im_end|>') + start_of_image = tokenizer.convert_tokens_to_ids('<|vision_start|>') + end_of_image = tokenizer.convert_tokens_to_ids('<|vision_end|>') + + start_of_caption = tokenizer.convert_tokens_to_ids('<|caption_start|>') + end_of_caption = tokenizer.convert_tokens_to_ids('<|caption_end|>') + start_of_depth = tokenizer.convert_tokens_to_ids('<|depth_start|>') + end_of_depth = tokenizer.convert_tokens_to_ids('<|depth_end|>') + start_of_normal = tokenizer.convert_tokens_to_ids('<|normal_start|>') + end_of_normal = tokenizer.convert_tokens_to_ids('<|normal_end|>') + + new_token_ids = dict( + bos_token_id=bos_token_id, + eos_token_id=eos_token_id, + start_of_image=start_of_image, + end_of_image=end_of_image, + start_of_caption=start_of_caption, + end_of_caption=end_of_caption, + start_of_depth=start_of_depth, + end_of_depth=end_of_depth, + start_of_normal=start_of_normal, + end_of_normal=end_of_normal, + ) + + return tokenizer, new_token_ids, num_new_tokens + + +def _unique_preserve_order(tokens: List[str]) -> List[str]: + seen = set() + out: List[str] = [] + for t in tokens: + if t in seen: + continue + seen.add(t) + out.append(t) + return out + + +def _format_tokens(token_format: str, start: int, end: int) -> List[str]: + # Inclusive. + return [token_format.format(i=i) for i in range(int(start), int(end) + 1)] + + +def add_codebook_tokens( + tokenizer, + *, + token_groups: List[Dict[str, Any]], + delimiter_tokens: List[str], + extra_tokens: Optional[List[str]] = None, +) -> Tuple[Any, Dict[str, List[int]], Dict[str, int], int]: + """ + Generic helper to add codebook-style tokens (DET/DINO/DINOLOCAL/custom) in one format. + + Returns: + tokenizer, + group_token_ids: dict[group_name] -> list[token_id] aligned to (start..end), + delimiter_token_ids: dict[token_str] -> token_id, + num_new_tokens + """ + extra_tokens = extra_tokens or [] + + group_tokens: Dict[str, List[str]] = {} + all_code_tokens: List[str] = [] + for g in token_groups: + name = str(g["name"]) + fmt = str(g["token_format"]) + start = int(g.get("start", 0)) + end = g.get("end") + if end is None: + raise ValueError(f"token_groups entry '{name}' missing 'end'") + end = int(end) + toks = _format_tokens(fmt, start, end) + group_tokens[name] = toks + all_code_tokens.extend(toks) + + tokens_to_add = _unique_preserve_order(all_code_tokens + list(delimiter_tokens) + list(extra_tokens)) + num_new_tokens = tokenizer.add_tokens(tokens_to_add) + + group_token_ids: Dict[str, List[int]] = { + name: [int(tokenizer.convert_tokens_to_ids(t)) for t in toks] + for name, toks in group_tokens.items() + } + delimiter_token_ids: Dict[str, int] = { + str(t): int(tokenizer.convert_tokens_to_ids(str(t))) + for t in _unique_preserve_order(list(delimiter_tokens) + list(extra_tokens)) + } + return tokenizer, group_token_ids, delimiter_token_ids, int(num_new_tokens) + + +def add_det_special_tokens(tokenizer): + """ + Add special tokens for detection box coordinates. + Creates tokens for quantized coordinate values (0-999) to make them learnable. + """ + token_groups = [ + {"name": "x1", "token_format": "<|x1_{i:03d}|>", "start": 0, "end": 999}, + {"name": "y1", "token_format": "<|y1_{i:03d}|>", "start": 0, "end": 999}, + {"name": "x2", "token_format": "<|x2_{i:03d}|>", "start": 0, "end": 999}, + {"name": "y2", "token_format": "<|y2_{i:03d}|>", "start": 0, "end": 999}, + {"name": "score", "token_format": "<|score_{i:02d}|>", "start": 0, "end": 99}, + ] + delimiter_tokens = ["<|det_start|>", "<|det_end|>"] + extra_tokens = ["<|box_start|>", "<|box_end|>"] + + tokenizer, group_ids, delim_ids, num_new_tokens = add_codebook_tokens( + tokenizer, + token_groups=token_groups, + delimiter_tokens=delimiter_tokens, + extra_tokens=extra_tokens, + ) + + coord_token_map: Dict[str, Dict[int, int]] = {} + for coord_type in ["x1", "y1", "x2", "y2"]: + coord_token_map[coord_type] = {i: int(tok_id) for i, tok_id in enumerate(group_ids[coord_type])} + + score_token_map: Dict[int, int] = {i: int(tok_id) for i, tok_id in enumerate(group_ids["score"])} + + det_delimiter_map = { + "det_start": int(delim_ids["<|det_start|>"]), + "det_end": int(delim_ids["<|det_end|>"]), + "box_start": int(delim_ids["<|box_start|>"]), + "box_end": int(delim_ids["<|box_end|>"]), + } + + new_token_ids = dict( + coord_token_map=coord_token_map, + score_token_map=score_token_map, + det_delimiter_map=det_delimiter_map, + ) + + return tokenizer, new_token_ids, num_new_tokens + + +def add_dino_feature_tokens(tokenizer, vocab_size=8192): + """ + Add special tokens for DINO features. + - 8192 code tokens: <|dino_0000|> ... <|dino_8191|> + - 2 delimiter tokens: <|dino_start|>, <|dino_end|> + Returns mapping dicts similar to add_det_special_tokens. + """ + token_groups = [ + {"name": "dino", "token_format": "<|dino_{i:04d}|>", "start": 0, "end": int(vocab_size) - 1}, + ] + delimiter_tokens = ["<|dino_start|>", "<|dino_end|>"] + tokenizer, group_ids, delim_ids, num_new_tokens = add_codebook_tokens( + tokenizer, + token_groups=token_groups, + delimiter_tokens=delimiter_tokens, + extra_tokens=None, + ) + + dino_token_map = {i: int(tok_id) for i, tok_id in enumerate(group_ids["dino"])} + dino_delimiter_map = { + "dino_start": int(delim_ids["<|dino_start|>"]), + "dino_end": int(delim_ids["<|dino_end|>"]), + } + + new_token_ids = dict( + dino_token_map=dino_token_map, + dino_delimiter_map=dino_delimiter_map, + ) + + return tokenizer, new_token_ids, num_new_tokens + + +def add_dinolocal_feature_tokens(tokenizer, vocab_size=8192): + """ + Add special tokens for DINO-Local features. + - vocab_size code tokens: <|dinolocal_0000|> ... <|dinolocal_{vocab_size-1:04d}|> + - 2 delimiter tokens: <|dinolocal_start|>, <|dinolocal_end|> + Returns mapping dicts similar to add_det_special_tokens. + """ + token_groups = [ + {"name": "dinolocal", "token_format": "<|dinolocal_{i:04d}|>", "start": 0, "end": int(vocab_size) - 1}, + ] + delimiter_tokens = ["<|dinolocal_start|>", "<|dinolocal_end|>"] + tokenizer, group_ids, delim_ids, num_new_tokens = add_codebook_tokens( + tokenizer, + token_groups=token_groups, + delimiter_tokens=delimiter_tokens, + extra_tokens=None, + ) + + dinolocal_token_map = {i: int(tok_id) for i, tok_id in enumerate(group_ids["dinolocal"])} + dinolocal_delimiter_map = { + "dinolocal_start": int(delim_ids["<|dinolocal_start|>"]), + "dinolocal_end": int(delim_ids["<|dinolocal_end|>"]), + } + + new_token_ids = dict( + dinolocal_token_map=dinolocal_token_map, + dinolocal_delimiter_map=dinolocal_delimiter_map, + ) + + return tokenizer, new_token_ids, num_new_tokens + + +def add_clip_feature_tokens(tokenizer, vocab_size=8192): + """ + Add special tokens for CLIP features. + - vocab_size code tokens: <|clip_0000|> ... <|clip_{vocab_size-1:04d}|> + - 2 delimiter tokens: <|clip_start|>, <|clip_end|> + Returns mapping dicts similar to add_det_special_tokens. + """ + token_groups = [ + {"name": "clip", "token_format": "<|clip_{i:04d}|>", "start": 0, "end": int(vocab_size) - 1}, + ] + delimiter_tokens = ["<|clip_start|>", "<|clip_end|>"] + tokenizer, group_ids, delim_ids, num_new_tokens = add_codebook_tokens( + tokenizer, + token_groups=token_groups, + delimiter_tokens=delimiter_tokens, + extra_tokens=None, + ) + + clip_token_map = {i: int(tok_id) for i, tok_id in enumerate(group_ids["clip"])} + clip_delimiter_map = { + "clip_start": int(delim_ids["<|clip_start|>"]), + "clip_end": int(delim_ids["<|clip_end|>"]), + } + + new_token_ids = dict( + clip_token_map=clip_token_map, + clip_delimiter_map=clip_delimiter_map, + ) + + return tokenizer, new_token_ids, num_new_tokens + + +def add_imagebind_feature_tokens(tokenizer, vocab_size=8192): + """ + Add special tokens for ImageBind (global) features. + - vocab_size code tokens: <|imagebind_0000|> ... <|imagebind_{vocab_size-1:04d}|> + - 2 delimiter tokens: <|imagebind_start|>, <|imagebind_end|> + Returns mapping dicts similar to add_det_special_tokens. + """ + token_groups = [ + {"name": "imagebind", "token_format": "<|imagebind_{i:04d}|>", "start": 0, "end": int(vocab_size) - 1}, + ] + delimiter_tokens = ["<|imagebind_start|>", "<|imagebind_end|>"] + tokenizer, group_ids, delim_ids, num_new_tokens = add_codebook_tokens( + tokenizer, + token_groups=token_groups, + delimiter_tokens=delimiter_tokens, + extra_tokens=None, + ) + + imagebind_token_map = {i: int(tok_id) for i, tok_id in enumerate(group_ids["imagebind"])} + imagebind_delimiter_map = { + "imagebind_start": int(delim_ids["<|imagebind_start|>"]), + "imagebind_end": int(delim_ids["<|imagebind_end|>"]), + } + + new_token_ids = dict( + imagebind_token_map=imagebind_token_map, + imagebind_delimiter_map=imagebind_delimiter_map, + ) + + return tokenizer, new_token_ids, num_new_tokens + + +def add_imagebindlocal_feature_tokens(tokenizer, vocab_size=8192): + """ + Add special tokens for ImageBind-Local features. + - vocab_size code tokens: <|imagebindlocal_0000|> ... <|imagebindlocal_{vocab_size-1:04d}|> + - 2 delimiter tokens: <|imagebindlocal_start|>, <|imagebindlocal_end|> + Returns mapping dicts similar to add_det_special_tokens. + """ + token_groups = [ + {"name": "imagebindlocal", "token_format": "<|imagebindlocal_{i:04d}|>", "start": 0, "end": int(vocab_size) - 1}, + ] + delimiter_tokens = ["<|imagebindlocal_start|>", "<|imagebindlocal_end|>"] + tokenizer, group_ids, delim_ids, num_new_tokens = add_codebook_tokens( + tokenizer, + token_groups=token_groups, + delimiter_tokens=delimiter_tokens, + extra_tokens=None, + ) + + imagebindlocal_token_map = {i: int(tok_id) for i, tok_id in enumerate(group_ids["imagebindlocal"])} + imagebindlocal_delimiter_map = { + "imagebindlocal_start": int(delim_ids["<|imagebindlocal_start|>"]), + "imagebindlocal_end": int(delim_ids["<|imagebindlocal_end|>"]), + } + + new_token_ids = dict( + imagebindlocal_token_map=imagebindlocal_token_map, + imagebindlocal_delimiter_map=imagebindlocal_delimiter_map, + ) + + return tokenizer, new_token_ids, num_new_tokens + + +def add_special_tokens_text_image(tokenizer): + all_special_tokens = [] + for k, v in tokenizer.special_tokens_map.items(): + if isinstance(v, str): + all_special_tokens.append(v) + elif isinstance(v, list): + all_special_tokens += v + + new_tokens = [] + + if '<|im_start|>' not in all_special_tokens: + new_tokens.append('<|im_start|>') + + if '<|im_end|>' not in all_special_tokens: + new_tokens.append('<|im_end|>') + + if '<|vision_start|>' not in all_special_tokens: + new_tokens.append('<|vision_start|>') + + if '<|vision_end|>' not in all_special_tokens: + new_tokens.append('<|vision_end|>') + + num_new_tokens = tokenizer.add_tokens(new_tokens) + bos_token_id = tokenizer.convert_tokens_to_ids('<|im_start|>') + eos_token_id = tokenizer.convert_tokens_to_ids('<|im_end|>') + start_of_image = tokenizer.convert_tokens_to_ids('<|vision_start|>') + end_of_image = tokenizer.convert_tokens_to_ids('<|vision_end|>') + + new_token_ids = dict( + bos_token_id=bos_token_id, + eos_token_id=eos_token_id, + start_of_image=start_of_image, + end_of_image=end_of_image, + ) + + return tokenizer, new_token_ids, num_new_tokens + +def len2weight(x, loss_reduction='square'): + if x == 0: + return x + if loss_reduction == 'token': + return 1 + if loss_reduction == 'sample': + return 1 / x + if loss_reduction == 'square': + return 1 / (x ** 0.5) + raise NotImplementedError(loss_reduction) diff --git a/data/dataset_base.py b/data/dataset_base.py new file mode 100644 index 0000000000000000000000000000000000000000..751e254a72798a951b5897b594e19eba6e0fb939 --- /dev/null +++ b/data/dataset_base.py @@ -0,0 +1,1235 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + + +import math +import random +import json +import os +import copy + +import numpy as np +import torch +import torch.nn.functional as F + +from .data_utils import ( + get_flattened_position_ids_interpolate, + get_flattened_position_ids_extrapolate, + len2weight, + patchify, + prepare_attention_mask_per_sample, +) +from .dataset_info import DATASET_INFO, DATASET_REGISTRY +from .interleave_datasets.any2any_dataset import UnifiedAny2AnyIterableDataset +from .transforms import ImageTransform +from .video_utils import FrameSampler + + +class DataConfig: + def __init__( + self, + grouped_datasets, + text_cond_dropout_prob=0.1, + vit_cond_dropout_prob=0.4, + vae_cond_dropout_prob=0.1, + vae_image_downsample=16, + max_latent_size=32, + vit_patch_size=14, + max_num_patch_per_side=70, + grounding_phrase_dropout_prob=0.5, + ): + self.grouped_datasets = grouped_datasets + self.text_cond_dropout_prob = text_cond_dropout_prob + self.vit_cond_dropout_prob = vit_cond_dropout_prob + self.vit_patch_size = vit_patch_size + self.max_num_patch_per_side = max_num_patch_per_side + self.vae_cond_dropout_prob = vae_cond_dropout_prob + self.vae_image_downsample = vae_image_downsample + self.max_latent_size = max_latent_size + self.grounding_phrase_dropout_prob = grounding_phrase_dropout_prob + + +class PackedDataset(torch.utils.data.IterableDataset): + def __init__( + self, + data_config, + tokenizer, + special_tokens, + modality_registry, + local_rank, + world_size, + num_workers, + expected_num_tokens=32768, + max_num_tokens_per_sample=16384, + max_num_tokens=36864, + prefer_buffer_before=16384, + max_buffer_size=50, + interpolate_pos=False, + use_flex=False, + data_status=None, + data_resume_state=None, + use_instruction=False, + use_condition_instruction=True, + use_target_instruction=True, + num_condition_modalities=1, + strict_num_condition_modalities=False, + timestep_sample=None, + mode_scale=None, + timestep_sample_mix_prob=None, + use_det_image=False, + visual_gen=True, + visual_und=True, + tail_n_rows=None, + force_condition_modality=None, + force_condition_modalities=None, + pred_intermediate_dir=None, + gt_restricted_dir=None, + fixed_row_list_path=None, + ): + super().__init__() + self.expected_num_tokens = expected_num_tokens + self.max_num_tokens_per_sample = max_num_tokens_per_sample + self.prefer_buffer_before = prefer_buffer_before + self.max_num_tokens = max_num_tokens + self.max_buffer_size = max_buffer_size + self.tokenizer = tokenizer + self.local_rank = local_rank + self.world_size = world_size + self.num_workers = num_workers + self.use_flex = use_flex + self.data_resume_state = data_resume_state + self.use_instruction = use_instruction + self.use_condition_instruction = use_condition_instruction + self.use_target_instruction = use_target_instruction + self.num_condition_modalities = num_condition_modalities + self.strict_num_condition_modalities = strict_num_condition_modalities + self.timestep_sample = timestep_sample + self.mode_scale = mode_scale + self.timestep_sample_mix_prob = timestep_sample_mix_prob + self.use_det_image = use_det_image + self.visual_gen = visual_gen + self.visual_und = visual_und + self.tail_n_rows = tail_n_rows + self.pred_intermediate_dir = pred_intermediate_dir + self.gt_restricted_dir = gt_restricted_dir + self.fixed_row_list_path = fixed_row_list_path + self.force_condition_modality = force_condition_modality + self.force_condition_modalities = force_condition_modalities + for k, v in special_tokens.items(): + setattr(self, k, v) + self.modality_registry = modality_registry + + # Derive token mappings and modality IDs from the registry. + self.start_token_mapping = { + s.name: s.start_token_key for s in self.modality_registry.specs + } + self.end_token_mapping = { + s.name: s.end_token_key for s in self.modality_registry.specs + } + self.modality_to_id = self.modality_registry.name_to_id() + self.id_to_modality = self.modality_registry.id_to_name() + + self.data_config = data_config + self.total_dataset_samples = 0 + self._seen_parquet_files = set() + self._epoch_tracked_groups = set() + grouped_datasets, is_mandatory, grouped_weights = self.build_datasets( + data_config.grouped_datasets, data_status + ) + self.grouped_datasets = grouped_datasets + self.dataset_iters = [iter(dataset) for dataset in grouped_datasets] + self.is_mandatory = is_mandatory + self.grouped_weights = grouped_weights + self.interpolate_pos = interpolate_pos + if self.interpolate_pos: + self.get_flattened_position_ids = get_flattened_position_ids_interpolate + else: + self.get_flattened_position_ids = get_flattened_position_ids_extrapolate + self._vit_size_warning_emitted = False + self._latent_size_warning_emitted = False + + def _fit_vit_image_tensor(self, image_tensor, modality_type): + patch_size = self.data_config.vit_patch_size + max_num_patch_per_side = self.data_config.max_num_patch_per_side + max_vit_side = patch_size * max_num_patch_per_side + _, img_h, img_w = image_tensor.shape + + def _align_down_to_patch_multiple(size): + return max(patch_size, (size // patch_size) * patch_size) + + needs_resize = img_h > max_vit_side or img_w > max_vit_side + if needs_resize: + scale = min(max_vit_side / img_h, max_vit_side / img_w) + resized_h = _align_down_to_patch_multiple(int(math.floor(img_h * scale))) + resized_w = _align_down_to_patch_multiple(int(math.floor(img_w * scale))) + resized_h = min(resized_h, max_vit_side) + resized_w = min(resized_w, max_vit_side) + else: + resized_h = _align_down_to_patch_multiple(img_h) + resized_w = _align_down_to_patch_multiple(img_w) + + if resized_h == img_h and resized_w == img_w: + return image_tensor + + image_tensor = F.interpolate( + image_tensor.unsqueeze(0), + size=(resized_h, resized_w), + mode="bilinear", + align_corners=False, + ).squeeze(0) + + if not self._vit_size_warning_emitted: + print( + "[JanusFlow][ViTClamp] resized visual-understanding tensor " + f"for modality={modality_type} from {img_h}x{img_w} to {resized_h}x{resized_w} " + f"(patch_size={patch_size}, max_num_patch_per_side={max_num_patch_per_side})", + flush=True, + ) + self._vit_size_warning_emitted = True + + return image_tensor + + def _fit_vae_image_tensor(self, image_tensor, modality_type): + downsample = self.data_config.vae_image_downsample + max_latent_size = self.data_config.max_latent_size + max_vae_side = downsample * max_latent_size + _, img_h, img_w = image_tensor.shape + + def _align_down_to_latent_multiple(size): + return max(downsample, (size // downsample) * downsample) + + needs_resize = img_h > max_vae_side or img_w > max_vae_side + if needs_resize: + scale = min(max_vae_side / img_h, max_vae_side / img_w) + resized_h = _align_down_to_latent_multiple(int(math.floor(img_h * scale))) + resized_w = _align_down_to_latent_multiple(int(math.floor(img_w * scale))) + resized_h = min(resized_h, max_vae_side) + resized_w = min(resized_w, max_vae_side) + else: + resized_h = _align_down_to_latent_multiple(img_h) + resized_w = _align_down_to_latent_multiple(img_w) + + if resized_h == img_h and resized_w == img_w: + return image_tensor + + image_tensor = F.interpolate( + image_tensor.unsqueeze(0), + size=(resized_h, resized_w), + mode="bilinear", + align_corners=False, + ).squeeze(0) + + if not self._latent_size_warning_emitted: + print( + "[JanusFlow][LatentClamp] resized visual-generation tensor " + f"for modality={modality_type} from {img_h}x{img_w} to {resized_h}x{resized_w} " + f"(vae_downsample={downsample}, max_latent_size={max_latent_size})", + flush=True, + ) + self._latent_size_warning_emitted = True + + return image_tensor + + + def build_datasets(self, datasets_metainfo, data_status): + datasets = [] + is_mandatory = [] + grouped_weights = [] + for grouped_dataset_name, dataset_args in datasets_metainfo.items(): + is_mandatory.append(dataset_args.pop('is_mandatory', False)) + grouped_weights.append(dataset_args.pop('weight', 0.0)) + + if 'frame_sampler_args' in dataset_args.keys(): + frame_sampler = FrameSampler(**dataset_args.pop('frame_sampler_args')) + dataset_args['frame_sampler'] = frame_sampler + if 'image_transform_args' in dataset_args.keys(): + transform = ImageTransform(**dataset_args.pop('image_transform_args')) + dataset_args['transform'] = transform + if 'vit_image_transform_args' in dataset_args.keys(): + vit_transform = ImageTransform(**dataset_args.pop('vit_image_transform_args')) + dataset_args['vit_transform'] = vit_transform + + assert 'dataset_names' in dataset_args.keys() + dataset_names = dataset_args.pop('dataset_names') + dataset_args['data_dir_list'] = [] + for item in dataset_names: + if self.local_rank == 0: + print(f'Preparing Dataset {grouped_dataset_name}/{item}') + meta_info = DATASET_INFO[grouped_dataset_name][item] + dataset_args['data_dir_list'].append(meta_info['data_dir']) + + if "parquet_info_path" in meta_info.keys(): + if 'parquet_info' not in dataset_args.keys(): + dataset_args['parquet_info'] = {} + info_path = meta_info['parquet_info_path'] + if not os.path.exists(info_path): + # Fall back to the copy bundled in the repo. The configured + # path lives under datasets/ which may be a symlink that + # isn't present on a fresh clone / a different cluster. + bundled = os.path.join( + os.path.dirname(__file__), 'bundled_parquet_info', + os.path.basename(info_path)) + if os.path.exists(bundled): + info_path = bundled + with open(info_path, 'r') as f: + parquet_info = json.load(f) + dataset_args['parquet_info'].update(parquet_info) + self._epoch_tracked_groups.add(grouped_dataset_name) + for path, info in parquet_info.items(): + if path not in self._seen_parquet_files: + self._seen_parquet_files.add(path) + self.total_dataset_samples += info.get('num_rows', 0) + + if 'json_dir' in meta_info.keys(): + # parquet/tar with json + if 'json_dir_list' not in dataset_args.keys(): + dataset_args['json_dir_list'] = [meta_info['json_dir']] + else: + dataset_args['json_dir_list'].append(meta_info['json_dir']) + + if 'jsonl_path' in meta_info.keys(): + # jsonl with jpeg + if 'jsonl_path_list' not in dataset_args.keys(): + dataset_args['jsonl_path_list'] = [meta_info['jsonl_path']] + else: + dataset_args['jsonl_path_list'].append(meta_info['jsonl_path']) + + resume_data_status = dataset_args.pop('resume_data_status', True) + if data_status is not None and grouped_dataset_name in data_status.keys() and resume_data_status: + data_status_per_group = data_status[grouped_dataset_name] + else: + data_status_per_group = None + # Validation hooks (force_condition_modality, tail_n_rows) only make + # sense for any2any parquet datasets; passing them to e.g. vlm_sft + # (SftJSONLIterableDataset) would raise TypeError on unknown kwargs. + extra_args = {} + if issubclass(DATASET_REGISTRY[grouped_dataset_name], UnifiedAny2AnyIterableDataset): + if self.tail_n_rows is not None: + extra_args['tail_n_rows'] = self.tail_n_rows + if self.force_condition_modality is not None: + extra_args['force_condition_modality'] = self.force_condition_modality + if self.force_condition_modalities is not None: + extra_args['force_condition_modalities'] = self.force_condition_modalities + if self.pred_intermediate_dir is not None: + extra_args['pred_intermediate_dir'] = self.pred_intermediate_dir + if self.gt_restricted_dir is not None: + extra_args['gt_restricted_dir'] = self.gt_restricted_dir + if self.fixed_row_list_path is not None: + extra_args['fixed_row_list_path'] = self.fixed_row_list_path + dataset = DATASET_REGISTRY[grouped_dataset_name]( + dataset_name=grouped_dataset_name, + tokenizer=self.tokenizer, + local_rank=self.local_rank, + world_size=self.world_size, + num_workers=self.num_workers, + data_status=data_status_per_group, + use_instruction=self.use_instruction, + use_condition_instruction=self.use_condition_instruction, + use_target_instruction=self.use_target_instruction, + num_condition_modalities=self.num_condition_modalities, + strict_num_condition_modalities=self.strict_num_condition_modalities, + use_det_image=self.use_det_image, + modality_registry=self.modality_registry, + **extra_args, + **dataset_args, + ) + dataset.grounding_phrase_dropout_prob = getattr( + self.data_config, 'grounding_phrase_dropout_prob', 0.0 + ) + datasets.append(dataset) + + return datasets, is_mandatory, grouped_weights + + def set_epoch(self, seed): + for dataset in self.grouped_datasets: + dataset.set_epoch(seed) + + def set_sequence_status(self): + sequence_status = dict( + curr = 0, + sample_lens = list(), + packed_position_ids = list(), + nested_attention_masks = list(), + split_lens = list(), + attn_modes = list(), + packed_text_ids = list(), + packed_text_indexes = list(), + packed_label_ids = list(), + ce_loss_indexes = list(), + ce_loss_weights = list(), + ce_loss_modality_ids = list(), # Track modality ID for each CE loss token + vae_image_tensors = list(), + vae_image_modality_types = list(), + packed_latent_position_ids = list(), + vae_latent_shapes = list(), + packed_vae_token_indexes = list(), + packed_timesteps = list(), + mse_loss_indexes = list(), + mse_loss_modality_ids = list(), # Track modality ID for each MSE loss token + mse_loss_route_ids = list(), # Route tag for rgb target monitoring + mse_loss_image_ids = list(), # Per-token image id for per-sample MSE logging + mse_loss_timesteps = list(), # Per-token sampled timestep for MSE tokens + packed_vit_tokens = list(), + vit_token_seqlens = list(), + vit_image_modality_types = list(), + packed_vit_position_ids = list(), + packed_vit_token_indexes = list(), + # (token_h, token_w) per ViT-input image; consumed by model_wrapper.forward + # to build 2D rope_image_info for the ViT-input image segment, matching the + # pretrained Hunyuan convention (build_batch_rope_image_info, cond_vit_image). + vit_image_token_shapes = list(), + target_modality_types = list(), + next_mse_image_id = 0, + ) + return sequence_status + + def to_tensor(self, sequence_status): + data = dict( + sequence_length=sum(sequence_status['sample_lens']), + num_samples=len(sequence_status['sample_lens']), + sample_lens=sequence_status['sample_lens'], + target_modality_types=sequence_status['target_modality_types'], + vae_image_modality_types=sequence_status['vae_image_modality_types'], + packed_text_ids=torch.tensor(sequence_status['packed_text_ids']), + packed_text_indexes=torch.tensor(sequence_status['packed_text_indexes']), + packed_position_ids=torch.tensor(sequence_status['packed_position_ids']), + ) + if not self.use_flex: + data['nested_attention_masks'] = sequence_status['nested_attention_masks'] + else: + sequence_len = data['sequence_length'] + pad_len = self.max_num_tokens - sequence_len + data['split_lens'] = sequence_status['split_lens'] + [pad_len] + data['attn_modes'] = sequence_status['attn_modes'] + ['causal'] + data['sample_lens'] += [pad_len] + + # if the model has a convnet vae (e.g., as visual tokenizer) + if len(sequence_status['vae_image_tensors']) > 0: + image_tensors = sequence_status.pop('vae_image_tensors') + image_sizes = [item.shape for item in image_tensors] + max_image_size = [max(item) for item in list(zip(*image_sizes))] + padded_images = torch.zeros(size=(len(image_tensors), *max_image_size)) + for i, image_tensor in enumerate(image_tensors): + padded_images[i, :, :image_tensor.shape[1], :image_tensor.shape[2]] = image_tensor + + data['padded_images'] = padded_images + data['patchified_vae_latent_shapes'] = sequence_status['vae_latent_shapes'] + data['packed_latent_position_ids'] = torch.cat(sequence_status['packed_latent_position_ids'], dim=0) + data['packed_vae_token_indexes'] = torch.tensor(sequence_status['packed_vae_token_indexes']) + + # if the model has a vit (e.g., as visual tokenizer) + if len(sequence_status['packed_vit_tokens']) > 0: + data['packed_vit_tokens'] = torch.cat(sequence_status['packed_vit_tokens'], dim=0) + data['packed_vit_position_ids'] = torch.cat(sequence_status['packed_vit_position_ids'], dim=0) + data['packed_vit_token_indexes'] = torch.tensor(sequence_status['packed_vit_token_indexes']) + data['vit_image_token_shapes'] = list(sequence_status['vit_image_token_shapes']) + data['vit_token_seqlens'] = torch.tensor(sequence_status['vit_token_seqlens']) + data['vit_image_modality_types'] = sequence_status['vit_image_modality_types'] + + # if the model is required to perform visual generation + if len(sequence_status['packed_timesteps']) > 0: + data['packed_timesteps'] = torch.tensor(sequence_status['packed_timesteps']) + data['mse_loss_indexes'] = torch.tensor(sequence_status['mse_loss_indexes'], dtype=torch.long) + data['mse_loss_modality_ids'] = torch.tensor(sequence_status['mse_loss_modality_ids'], dtype=torch.long) + data['mse_loss_route_ids'] = torch.tensor(sequence_status['mse_loss_route_ids'], dtype=torch.long) + data['mse_loss_image_ids'] = torch.tensor(sequence_status['mse_loss_image_ids'], dtype=torch.long) + data['mse_loss_timesteps'] = torch.tensor(sequence_status['mse_loss_timesteps']) + + # if the model is required to perform text generation + if len(sequence_status['packed_label_ids']) > 0: + data['packed_label_ids'] = torch.tensor(sequence_status['packed_label_ids'], dtype=torch.long) + data['ce_loss_indexes'] = torch.tensor(sequence_status['ce_loss_indexes'], dtype=torch.long) + data['ce_loss_weights'] = torch.tensor(sequence_status['ce_loss_weights']) + data['ce_loss_modality_ids'] = torch.tensor(sequence_status['ce_loss_modality_ids'], dtype=torch.long) + + return data + + def __iter__(self): + worker_info = torch.utils.data.get_worker_info() + worker_id = worker_info.id if worker_info is not None else 0 + total_weights = sum(self.grouped_weights) + assert total_weights > 0.0 + group_cumprobs = [sum(self.grouped_weights[:i + 1]) / total_weights + for i in range(len(self.grouped_weights))] + sequence_status = self.set_sequence_status() + batch_data_indexes = [] + + buffer = [] + if self.data_resume_state is not None: + worker_resume_state = self.data_resume_state.get(worker_id, self.data_resume_state) + buffer = copy.deepcopy(worker_resume_state.get("buffer", [])) + py_state = worker_resume_state.get("python_random_state") + np_state = worker_resume_state.get("numpy_random_state") + torch_state = worker_resume_state.get("torch_random_state") + if py_state is not None: + random.setstate(py_state) + if np_state is not None: + np.random.set_state(np_state) + if torch_state is not None: + torch.random.set_rng_state(torch_state) + # Consume once. Future epochs in the same process should proceed normally. + self.data_resume_state = None + while True: + # Ensure at least one sample from each group unless explicitly disabled. + # Disabling this can drastically reduce packed sequence length and + # avoid pathological long-sequence attention OOM/NaN behavior. + _disable_mandatory = os.environ.get("HUNYUAN_DISABLE_MANDATORY_WARMSTART", "0") == "1" + if sequence_status['curr'] == 0 and (not _disable_mandatory): + _max_mandatory_trials = int(os.environ.get("HUNYUAN_MANDATORY_MAX_TRIALS", "2000")) + for group_index, group_iter in enumerate(self.dataset_iters): + if self.is_mandatory[group_index]: + _trials = 0 + while True: + sample = next(group_iter) + # Tentative pack on a cloned status: this gives the + # true token expansion for visual branches. + trial_status = self.pack_sequence( + sample, self._clone_sequence_status(sequence_status) + ) + num_tokens = trial_status['curr'] - sequence_status['curr'] + if ( + num_tokens < self.max_num_tokens_per_sample + and trial_status['curr'] <= self.max_num_tokens + ): + sequence_status = trial_status + batch_data_indexes.append(sample['data_indexes']) + break + else: + _trials += 1 + if _max_mandatory_trials > 0 and _trials >= _max_mandatory_trials: + print( + f"[DataPack] mandatory group {group_index} exceeded " + f"{_max_mandatory_trials} trials under token constraints " + f"(max_per_sample={self.max_num_tokens_per_sample}, max_total={self.max_num_tokens}); " + "skipping mandatory warmstart for this group in this batch" + ) + break + continue + + if sequence_status['curr'] < self.prefer_buffer_before and len(buffer) > 0: + sample = buffer.pop(0) + sample_from_buffer = True + else: + # sample normally across all groups + n = random.random() + group_index = 0 + for i, cumprob in enumerate(group_cumprobs): + if n < cumprob: + group_index = i + break + sample = next(self.dataset_iters[group_index]) + sample_from_buffer = False + + trial_status = self.pack_sequence( + sample, self._clone_sequence_status(sequence_status) + ) + num_tokens = trial_status['curr'] - sequence_status['curr'] + if num_tokens > self.max_num_tokens_per_sample: + # print(f"skip a sample with length {num_tokens}") + continue + + if trial_status['curr'] > self.max_num_tokens: + if len(buffer) < self.max_buffer_size and not sample_from_buffer: + buffer.append(sample) + else: + if sequence_status['curr'] > 0: + data = self.to_tensor(sequence_status) + data['batch_data_indexes'] = batch_data_indexes + data['num_epoch_samples'] = sum( + 1 for idx in batch_data_indexes + if idx["dataset_name"] in self._epoch_tracked_groups + ) + data['data_resume_state'] = self._build_resume_state(buffer, worker_id) + yield data + sequence_status = self.set_sequence_status() + batch_data_indexes = [] + continue + + sequence_status = trial_status + batch_data_indexes.append(sample['data_indexes']) + + if sequence_status['curr'] >= self.expected_num_tokens: + data = self.to_tensor(sequence_status) + data['batch_data_indexes'] = batch_data_indexes + data['num_epoch_samples'] = sum( + 1 for idx in batch_data_indexes + if idx["dataset_name"] in self._epoch_tracked_groups + ) + data['data_resume_state'] = self._build_resume_state(buffer, worker_id) + yield data + sequence_status = self.set_sequence_status() + batch_data_indexes = [] + + def _build_resume_state(self, buffer, worker_id): + """Capture the iterable packer's next-step resume state. + + This stores only CPU-side iterator state. Sub-dataset row cursors are + still tracked separately via ``data_status`` in the training loop. + """ + return { + "worker_id": worker_id, + "version": 1, + "buffer": copy.deepcopy(buffer), + "python_random_state": random.getstate(), + "numpy_random_state": np.random.get_state(), + "torch_random_state": torch.random.get_rng_state().cpu(), + } + + def _clone_sequence_status(self, sequence_status): + """Clone mutable sequence status containers for tentative packing.""" + cloned = {} + for k, v in sequence_status.items(): + if isinstance(v, list): + cloned[k] = v.copy() + else: + cloned[k] = v + return cloned + + def _sample_timestep(self): + """Sample a final timestep value in (0, 1] for one image chunk. + + The sampling strategy is controlled by ``self.timestep_sample``: + + * ``logit_norm`` – logistic-distribution sample (sigmoid of a normal). + * ``mode`` – uniform sample optionally warped by a cosine mode + schedule controlled by ``self.mode_scale``. + * ``linear`` – inverse-CDF sample giving P(t)=2t (higher density + near t=1). + * ``pure_noise`` – constant ``1.0`` (pure-noise target). + * ``mix`` – with probability ``timestep_sample_mix_prob`` draw a + uniform sample, otherwise ``1.0``. + + Returns a ``float`` ready to be used as the flow-matching timestep. + """ + eps = 1e-6 + strategy = self.timestep_sample + + if strategy == 'logit_norm': + # Sigmoid of a standard-normal sample → logistic distribution on (0,1). + t = 1.0 / (1.0 + math.exp(-np.random.randn())) + elif strategy == 'mode': + t = float(np.random.rand()) + if self.mode_scale != 0.0: + t = ( + 1.0 - t + - self.mode_scale + * (math.cos(math.pi * t / 2) ** 2 - 1.0 + t) + ) + t = max(eps, min(1.0 - eps, t)) + elif strategy == 'linear': + t = math.sqrt(float(np.random.rand())) + t = max(eps, min(1.0 - eps, t)) + elif strategy == 'pure_noise': + t = 1.0 + elif strategy == 'mix': + if np.random.rand() < self.timestep_sample_mix_prob: + t = float(np.random.rand()) + else: + t = 1.0 + else: + raise ValueError(f"Unknown timestep_sample strategy: {strategy}") + + return t + + def _native_token_id(self, token): + token_id = self.tokenizer.convert_tokens_to_ids(token) + if token_id is None or token_id < 0: + raise ValueError(f"Native Hunyuan token is not in tokenizer: {token}") + return int(token_id) + + def pack_sequence(self, sample, sequence_status): + image_tensor_list = list(sample['image_tensor_list']) + text_ids_list = list(sample['text_ids_list']) + sequence_plan = sample['sequence_plan'] + + split_lens, attn_modes = list(), list() + curr = sequence_status['curr'] + curr_rope_id = 0 + sample_lens = 0 + last_loss_modality_type = None + + for item in sequence_plan: + split_start = item.get('split_start', True) + if split_start: + curr_split_len = 0 + + if item['type'] == 'raw_text': + text_ids = text_ids_list.pop(0) + if item['enable_cfg'] == 1 and random.random() < self.data_config.text_cond_dropout_prob: + continue + if item['loss'] == 1: + raise NotImplementedError("raw_text sequence items are for no-loss chat scaffolding only") + + sequence_status['packed_text_ids'].extend(text_ids) + sequence_status['packed_text_indexes'].extend(range(curr, curr + len(text_ids))) + curr += len(text_ids) + curr_split_len += len(text_ids) + + attn_modes.append("causal") + sequence_status['packed_position_ids'].extend(range(curr_rope_id, curr_rope_id + curr_split_len)) + curr_rope_id += curr_split_len + + elif item['type'] == 'text': + start_token_attr = self.start_token_mapping[item['modality_type']] + end_token_attr = self.end_token_mapping[item['modality_type']] + text_ids = text_ids_list.pop(0) + if item['enable_cfg'] == 1 and random.random() < self.data_config.text_cond_dropout_prob: + continue + + + shifted_text_ids = [getattr(self, start_token_attr)] + text_ids + sequence_status['packed_text_ids'].extend(shifted_text_ids) + sequence_status['packed_text_indexes'].extend(range(curr, curr + len(shifted_text_ids))) + if item['loss'] == 1: + last_loss_modality_type = item['modality_type'] + sequence_status['ce_loss_indexes'].extend(range(curr, curr + len(shifted_text_ids))) + sequence_status['ce_loss_weights'].extend( + [len2weight(len(shifted_text_ids))] * len(shifted_text_ids) + ) + sequence_status['ce_loss_modality_ids'].extend( + [self.modality_to_id[item['modality_type']]] * len(shifted_text_ids) + ) + sequence_status['packed_label_ids'].extend(text_ids + [getattr(self, end_token_attr)]) + curr += len(shifted_text_ids) + curr_split_len += len(shifted_text_ids) + + # add a <|im_end|> token + sequence_status['packed_text_ids'].append(getattr(self, end_token_attr)) + sequence_status['packed_text_indexes'].append(curr) + if item['special_token_loss'] == 1: # <|im_end|> may have loss + sequence_status['ce_loss_indexes'].append(curr) + sequence_status['ce_loss_weights'].append(1.0) + sequence_status['packed_label_ids'].append(item['special_token_label']) + curr += 1 + curr_split_len += 1 + + # update sequence status + attn_modes.append("causal") + sequence_status['packed_position_ids'].extend(range(curr_rope_id, curr_rope_id + curr_split_len)) + curr_rope_id += curr_split_len + + elif item['type'] == 'vit_image': + start_token_attr = self.start_token_mapping[item['modality_type']] + end_token_attr = self.end_token_mapping[item['modality_type']] + if not self.visual_und: + curr_rope_id += 1 + continue + image_tensor = image_tensor_list.pop(0) + # Config-driven conditioning: allow modalities to opt out of ViT conditioning in BOTH train/infer. + # Only applies to conditioning branches (loss==0). Target branches are kept intact. + if self.modality_registry is not None and int(item.get('loss', 0)) == 0: + try: + spec = self.modality_registry.get(item['modality_type']) + if not spec.represent_vit: + curr_rope_id += 1 + continue + except Exception: + # Unknown modality -> keep legacy behavior + pass + if item['enable_cfg'] == 1 and random.random() < self.data_config.vit_cond_dropout_prob: + curr_rope_id += 1 + continue + + # add a <|startofimage|> token + + sequence_status['packed_text_ids'].append(getattr(self, start_token_attr)) + sequence_status['packed_text_indexes'].append(curr) + curr += 1 + curr_split_len += 1 + + # preprocess image + image_tensor = self._fit_vit_image_tensor(image_tensor, item['modality_type']) + vit_tokens = patchify(image_tensor, self.data_config.vit_patch_size) + num_img_tokens = vit_tokens.shape[0] + sequence_status['packed_vit_token_indexes'].extend(range(curr, curr + num_img_tokens)) + curr += num_img_tokens + curr_split_len += num_img_tokens + + sequence_status['packed_vit_tokens'].append(vit_tokens) + sequence_status['vit_token_seqlens'].append(num_img_tokens) + sequence_status['vit_image_modality_types'].append(item['modality_type']) + sequence_status['vit_image_token_shapes'].append(( + image_tensor.size(1) // self.data_config.vit_patch_size, + image_tensor.size(2) // self.data_config.vit_patch_size, + )) + vit_position_ids = self.get_flattened_position_ids( + image_tensor.size(1), image_tensor.size(2), + self.data_config.vit_patch_size, + max_num_patches_per_side=self.data_config.max_num_patch_per_side + ) + max_vit_position_id = self.data_config.max_num_patch_per_side ** 2 - 1 + if vit_position_ids.numel() > 0 and int(vit_position_ids.max().item()) > max_vit_position_id: + raise ValueError( + "ViT position id out of range after transform: " + f"modality={item['modality_type']}, " + f"image_hw={tuple(image_tensor.shape[-2:])}, " + f"patch_size={self.data_config.vit_patch_size}, " + f"max_num_patch_per_side={self.data_config.max_num_patch_per_side}, " + f"max_position_id={int(vit_position_ids.max().item())}, " + f"allowed_max={max_vit_position_id}" + ) + sequence_status['packed_vit_position_ids'].append(vit_position_ids) + # import pdb; pdb.set_trace() + + # add a <|endofimage|> token + sequence_status['packed_text_ids'].append(getattr(self, end_token_attr)) + sequence_status['packed_text_indexes'].append(curr) + if item['special_token_loss'] == 1: # <|endofimage|> may have loss + sequence_status['ce_loss_indexes'].append(curr) + sequence_status['ce_loss_weights'].append(1.0) + sequence_status['packed_label_ids'].append(item['special_token_label']) + curr += 1 + curr_split_len += 1 + + # update sequence status + attn_modes.append("full") + sequence_status['packed_position_ids'].extend([curr_rope_id] * curr_split_len) + curr_rope_id += 1 + + elif item['type'] == 'vae_image': + start_token_attr = self.start_token_mapping[item['modality_type']] + end_token_attr = self.end_token_mapping[item['modality_type']] + if not self.visual_gen: + curr_rope_id += 1 + continue + image_tensor = image_tensor_list.pop(0) + # Config-driven conditioning: allow modalities to opt out of VAE conditioning in BOTH train/infer. + # Only applies to conditioning branches (loss==0). Target branches are kept intact. + if self.modality_registry is not None and int(item.get('loss', 0)) == 0: + try: + spec = self.modality_registry.get(item['modality_type']) + if not spec.represent_vae: + curr_rope_id += 1 + continue + except Exception: + # Unknown modality -> keep legacy behavior + pass + if item['enable_cfg'] == 1 and random.random() < self.data_config.vae_cond_dropout_prob: + # FIXME fix vae dropout in video2video setting. + curr_rope_id += 1 + continue + + # add a <|startofimage|> token + + sequence_status['packed_text_ids'].append(getattr(self, start_token_attr)) + sequence_status['packed_text_indexes'].append(curr) + curr += 1 + curr_split_len += 1 + + # preprocess image + image_tensor = self._fit_vae_image_tensor(image_tensor, item['modality_type']) + sequence_status['vae_image_tensors'].append(image_tensor) + sequence_status['vae_image_modality_types'].append(item['modality_type']) + latent_position_ids = self.get_flattened_position_ids( + image_tensor.size(1), image_tensor.size(2), + self.data_config.vae_image_downsample, + max_num_patches_per_side=self.data_config.max_latent_size + ) + max_latent_position_id = self.data_config.max_latent_size ** 2 - 1 + if ( + latent_position_ids.numel() > 0 + and int(latent_position_ids.max().item()) > max_latent_position_id + ): + raise ValueError( + "Latent position id out of range after transform: " + f"modality={item['modality_type']}, " + f"image_hw={tuple(image_tensor.shape[-2:])}, " + f"vae_downsample={self.data_config.vae_image_downsample}, " + f"max_latent_size={self.data_config.max_latent_size}, " + f"max_position_id={int(latent_position_ids.max().item())}, " + f"allowed_max={max_latent_position_id}" + ) + sequence_status['packed_latent_position_ids'].append(latent_position_ids) + H, W = image_tensor.shape[1:] + h = H // self.data_config.vae_image_downsample + w = W // self.data_config.vae_image_downsample + sequence_status['vae_latent_shapes'].append((h, w)) + + num_img_tokens = w * h + sequence_status['packed_vae_token_indexes'].extend(range(curr, curr + num_img_tokens)) + if item['loss'] == 1: + last_loss_modality_type = item['modality_type'] + mse_image_id = sequence_status['next_mse_image_id'] + sequence_status['next_mse_image_id'] += 1 + sequence_status['mse_loss_indexes'].extend(range(curr, curr + num_img_tokens)) + sequence_status['mse_loss_modality_ids'].extend( + [self.modality_to_id[item['modality_type']]] * num_img_tokens + ) + if split_start: + timestep = self._sample_timestep() + route_name = sample.get('rgb_loss_route', None) + if item['modality_type'] == 'rgb' and route_name is not None: + route_to_id = {'caption2rgb': 1, 'grounding2rgb': 2, 'dinolocal2rgb': 3} + route_id = route_to_id.get(route_name, 0) + else: + route_id = 0 + sequence_status['mse_loss_route_ids'].extend([route_id] * num_img_tokens) + sequence_status['mse_loss_image_ids'].extend([mse_image_id] * num_img_tokens) + sequence_status['mse_loss_timesteps'].extend([timestep] * num_img_tokens) + else: + timestep = 0.0 + + sequence_status['packed_timesteps'].extend([timestep] * num_img_tokens) + curr += num_img_tokens + curr_split_len += num_img_tokens + + # add a <|endofimage|> token + sequence_status['packed_text_ids'].append(getattr(self, end_token_attr)) + sequence_status['packed_text_indexes'].append(curr) + # <|endofimage|> may have loss + if item['special_token_loss'] == 1: + sequence_status['ce_loss_indexes'].append(curr) + sequence_status['ce_loss_weights'].append(1.0) + sequence_status['packed_label_ids'].append(item['special_token_label']) + curr += 1 + curr_split_len += 1 + + # update sequence status + if split_start: + if item['loss'] == 1 and 'frame_delta' not in item.keys(): + attn_modes.append("noise") + else: + attn_modes.append("full") + sequence_status['packed_position_ids'].extend([curr_rope_id] * (num_img_tokens + 2)) + if 'frame_delta' in item.keys(): + curr_rope_id += item['frame_delta'] + elif item['loss'] == 0: + curr_rope_id += 1 + + elif item['type'] == 'native_gen_image': + if not self.visual_gen: + curr_rope_id += 1 + continue + image_tensor = image_tensor_list.pop(0) + + prefix_ids = [ + self._native_token_id(''), + self._native_token_id(f""), + self._native_token_id(f""), + self._native_token_id(''), + ] + eoi_id = self._native_token_id('') + + sequence_status['packed_text_ids'].extend(prefix_ids) + sequence_status['packed_text_indexes'].extend(range(curr, curr + len(prefix_ids))) + curr += len(prefix_ids) + curr_split_len += len(prefix_ids) + + image_tensor = self._fit_vae_image_tensor(image_tensor, item['modality_type']) + sequence_status['vae_image_tensors'].append(image_tensor) + sequence_status['vae_image_modality_types'].append(item['modality_type']) + latent_position_ids = self.get_flattened_position_ids( + image_tensor.size(1), image_tensor.size(2), + self.data_config.vae_image_downsample, + max_num_patches_per_side=self.data_config.max_latent_size + ) + sequence_status['packed_latent_position_ids'].append(latent_position_ids) + H, W = image_tensor.shape[1:] + h = H // self.data_config.vae_image_downsample + w = W // self.data_config.vae_image_downsample + sequence_status['vae_latent_shapes'].append((h, w)) + + num_img_tokens = w * h + sequence_status['packed_vae_token_indexes'].extend(range(curr, curr + num_img_tokens)) + last_loss_modality_type = item['modality_type'] + mse_image_id = sequence_status['next_mse_image_id'] + sequence_status['next_mse_image_id'] += 1 + sequence_status['mse_loss_indexes'].extend(range(curr, curr + num_img_tokens)) + sequence_status['mse_loss_modality_ids'].extend( + [self.modality_to_id[item['modality_type']]] * num_img_tokens + ) + timestep = self._sample_timestep() + route_name = sample.get('rgb_loss_route', None) + if item['modality_type'] == 'rgb' and route_name is not None: + route_to_id = {'caption2rgb': 1, 'grounding2rgb': 2, 'dinolocal2rgb': 3} + route_id = route_to_id.get(route_name, 0) + else: + route_id = 0 + sequence_status['mse_loss_route_ids'].extend([route_id] * num_img_tokens) + sequence_status['mse_loss_image_ids'].extend([mse_image_id] * num_img_tokens) + sequence_status['mse_loss_timesteps'].extend([timestep] * num_img_tokens) + sequence_status['packed_timesteps'].extend([timestep] * num_img_tokens) + curr += num_img_tokens + curr_split_len += num_img_tokens + + sequence_status['packed_text_ids'].append(eoi_id) + sequence_status['packed_text_indexes'].append(curr) + curr += 1 + curr_split_len += 1 + + if split_start: + attn_modes.append("noise") + sequence_status['packed_position_ids'].extend( + [curr_rope_id] * (len(prefix_ids) + num_img_tokens + 1) + ) + + elif item['type'] == 'native_cond_joint_image': + if not (self.visual_gen or self.visual_und): + curr_rope_id += 1 + continue + vae_image_tensor = image_tensor_list.pop(0) + vit_image_tensor = image_tensor_list.pop(0) + if item['enable_cfg'] == 1 and random.random() < self.data_config.vae_cond_dropout_prob: + curr_rope_id += 1 + continue + + boi_id = self._native_token_id('') + sep_id = self._native_token_id('') + eoi_id = self._native_token_id('') + + sequence_status['packed_text_ids'].append(boi_id) + sequence_status['packed_text_indexes'].append(curr) + curr += 1 + curr_split_len += 1 + + vae_image_tensor = self._fit_vae_image_tensor(vae_image_tensor, item['modality_type']) + sequence_status['vae_image_tensors'].append(vae_image_tensor) + sequence_status['vae_image_modality_types'].append(item['modality_type']) + latent_position_ids = self.get_flattened_position_ids( + vae_image_tensor.size(1), vae_image_tensor.size(2), + self.data_config.vae_image_downsample, + max_num_patches_per_side=self.data_config.max_latent_size + ) + sequence_status['packed_latent_position_ids'].append(latent_position_ids) + H, W = vae_image_tensor.shape[1:] + h = H // self.data_config.vae_image_downsample + w = W // self.data_config.vae_image_downsample + num_vae_tokens = w * h + sequence_status['vae_latent_shapes'].append((h, w)) + sequence_status['packed_vae_token_indexes'].extend(range(curr, curr + num_vae_tokens)) + sequence_status['packed_timesteps'].extend([0.0] * num_vae_tokens) + curr += num_vae_tokens + curr_split_len += num_vae_tokens + + sequence_status['packed_text_ids'].append(sep_id) + sequence_status['packed_text_indexes'].append(curr) + curr += 1 + curr_split_len += 1 + + vit_image_tensor = self._fit_vit_image_tensor(vit_image_tensor, item['modality_type']) + vit_tokens = patchify(vit_image_tensor, self.data_config.vit_patch_size) + num_vit_tokens = vit_tokens.shape[0] + sequence_status['packed_vit_token_indexes'].extend(range(curr, curr + num_vit_tokens)) + curr += num_vit_tokens + curr_split_len += num_vit_tokens + sequence_status['packed_vit_tokens'].append(vit_tokens) + sequence_status['vit_token_seqlens'].append(num_vit_tokens) + sequence_status['vit_image_modality_types'].append(item['modality_type']) + sequence_status['vit_image_token_shapes'].append(( + vit_image_tensor.size(1) // self.data_config.vit_patch_size, + vit_image_tensor.size(2) // self.data_config.vit_patch_size, + )) + vit_position_ids = self.get_flattened_position_ids( + vit_image_tensor.size(1), vit_image_tensor.size(2), + self.data_config.vit_patch_size, + max_num_patches_per_side=self.data_config.max_num_patch_per_side + ) + sequence_status['packed_vit_position_ids'].append(vit_position_ids) + + sequence_status['packed_text_ids'].append(eoi_id) + sequence_status['packed_text_indexes'].append(curr) + curr += 1 + curr_split_len += 1 + + if split_start: + attn_modes.append("full") + sequence_status['packed_position_ids'].extend([curr_rope_id] * curr_split_len) + curr_rope_id += 1 + + if item.get('split_end', True): + split_lens.append(curr_split_len) + sample_lens += curr_split_len + + sequence_status['curr'] = curr + sequence_status['sample_lens'].append(sample_lens) + sequence_status['target_modality_types'].append(last_loss_modality_type or item['modality_type']) + # prepare attention mask + if not self.use_flex: + sequence_status['nested_attention_masks'].append( + prepare_attention_mask_per_sample(split_lens, attn_modes) + ) + else: + sequence_status['split_lens'].extend(split_lens) + sequence_status['attn_modes'].extend(attn_modes) + + return sequence_status + + +class SimpleCustomBatch: + def __init__(self, batch): + data = batch[0] + self.batch_data_indexes = data['batch_data_indexes'] + self.data_resume_state = data.get("data_resume_state") + self.sequence_length = data["sequence_length"] + self.num_samples = data["num_samples"] + self.num_epoch_samples = data.get("num_epoch_samples", data["num_samples"]) + self.sample_lens = data["sample_lens"] + self.target_modality_types = data["target_modality_types"] + self.vae_image_modality_types = data["vae_image_modality_types"] + self.packed_text_ids = data["packed_text_ids"] + self.packed_text_indexes = data["packed_text_indexes"] + self.packed_position_ids = data["packed_position_ids"] + + self.use_flex = "nested_attention_masks" not in data.keys() + + if self.use_flex: + self.split_lens = data["split_lens"] + self.attn_modes = data["attn_modes"] + else: + self.nested_attention_masks = data["nested_attention_masks"] + + if "padded_images" in data.keys(): + self.padded_images = data["padded_images"] + self.patchified_vae_latent_shapes = data["patchified_vae_latent_shapes"] + self.packed_latent_position_ids = data["packed_latent_position_ids"] + self.packed_vae_token_indexes = data["packed_vae_token_indexes"] + + if "packed_vit_tokens" in data.keys(): + self.packed_vit_tokens = data["packed_vit_tokens"] + self.packed_vit_position_ids = data["packed_vit_position_ids"] + self.packed_vit_token_indexes = data["packed_vit_token_indexes"] + self.vit_token_seqlens = data["vit_token_seqlens"] + self.vit_image_modality_types = data["vit_image_modality_types"] + # Per-image (token_h, token_w) for 2D rope_image_info on ViT inputs (B fix) + self.vit_image_token_shapes = data.get("vit_image_token_shapes", []) + + if "packed_timesteps" in data.keys(): + self.packed_timesteps = data["packed_timesteps"] + self.mse_loss_indexes = data["mse_loss_indexes"] + self.mse_loss_modality_ids = data["mse_loss_modality_ids"] + self.mse_loss_route_ids = data["mse_loss_route_ids"] + self.mse_loss_image_ids = data["mse_loss_image_ids"] + self.mse_loss_timesteps = data["mse_loss_timesteps"] + + if "packed_label_ids" in data.keys(): + self.packed_label_ids = data["packed_label_ids"] + self.ce_loss_indexes = data["ce_loss_indexes"] + self.ce_loss_weights = data["ce_loss_weights"] + self.ce_loss_modality_ids = data["ce_loss_modality_ids"] + + def pin_memory(self): + self.packed_text_ids = self.packed_text_ids.pin_memory() + self.packed_text_indexes = self.packed_text_indexes.pin_memory() + self.packed_position_ids = self.packed_position_ids.pin_memory() + + if not self.use_flex: + self.nested_attention_masks = [item.pin_memory() for item in self.nested_attention_masks] + + if hasattr(self, 'padded_images'): + self.padded_images = self.padded_images.pin_memory() + self.packed_vae_token_indexes = self.packed_vae_token_indexes.pin_memory() + self.packed_latent_position_ids = self.packed_latent_position_ids.pin_memory() + + if hasattr(self, 'packed_timesteps'): + self.packed_timesteps = self.packed_timesteps.pin_memory() + self.mse_loss_indexes = self.mse_loss_indexes.pin_memory() + self.mse_loss_modality_ids = self.mse_loss_modality_ids.pin_memory() + self.mse_loss_route_ids = self.mse_loss_route_ids.pin_memory() + self.mse_loss_image_ids = self.mse_loss_image_ids.pin_memory() + self.mse_loss_timesteps = self.mse_loss_timesteps.pin_memory() + + if hasattr(self, 'packed_vit_tokens'): + self.packed_vit_tokens = self.packed_vit_tokens.pin_memory() + self.packed_vit_position_ids = self.packed_vit_position_ids.pin_memory() + self.packed_vit_token_indexes = self.packed_vit_token_indexes.pin_memory() + self.vit_token_seqlens = self.vit_token_seqlens.pin_memory() + + if hasattr(self, 'packed_label_ids'): + self.packed_label_ids = self.packed_label_ids.pin_memory() + self.ce_loss_indexes = self.ce_loss_indexes.pin_memory() + self.ce_loss_weights = self.ce_loss_weights.pin_memory() + self.ce_loss_modality_ids = self.ce_loss_modality_ids.pin_memory() + + return self + + def cuda(self, device): + self.packed_text_ids = self.packed_text_ids.to(device) + self.packed_text_indexes = self.packed_text_indexes.to(device) + self.packed_position_ids = self.packed_position_ids.to(device) + + if not self.use_flex: + self.nested_attention_masks = [item.to(device) for item in self.nested_attention_masks] + + if hasattr(self, 'padded_images'): + self.padded_images = self.padded_images.to(device) + self.packed_vae_token_indexes = self.packed_vae_token_indexes.to(device) + self.packed_latent_position_ids = self.packed_latent_position_ids.to(device) + + if hasattr(self, 'packed_timesteps'): + self.packed_timesteps = self.packed_timesteps.to(device) + self.mse_loss_indexes = self.mse_loss_indexes.to(device) + self.mse_loss_modality_ids = self.mse_loss_modality_ids.to(device) + self.mse_loss_route_ids = self.mse_loss_route_ids.to(device) + self.mse_loss_image_ids = self.mse_loss_image_ids.to(device) + self.mse_loss_timesteps = self.mse_loss_timesteps.to(device) + + if hasattr(self, 'packed_vit_tokens'): + self.packed_vit_tokens = self.packed_vit_tokens.to(device) + self.packed_vit_position_ids = self.packed_vit_position_ids.to(device) + self.packed_vit_token_indexes = self.packed_vit_token_indexes.to(device) + self.vit_token_seqlens = self.vit_token_seqlens.to(device) + + if hasattr(self, 'packed_label_ids'): + self.packed_label_ids = self.packed_label_ids.to(device) + self.ce_loss_indexes = self.ce_loss_indexes.to(device) + self.ce_loss_weights = self.ce_loss_weights.to(device) + self.ce_loss_modality_ids = self.ce_loss_modality_ids.to(device) + + return self + + def to_dict(self): + data = dict( + sequence_length = self.sequence_length, + num_samples = self.num_samples, + num_epoch_samples = self.num_epoch_samples, + sample_lens = self.sample_lens, + target_modality_types = self.target_modality_types, + vae_image_modality_types = self.vae_image_modality_types, + packed_text_ids = self.packed_text_ids, + packed_text_indexes = self.packed_text_indexes, + packed_position_ids = self.packed_position_ids, + batch_data_indexes = self.batch_data_indexes, + data_resume_state = self.data_resume_state, + ) + + if not self.use_flex: + data['nested_attention_masks'] = self.nested_attention_masks + else: + data['split_lens'] = self.split_lens + data['attn_modes'] = self.attn_modes + + if hasattr(self, 'padded_images'): + data['padded_images'] = self.padded_images + data['patchified_vae_latent_shapes'] = self.patchified_vae_latent_shapes + data['packed_latent_position_ids'] = self.packed_latent_position_ids + data['packed_vae_token_indexes'] = self.packed_vae_token_indexes + + if hasattr(self, 'packed_vit_tokens'): + data['packed_vit_tokens'] = self.packed_vit_tokens + data['packed_vit_position_ids'] = self.packed_vit_position_ids + data['packed_vit_token_indexes'] = self.packed_vit_token_indexes + data['vit_token_seqlens'] = self.vit_token_seqlens + data['vit_image_modality_types'] = self.vit_image_modality_types + data['vit_image_token_shapes'] = getattr(self, 'vit_image_token_shapes', []) + + if hasattr(self, 'packed_timesteps'): + data['packed_timesteps'] = self.packed_timesteps + data['mse_loss_indexes'] = self.mse_loss_indexes + data['mse_loss_modality_ids'] = self.mse_loss_modality_ids + data['mse_loss_route_ids'] = self.mse_loss_route_ids + data['mse_loss_image_ids'] = self.mse_loss_image_ids + data['mse_loss_timesteps'] = self.mse_loss_timesteps + + if hasattr(self, 'packed_label_ids'): + data['packed_label_ids'] = self.packed_label_ids + data['ce_loss_indexes'] = self.ce_loss_indexes + data['ce_loss_weights'] = self.ce_loss_weights + data['ce_loss_modality_ids'] = self.ce_loss_modality_ids + + return data + + +def collate_wrapper(): + def collate_fn(batch): + return SimpleCustomBatch(batch) + return collate_fn diff --git a/data/dataset_info.py b/data/dataset_info.py new file mode 100644 index 0000000000000000000000000000000000000000..6706f11ca97846dd893266c49a1fcf71803af61b --- /dev/null +++ b/data/dataset_info.py @@ -0,0 +1,1019 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +from .interleave_datasets import UnifiedEditIterableDataset +from .t2i_dataset import T2IIterableDataset +from .vlm_dataset import SftJSONLIterableDataset, SftParquetIterableDataset +from .interleave_datasets.any2any_dataset import UnifiedAny2AnyIterableDataset +from .interleave_datasets.hunyuan_native_chat_any2any_dataset import ( + HunyuanNativeChatAny2AnyIterableDataset, +) +import torch +import os + + +Any2AnyDatasetClass = ( + HunyuanNativeChatAny2AnyIterableDataset + if os.environ.get("HUNYUAN_NATIVE_CHAT_SERIALIZATION", "0") == "1" + else UnifiedAny2AnyIterableDataset +) + +DATASET_REGISTRY = { + 't2i_pretrain': T2IIterableDataset, + 'vlm_sft': SftJSONLIterableDataset, + 'vlm_sft_parquet': SftParquetIterableDataset, + 'unified_edit': UnifiedEditIterableDataset, + 'unified_any2rgb': Any2AnyDatasetClass, + 'unified_any2depth': Any2AnyDatasetClass, + 'unified_any2normal': Any2AnyDatasetClass, + 'unified_any2caption': Any2AnyDatasetClass, + 'unified_any2det': Any2AnyDatasetClass, + 'unified_any2seg': Any2AnyDatasetClass, + 'unified_any2grounding': Any2AnyDatasetClass, + 'unified_any2canny': Any2AnyDatasetClass, + 'unified_any2dino': Any2AnyDatasetClass, + 'unified_any2dinolocal': Any2AnyDatasetClass, + 'unified_any2clip': Any2AnyDatasetClass, + 'unified_any2imagebind': Any2AnyDatasetClass, + 'unified_any2imagebindlocal': Any2AnyDatasetClass, + 'unified_any2cocodet': Any2AnyDatasetClass, + 'unified_any2samseg': Any2AnyDatasetClass, + 'unified_any2samedge': Any2AnyDatasetClass, +} + + +DATASET_INFO = { + 't2i_pretrain': { + 't2i': { + 'data_dir': './datasets/bagel_example/t2i', # path of the parquet files + 'num_files': 10, # number of data units to be sharded across all ranks and workers + 'num_total_samples': 1000, # number of total samples in the dataset + }, + }, + 'unified_edit':{ + 'seedxedit_multi': { + 'data_dir': './datasets/bagel_example/editing/seedxedit_multi', + 'num_files': 10, + 'num_total_samples': 1000, + "parquet_info_path": './datasets/bagel_example/editing/parquet_info/seedxedit_multi.json', # information of the parquet files + }, + }, + 'vlm_sft': { + 'text_only_benchmark': { + 'data_dir': './datasets/text_only_benchmark/images', + 'jsonl_path': './datasets/text_only_benchmark/label/labels.jsonl', + }, + 'ai2d(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/ai2d(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/ai2d(cauldron,llava_format)/label/labels.jsonl', + }, + 'ai2d(gpt4v)': { + 'data_dir': './datasets/llava_onevision_vqa/ai2d(gpt4v)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/ai2d(gpt4v)/label/labels.jsonl', + }, + 'ai2d(internvl)': { + 'data_dir': './datasets/llava_onevision_vqa/ai2d(internvl)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/ai2d(internvl)/label/labels.jsonl', + }, + 'allava_instruct_laion4v': { + 'data_dir': './datasets/llava_onevision_vqa/allava_instruct_laion4v/images', + 'jsonl_path': './datasets/llava_onevision_vqa/allava_instruct_laion4v/label/labels.jsonl', + }, + 'allava_instruct_vflan4v': { + 'data_dir': './datasets/llava_onevision_vqa/allava_instruct_vflan4v/images', + 'jsonl_path': './datasets/llava_onevision_vqa/allava_instruct_vflan4v/label/labels.jsonl', + }, + 'aokvqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/aokvqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/aokvqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'chart2text(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/chart2text(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/chart2text(cauldron)/label/labels.jsonl', + }, + 'chartqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/chartqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/chartqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'chrome_writting': { + 'data_dir': './datasets/llava_onevision_vqa/chrome_writting/images', + 'jsonl_path': './datasets/llava_onevision_vqa/chrome_writting/label/labels.jsonl', + }, + 'CLEVR-Math(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/CLEVR-Math(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/CLEVR-Math(MathV360K)/label/labels.jsonl', + }, + 'clevr(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/clevr(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/clevr(cauldron,llava_format)/label/labels.jsonl', + }, + 'diagram_image_to_text(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/diagram_image_to_text(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/diagram_image_to_text(cauldron)/label/labels.jsonl', + }, + 'dvqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/dvqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/dvqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'Evol-Instruct-GPT4-Turbo': { + 'data_dir': './datasets/llava_onevision_vqa/Evol-Instruct-GPT4-Turbo/images', + 'jsonl_path': './datasets/llava_onevision_vqa/Evol-Instruct-GPT4-Turbo/label/labels.jsonl', + }, + 'figureqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/figureqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/figureqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'FigureQA(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/FigureQA(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/FigureQA(MathV360K)/label/labels.jsonl', + }, + 'geo170k(align)': { + 'data_dir': './datasets/llava_onevision_vqa/geo170k(align)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/geo170k(align)/label/labels.jsonl', + }, + 'geo170k(qa)': { + 'data_dir': './datasets/llava_onevision_vqa/geo170k(qa)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/geo170k(qa)/label/labels.jsonl', + }, + 'geo3k': { + 'data_dir': './datasets/llava_onevision_vqa/geo3k/images', + 'jsonl_path': './datasets/llava_onevision_vqa/geo3k/label/labels.jsonl', + }, + 'Geometry3K(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/Geometry3K(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/Geometry3K(MathV360K)/label/labels.jsonl', + }, + 'geomverse(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/geomverse(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/geomverse(cauldron)/label/labels.jsonl', + }, + 'GeoQA+(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/GeoQA+(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/GeoQA+(MathV360K)/label/labels.jsonl', + }, + 'GEOS(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/GEOS(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/GEOS(MathV360K)/label/labels.jsonl', + }, + 'hateful_memes(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/hateful_memes(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/hateful_memes(cauldron,llava_format)/label/labels.jsonl', + }, + 'hitab(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/hitab(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/hitab(cauldron,llava_format)/label/labels.jsonl', + }, + 'hme100k': { + 'data_dir': './datasets/llava_onevision_vqa/hme100k/images', + 'jsonl_path': './datasets/llava_onevision_vqa/hme100k/label/labels.jsonl', + }, + 'iam(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/iam(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/iam(cauldron)/label/labels.jsonl', + }, + 'iconqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/iconqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/iconqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'IconQA(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/IconQA(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/IconQA(MathV360K)/label/labels.jsonl', + }, + 'iiit5k': { + 'data_dir': './datasets/llava_onevision_vqa/iiit5k/images', + 'jsonl_path': './datasets/llava_onevision_vqa/iiit5k/label/labels.jsonl', + }, + 'image_textualization(filtered)': { + 'data_dir': './datasets/llava_onevision_vqa/image_textualization(filtered)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/image_textualization(filtered)/label/labels.jsonl', + }, + 'infographic_vqa': { + 'data_dir': './datasets/llava_onevision_vqa/infographic_vqa/images', + 'jsonl_path': './datasets/llava_onevision_vqa/infographic_vqa/label/labels.jsonl', + }, + 'infographic_vqa_llava_format': { + 'data_dir': './datasets/llava_onevision_vqa/infographic_vqa_llava_format/images', + 'jsonl_path': './datasets/llava_onevision_vqa/infographic_vqa_llava_format/label/labels.jsonl', + }, + 'infographic(gpt4v)': { + 'data_dir': './datasets/llava_onevision_vqa/infographic(gpt4v)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/infographic(gpt4v)/label/labels.jsonl', + }, + 'intergps(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/intergps(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/intergps(cauldron,llava_format)/label/labels.jsonl', + }, + 'k12_printing': { + 'data_dir': './datasets/llava_onevision_vqa/k12_printing/images', + 'jsonl_path': './datasets/llava_onevision_vqa/k12_printing/label/labels.jsonl', + }, + 'llava_wild_4v_12k_filtered': { + 'data_dir': './datasets/llava_onevision_vqa/llava_wild_4v_12k_filtered/images', + 'jsonl_path': './datasets/llava_onevision_vqa/llava_wild_4v_12k_filtered/label/labels.jsonl', + }, + 'llava_wild_4v_39k_filtered': { + 'data_dir': './datasets/llava_onevision_vqa/llava_wild_4v_39k_filtered/images', + 'jsonl_path': './datasets/llava_onevision_vqa/llava_wild_4v_39k_filtered/label/labels.jsonl', + }, + 'llavar_gpt4_20k': { + 'data_dir': './datasets/llava_onevision_vqa/llavar_gpt4_20k/images', + 'jsonl_path': './datasets/llava_onevision_vqa/llavar_gpt4_20k/label/labels.jsonl', + }, + 'lrv_chart': { + 'data_dir': './datasets/llava_onevision_vqa/lrv_chart/images', + 'jsonl_path': './datasets/llava_onevision_vqa/lrv_chart/label/labels.jsonl', + }, + 'lrv_normal(filtered)': { + 'data_dir': './datasets/llava_onevision_vqa/lrv_normal(filtered)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/lrv_normal(filtered)/label/labels.jsonl', + }, + 'magpie_pro(l3_80b_mt)': { + 'data_dir': './datasets/llava_onevision_vqa/magpie_pro(l3_80b_mt)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/magpie_pro(l3_80b_mt)/label/labels.jsonl', + }, + 'magpie_pro(l3_80b_st)': { + 'data_dir': './datasets/llava_onevision_vqa/magpie_pro(l3_80b_st)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/magpie_pro(l3_80b_st)/label/labels.jsonl', + }, + 'magpie_pro(qwen2_72b_st)': { + 'data_dir': './datasets/llava_onevision_vqa/magpie_pro(qwen2_72b_st)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/magpie_pro(qwen2_72b_st)/label/labels.jsonl', + }, + 'mapqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/mapqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/mapqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'MapQA(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/MapQA(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/MapQA(MathV360K)/label/labels.jsonl', + }, + 'mathqa': { + 'data_dir': './datasets/llava_onevision_vqa/mathqa/images', + 'jsonl_path': './datasets/llava_onevision_vqa/mathqa/label/labels.jsonl', + }, + 'MathV360K_TQA': { + 'data_dir': './datasets/llava_onevision_vqa/MathV360K_TQA/images', + 'jsonl_path': './datasets/llava_onevision_vqa/MathV360K_TQA/label/labels.jsonl', + }, + 'MathV360K_VQA-AS': { + 'data_dir': './datasets/llava_onevision_vqa/MathV360K_VQA-AS/images', + 'jsonl_path': './datasets/llava_onevision_vqa/MathV360K_VQA-AS/label/labels.jsonl', + }, + 'MathV360K_VQA-RAD': { + 'data_dir': './datasets/llava_onevision_vqa/MathV360K_VQA-RAD/images', + 'jsonl_path': './datasets/llava_onevision_vqa/MathV360K_VQA-RAD/label/labels.jsonl', + }, + 'mavis_math_metagen': { + 'data_dir': './datasets/llava_onevision_vqa/mavis_math_metagen/images', + 'jsonl_path': './datasets/llava_onevision_vqa/mavis_math_metagen/label/labels.jsonl', + }, + 'mavis_math_rule_geo': { + 'data_dir': './datasets/llava_onevision_vqa/mavis_math_rule_geo/images', + 'jsonl_path': './datasets/llava_onevision_vqa/mavis_math_rule_geo/label/labels.jsonl', + }, + 'multihiertt(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/multihiertt(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/multihiertt(cauldron)/label/labels.jsonl', + }, + 'orand_car_a': { + 'data_dir': './datasets/llava_onevision_vqa/orand_car_a/images', + 'jsonl_path': './datasets/llava_onevision_vqa/orand_car_a/label/labels.jsonl', + }, + 'PMC-VQA(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/PMC-VQA(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/PMC-VQA(MathV360K)/label/labels.jsonl', + }, + 'raven(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/raven(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/raven(cauldron)/label/labels.jsonl', + }, + 'rendered_text(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/rendered_text(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/rendered_text(cauldron)/label/labels.jsonl', + }, + 'robut_sqa(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/robut_sqa(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/robut_sqa(cauldron)/label/labels.jsonl', + }, + 'robut_wikisql(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/robut_wikisql(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/robut_wikisql(cauldron)/label/labels.jsonl', + }, + 'robut_wtq(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/robut_wtq(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/robut_wtq(cauldron,llava_format)/label/labels.jsonl', + }, + 'scienceqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/scienceqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/scienceqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'scienceqa(nona_context)': { + 'data_dir': './datasets/llava_onevision_vqa/scienceqa(nona_context)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/scienceqa(nona_context)/label/labels.jsonl', + }, + 'screen2words(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/screen2words(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/screen2words(cauldron)/label/labels.jsonl', + }, + 'sharegpt4o': { + 'data_dir': './datasets/llava_onevision_vqa/sharegpt4o/images', + 'jsonl_path': './datasets/llava_onevision_vqa/sharegpt4o/label/labels.jsonl', + }, + 'sharegpt4v(coco)': { + 'data_dir': './datasets/llava_onevision_vqa/sharegpt4v(coco)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/sharegpt4v(coco)/label/labels.jsonl', + }, + 'sharegpt4v(knowledge)': { + 'data_dir': './datasets/llava_onevision_vqa/sharegpt4v(knowledge)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/sharegpt4v(knowledge)/label/labels.jsonl', + }, + 'sharegpt4v(llava)': { + 'data_dir': './datasets/llava_onevision_vqa/sharegpt4v(llava)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/sharegpt4v(llava)/label/labels.jsonl', + }, + 'sharegpt4v(sam)': { + 'data_dir': './datasets/llava_onevision_vqa/sharegpt4v(sam)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/sharegpt4v(sam)/label/labels.jsonl', + }, + 'sroie': { + 'data_dir': './datasets/llava_onevision_vqa/sroie/images', + 'jsonl_path': './datasets/llava_onevision_vqa/sroie/label/labels.jsonl', + }, + 'st_vqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/st_vqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/st_vqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'Super-CLEVR(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/Super-CLEVR(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/Super-CLEVR(MathV360K)/label/labels.jsonl', + }, + 'tabmwp(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/tabmwp(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/tabmwp(cauldron)/label/labels.jsonl', + }, + 'TabMWP(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/TabMWP(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/TabMWP(MathV360K)/label/labels.jsonl', + }, + 'tallyqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/tallyqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/tallyqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'textcaps': { + 'data_dir': './datasets/llava_onevision_vqa/textcaps/images', + 'jsonl_path': './datasets/llava_onevision_vqa/textcaps/label/labels.jsonl', + }, + 'textocr(gpt4v)': { + 'data_dir': './datasets/llava_onevision_vqa/textocr(gpt4v)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/textocr(gpt4v)/label/labels.jsonl', + }, + 'tqa(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/tqa(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/tqa(cauldron,llava_format)/label/labels.jsonl', + }, + 'UniGeo(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/UniGeo(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/UniGeo(MathV360K)/label/labels.jsonl', + }, + 'ureader_cap': { + 'data_dir': './datasets/llava_onevision_vqa/ureader_cap/images', + 'jsonl_path': './datasets/llava_onevision_vqa/ureader_cap/label/labels.jsonl', + }, + 'ureader_ie': { + 'data_dir': './datasets/llava_onevision_vqa/ureader_ie/images', + 'jsonl_path': './datasets/llava_onevision_vqa/ureader_ie/label/labels.jsonl', + }, + 'vision_flan(filtered)': { + 'data_dir': './datasets/llava_onevision_vqa/vision_flan(filtered)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/vision_flan(filtered)/label/labels.jsonl', + }, + 'vistext(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/vistext(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/vistext(cauldron)/label/labels.jsonl', + }, + 'visual7w(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/visual7w(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/visual7w(cauldron,llava_format)/label/labels.jsonl', + }, + 'visualmrc(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/visualmrc(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/visualmrc(cauldron)/label/labels.jsonl', + }, + 'VisualWebInstruct(filtered)': { + 'data_dir': './datasets/llava_onevision_vqa/VisualWebInstruct(filtered)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/VisualWebInstruct(filtered)/label/labels.jsonl', + }, + 'VizWiz(MathV360K)': { + 'data_dir': './datasets/llava_onevision_vqa/VizWiz(MathV360K)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/VizWiz(MathV360K)/label/labels.jsonl', + }, + 'vqarad(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/vqarad(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/vqarad(cauldron,llava_format)/label/labels.jsonl', + }, + 'vsr(cauldron,llava_format)': { + 'data_dir': './datasets/llava_onevision_vqa/vsr(cauldron,llava_format)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/vsr(cauldron,llava_format)/label/labels.jsonl', + }, + 'websight(cauldron)': { + 'data_dir': './datasets/llava_onevision_vqa/websight(cauldron)/images', + 'jsonl_path': './datasets/llava_onevision_vqa/websight(cauldron)/label/labels.jsonl', + }, + }, + # vlm_sft bundled into parquet shards (streaming-friendly, S3-ready). + # Written by data/any2any_preprocess/generate_parquet_vlm_sft.py; sample + # selection (shuffle_lines + num_used_data) is baked in at conversion. + 'vlm_sft_parquet': { + 'llava_onevision_vqa': { + 'data_dir': './datasets/llava_onevision_vqa_parquet/train', + 'parquet_info_path': './datasets/llava_onevision_vqa_parquet/parquet_info/llava_onevision_vqa.json', + }, + }, + 'unified_any2rgb': { + 'blip3o_example_toydataset': { + 'data_dir': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train/blip3o_example_toydataset.json', + }, + 'blip3o_example_toydataset_13modality_clip448_imagebind': { + 'data_dir': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train/blip3o_example_toydataset.json', + }, + 'blip3o':{ + 'data_dir': './datasets/blip3o/parquet', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2depth': { + 'blip3o_example_toydataset': { + 'data_dir': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train/blip3o_example_toydataset.json', + }, + 'blip3o':{ + 'data_dir': './datasets/blip3o/parquet', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2normal': { + 'blip3o_example_toydataset': { + 'data_dir': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train/blip3o_example_toydataset.json', + }, + 'blip3o':{ + 'data_dir': './datasets/blip3o/parquet', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2caption': { + 'blip3o_example_toydataset': { + 'data_dir': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train/blip3o_example_toydataset.json', + }, + 'blip3o_example_toydataset_13modality_clip448_imagebind': { + 'data_dir': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train/blip3o_example_toydataset.json', + }, + 'blip3o':{ + 'data_dir': './datasets/blip3o/parquet', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2det': { + 'blip3o_rgb_caption_depth_normal_det_seg':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg.json', + } + }, + 'unified_any2seg': { + 'blip3o_example_toydataset': { + 'data_dir': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train/blip3o_example_toydataset.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2grounding': { + 'blip3o_example_toydataset': { + 'data_dir': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train/blip3o_example_toydataset.json', + }, + 'blip3o_example_toydataset_13modality_clip448_imagebind': { + 'data_dir': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train/blip3o_example_toydataset.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding', + 'num_files': 1000, + 'num_total_samples': 11_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding2.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 1000, + 'num_total_samples': 11_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding2_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 1000, + 'num_total_samples': 11_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding2_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2canny': { + 'blip3o_example_toydataset': { + 'data_dir': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train/blip3o_example_toydataset.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2dino': { + 'blip3o_example_toydataset': { + 'data_dir': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global/train/blip3o_example_toydataset.json', + }, + 'blip3o_example_toydataset_13modality_clip448_imagebind': { + 'data_dir': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train/blip3o_example_toydataset.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2dinolocal': { + 'blip3o_example_toydataset_13modality_clip448_imagebind': { + 'data_dir': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train/blip3o_example_toydataset.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2clip': { + 'blip3o_example_toydataset_13modality_clip448_imagebind': { + 'data_dir': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train/blip3o_example_toydataset.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2imagebind': { + 'blip3o_example_toydataset_13modality_clip448_imagebind': { + 'data_dir': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train/blip3o_example_toydataset.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + }, + 'unified_any2imagebindlocal': { + 'blip3o_example_toydataset_13modality_clip448_imagebind': { + 'data_dir': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train', + 'num_files': 1, + 'num_total_samples': 1000, + 'parquet_info_path': './datasets/blip3o/parquet_toy_13modality_clip448_imagebind/train/blip3o_example_toydataset.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind', + 'num_files': 2891, + 'num_total_samples': 25_000_000, + 'parquet_info_path': './datasets/blip3o/parquet_info/blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind.json', + }, + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind_aligned':{ + 'data_dir': './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned', + 'num_files': 1000, + 'num_total_samples': 3_899_886, + 'parquet_info_path': './datasets/blip3o/parquet_info/parquet_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global_clip448_imagebind_aligned.json', + } + } +} + + +# ── 16-modality parquet (13 old + samseg/samedge/cocodet). Superset of the old +# parquet → registered under every modality key the new run uses. Additive: does +# not touch existing dataset entries. ──────────────────────────────────────── +_PARQUET_16MOD_NAME = ( + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_clip448_imagebind' + '_samseg_samedge_cocodet' +) +_PARQUET_16MOD_INFO = { + 'data_dir': ( + './datasets/blip3o/parquet_rgb_caption_depth_normal_det_seg_grounding' + '_canny_dino_global_clip448_imagebind_samseg_samedge_cocodet' + ), + 'num_files': 2888, # 2891 minus 3 held-out val files (parquet_16mod_VAL_heldout) + 'num_total_samples': 25_000_000, + 'parquet_info_path': ( + './datasets/blip3o/parquet_info/' + 'blip3o_rgb_caption_depth_normal_det_seg_grounding_canny_dino_global' + '_clip448_imagebind_samseg_samedge_cocodet.json' + ), +} +for _mod_key in [ + 'unified_any2rgb', 'unified_any2caption', 'unified_any2depth', + 'unified_any2normal', 'unified_any2seg', 'unified_any2canny', + 'unified_any2grounding', 'unified_any2dino', 'unified_any2dinolocal', + 'unified_any2clip', 'unified_any2imagebind', 'unified_any2imagebindlocal', + 'unified_any2cocodet', 'unified_any2samseg', 'unified_any2samedge', +]: + DATASET_INFO.setdefault(_mod_key, {})[_PARQUET_16MOD_NAME] = dict(_PARQUET_16MOD_INFO) + + +# MODALITY_STATS = { +# "rgb": { +# "mean": [ +# 0.09998548775911331, -0.25365808606147766, 0.02537657506763935, 0.15525108575820923, +# -0.13307523727416992, 0.18412069976329803, -0.3696898818016052, 0.1216680109500885, +# 0.07324755936861038, 0.011612555012106895, 0.17749321460723877, 0.009583432227373123, +# 0.006619213614612818, -0.1372869461774826, -0.34581223130226135, -0.08381273597478867 +# ], +# "std": [ +# 0.6712213754653931, 1.1496732234954834, 0.6890255212783813, 0.48065587878227234, +# 0.5058963894844055, 0.5045602917671204, 0.964796781539917, 0.7499234676361084, +# 0.60835862159729, 0.8583494424819946, 0.5590784549713135, 0.6568386554718018, +# 0.8276281356811523, 0.8293890357017517, 0.7076113820075989, 0.8054326176643372 +# ] +# }, +# "depth": { +# "mean": [ +# 0.3062567710876465, -0.9071211814880371, -0.5659458041191101, -0.027933871373534203, +# 0.13497579097747803, 1.6215254068374634, -1.7268935441970825, 1.1100306510925293, +# 0.06933767348527908, -0.5322779417037964, -0.2097727358341217, 0.07714101672172546, +# -1.3442918062210083, -0.46783745288848877, -0.31114235520362854, 0.9852880239486694 +# ], +# "std": [ +# 0.4548855125904083, 2.0455949306488037, 0.40026405453681946, 0.34950074553489685, +# 0.40104442834854126, 0.47336098551750183, 1.658141851425171, 1.2504311800003052, +# 0.3990429639816284, 1.1091442108154297, 0.724875271320343, 0.8045597672462463, +# 1.4909602403640747, 1.501410961151123, 1.1055831909179688, 1.3423223495483398 +# ] +# }, +# "normal": { +# "mean": [ +# 1.1839842796325684, 0.8041657209396362, -0.391467422246933, 0.5322199463844299, +# -0.5196242928504944, 0.537630021572113, 0.4950917363166809, -0.8294451236724854, +# 1.2865995168685913, -1.2402032613754272, 0.2119874656200409, 0.4859861135482788, +# 0.43453630805015564, -1.550497055053711, -0.6797669529914856, -0.09787978231906891 +# ], +# "std": [ +# 0.6379154920578003, 0.5921596884727478, 1.1566283702850342, 0.6052563786506653, +# 0.6098771095275879, 0.5771185755729675, 0.5548882484436035, 0.42952394485473633, +# 0.7510039806365967, 1.1233150959014893, 0.7662065625190735, 0.6668922305107117, +# 0.5062761306762695, 1.2029993534088135, 0.9624990820884705, 0.5272090435028076 +# ] +# } +# } + + +MODALITY_STATS = { + "depth": { + "mean": [ + 0.28762707114219666, -1.011340856552124, -0.5465618371963501, -0.01756225898861885, + 0.12532611191272736, 1.56802499294281, -1.7659778594970703, 1.1437808275222778, + 0.0657510980963707, -0.5864744186401367, -0.2622603476047516, 0.04382546991109848, + -1.4009149074554443, -0.35514819622039795, -0.2363666445016861, 1.04072904586792 + ], + "std": [ + 0.4532972276210785, 2.055128812789917, 0.397210031747818, 0.34771019220352173, + 0.4028947949409485, 0.47736671566963196, 1.6445382833480835, 1.2453844547271729, + 0.4030587077140808, 1.1071559190750122, 0.7346603870391846, 0.809998095035553, + 1.4902814626693726, 1.511523723602295, 1.1147352457046509, 1.346556544303894 + ] + }, + "normal": { + "mean": [ + 1.1103582382202148, 0.7585429549217224, -0.4633699059486389, 0.4460155665874481, + -0.4614908993244171, 0.5055513978004456, 0.5129532217979431, -0.8317145705223083, + 1.1523557901382446, -1.0965044498443604, 0.29184550046920776, 0.3881677985191345, + 0.41409650444984436, -1.3409103155136108, -0.7599201202392578, -0.14071156084537506 + ], + "std": [ + 0.658498227596283, 0.6019635200500488, 1.2136141061782837, 0.644258439540863, + 0.656324028968811, 0.5987396836280823, 0.5700253844261169, 0.4413583278656006, + 0.8087592124938965, 1.2170354127883911, 0.7942348718643188, 0.6947795748710632, + 0.5312002897262573, 1.2880762815475464, 1.0215877294540405, 0.5333302021026611 + ] + } +} + + +def normalize_latents_by_modality(latents, modality_types, device): + """ + Normalize VAE latents by modality type. + Supports rgb, depth, and normal modalities. + + Args: + latents: torch.Tensor of shape [B, C, H, W] + modality_types: List[str] of length B indicating modality for each sample + device: torch device + + Returns: + Normalized latents tensor + """ + if not MODALITY_STATS: + return latents + + normalized_latents = latents.clone() + + for i, modality in enumerate(modality_types): + if modality in MODALITY_STATS: + # Get mean and std for this modality + mean = torch.tensor(MODALITY_STATS[modality]["mean"], device=device, dtype=latents.dtype) + std = torch.tensor(MODALITY_STATS[modality]["std"], device=device, dtype=latents.dtype) + + # Reshape to [C, 1, 1] for broadcasting + mean = mean.view(-1, 1, 1) + std = std.view(-1, 1, 1) + + # Normalize: (x - mean) / std + normalized_latents[i] = (latents[i] - mean) / std + + return normalized_latents + +def denormalize_latents_by_modality(latents, modality_type, device): + """ + Denormalize VAE latents by modality type. + Reverses the normalization applied during training for rgb, depth, and normal. + + Args: + latents: torch.Tensor of shape [B, C, H, W] - normalized latents from model + modality_type: str indicating modality for the sample + device: torch device + + Returns: + Denormalized latents tensor ready for VAE decoder + """ + if not MODALITY_STATS or modality_type not in MODALITY_STATS: + return latents + + # Get mean and std for this modality + mean = torch.tensor(MODALITY_STATS[modality_type]["mean"], device=device, dtype=latents.dtype) + std = torch.tensor(MODALITY_STATS[modality_type]["std"], device=device, dtype=latents.dtype) + + # Reshape to [C, 1, 1] for broadcasting + mean = mean.view(-1, 1, 1) + std = std.view(-1, 1, 1) + + # Denormalize: x * std + mean (reverse of normalization) + denormalized_latents = latents * std + mean + + return denormalized_latents diff --git a/data/distributed_iterable_dataset.py b/data/distributed_iterable_dataset.py new file mode 100644 index 0000000000000000000000000000000000000000..65668a4b97b7824caee2a6f02ce1e0999238b39c --- /dev/null +++ b/data/distributed_iterable_dataset.py @@ -0,0 +1,58 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +import random +import torch + + +class DistributedIterableDataset(torch.utils.data.IterableDataset): + def __init__(self, dataset_name, local_rank=0, world_size=1, num_workers=8): + self.dataset_name = dataset_name + self.local_rank = local_rank + self.world_size = world_size + self.num_workers = num_workers + self.rng = random.Random() + self.data_paths = None + + def get_data_paths(self, *args, **kwargs): + raise NotImplementedError + + def set_epoch(self, seed=42): + if self.data_paths is None: + return + + if isinstance(self.data_paths[0], tuple): + data_paths = sorted(self.data_paths, key=lambda x: (x[0], x[1])) + elif isinstance(self.data_paths[0], str): + data_paths = sorted(self.data_paths) + else: + raise ValueError(f"Unknown data_paths type: {type(self.data_paths[0])}") + + self.rng.seed(seed) + self.rng.shuffle(data_paths) + + num_files_per_rank = len(data_paths) // self.world_size + local_start = self.local_rank * num_files_per_rank + local_end = (self.local_rank + 1) * num_files_per_rank + self.num_files_per_rank = num_files_per_rank + self.data_paths_per_rank = data_paths[local_start:local_end] + + def get_data_paths_per_worker(self): + if self.data_paths is None: + return None + + info = torch.utils.data.get_worker_info() + if info is None: + # Single worker: Use all files assigned to the rank + return self.data_paths_per_rank, 0 + + worker_id = info.id + num_files_per_worker = self.num_files_per_rank // info.num_workers + start = num_files_per_worker * worker_id + end = num_files_per_worker * (worker_id + 1) + data_paths_per_worker = self.data_paths_per_rank[start:end] + + return data_paths_per_worker[::-1], worker_id + + def __iter__(self): + raise NotImplementedError diff --git a/data/generate_text_benchmark.py b/data/generate_text_benchmark.py new file mode 100644 index 0000000000000000000000000000000000000000..2de2ca29630b1feec42c5c0061d06c31df786fe5 --- /dev/null +++ b/data/generate_text_benchmark.py @@ -0,0 +1,109 @@ +#!/usr/bin/env python3 +"""Generate a synthetic text-only JSONL benchmark dataset. + +Usage: + python data/generate_text_benchmark.py + python data/generate_text_benchmark.py --num-samples 200000 --output datasets/text_only_benchmark/label/labels.jsonl + +Each record has no 'image' key so SftJSONLIterableDataset treats it as pure text, +which is what we want for text-only throughput benchmarking. +""" + +import argparse +import json +import os +import random + +# Topic pool for varied question/answer generation +TOPICS = [ + ("mathematics", "Explain how gradient descent works in machine learning.", + "Gradient descent is an optimization algorithm used to minimize a loss function by iteratively moving in the direction of steepest descent. Starting from an initial parameter vector, we compute the gradient of the loss with respect to each parameter, then update the parameters by subtracting a small multiple (the learning rate) of the gradient. This process repeats until convergence. Variants include stochastic gradient descent, which uses a single sample per update, and mini-batch gradient descent, which uses a small subset. Adaptive methods like Adam adjust the learning rate per parameter using estimates of first and second moments of the gradients."), + ("science", "What is the relationship between entropy and information?", + "Entropy in information theory, introduced by Claude Shannon, quantifies the average uncertainty or information content of a random variable. For a discrete distribution with probabilities p_i, Shannon entropy is H = -sum(p_i log p_i). High entropy means the outcomes are more unpredictable and each observation carries more information. This parallels thermodynamic entropy, which measures the number of microstates compatible with a macrostate. The connection runs deep: both measure the spread or disorder of a distribution. In data compression, entropy gives a lower bound on the average number of bits needed to encode messages from a source."), + ("history", "Describe the main causes of the First World War.", + "The First World War emerged from a complex interplay of factors. Long-term causes included the system of European alliances dividing the continent into two armed camps, intense nationalism especially in the Balkans, imperial competition among European powers, and a massive arms race particularly in naval power between Britain and Germany. The immediate trigger was the assassination of Archduke Franz Ferdinand of Austria-Hungary in Sarajevo on June 28, 1914, by a Bosnian Serb nationalist. Austria-Hungary's ultimatum to Serbia, Russia's mobilization in defense of Serbia, Germany's declaration of war on Russia, and the subsequent chain of alliance obligations drew all major European powers into conflict within weeks."), + ("technology", "How does a transformer neural network process sequences?", + "Transformer networks process sequences through self-attention mechanisms that allow each token to attend to every other token in the input. The input is first converted to embeddings and augmented with positional encodings to preserve order information. Each transformer layer applies multi-head self-attention, which computes query, key, and value projections for all tokens simultaneously, then computes attention weights as scaled dot products between queries and keys, applies softmax normalization, and aggregates values weighted by these scores. A feed-forward network follows each attention block. Residual connections and layer normalization stabilize training. This parallel processing of all positions simultaneously makes transformers highly efficient on modern hardware compared to recurrent architectures."), + ("philosophy", "What is the hard problem of consciousness?", + "The hard problem of consciousness, articulated by philosopher David Chalmers, concerns why physical processes in the brain give rise to subjective experience. The easy problems of consciousness involve explaining cognitive functions like attention, memory, and behavioral control, which seem tractable through neuroscience. The hard problem asks why there is something it is like to be a conscious creature at all. Why does neural activity produce qualia, the felt quality of experiences like the redness of red or the painfulness of pain? Physicalist approaches attempt to reduce consciousness to brain states, while dualists argue mind is irreducible to matter. Illusionists claim our intuitions about qualia are themselves mistaken."), + ("biology", "Explain the process of DNA replication.", + "DNA replication is the process by which a cell copies its genome before division. It begins at specific sequences called origins of replication. The enzyme helicase unwinds the double helix by breaking hydrogen bonds between base pairs, creating a replication fork. Single-strand binding proteins stabilize the unwound strands. Primase synthesizes short RNA primers to provide a starting point for DNA polymerase. DNA polymerase III then extends the new strand in the 5' to 3' direction, reading the template 3' to 5'. Since both strands must be replicated but polymerase can only work in one direction, one strand is synthesized continuously (leading strand) and the other discontinuously in Okazaki fragments (lagging strand). RNA primers are later replaced with DNA and fragments joined by ligase."), + ("economics", "What is the efficient market hypothesis?", + "The efficient market hypothesis (EMH), developed by Eugene Fama, states that asset prices fully reflect all available information. In the weak form, prices incorporate all historical price data, making technical analysis unprofitable. In the semi-strong form, prices reflect all publicly available information including financial statements and news, making fundamental analysis unable to generate consistent excess returns. In the strong form, prices even incorporate private insider information. EMH implies that consistently beating the market through stock picking is impossible without taking on additional risk. Critics point to documented anomalies like momentum effects, value premiums, and market bubbles as evidence against strict EMH. Behavioral finance offers alternative explanations based on investor psychology and cognitive biases."), + ("physics", "How does quantum entanglement work?", + "Quantum entanglement occurs when two or more particles become correlated in such a way that the quantum state of each particle cannot be described independently of the others, regardless of the distance separating them. When particles interact or are created together under certain conditions, they can form an entangled state. Measuring a property of one particle instantly determines the corresponding property of its entangled partner. Einstein called this spooky action at a distance and argued it implied quantum mechanics was incomplete. Bell's theorem showed that correlations in entangled systems cannot be explained by local hidden variables, and subsequent experiments confirmed quantum mechanical predictions. Entanglement does not allow faster-than-light communication because the measurement outcomes are random; only by comparing results classically can the correlation be seen."), + ("literature", "What are the major themes in Dostoevsky's Crime and Punishment?", + "Crime and Punishment explores several interconnected themes. The central theme is the psychological burden of guilt and the impossibility of escaping moral consequences. Raskolnikov's theory that extraordinary men are above conventional morality and may commit crimes for higher purposes is systematically dismantled through his suffering. The novel examines nihilism and its failure as a guiding philosophy. Redemption through suffering is another major theme, influenced by Orthodox Christian values. The contrast between rational theories and human emotional reality runs throughout. Social conditions in St. Petersburg, poverty, and class inequality provide the backdrop and partially explain characters' desperation. The novel also explores compassion as a transformative force, embodied in Sonya, whose faith and love ultimately reach Raskolnikov."), + ("computer science", "Explain the CAP theorem in distributed systems.", + "The CAP theorem, proved by Eric Brewer, states that a distributed data store can provide at most two of three guarantees simultaneously: Consistency (every read receives the most recent write or an error), Availability (every request receives a non-error response, though it may not be the most recent), and Partition tolerance (the system continues operating despite network partitions dropping messages between nodes). Since network partitions are inevitable in real distributed systems, the practical choice is between consistency and availability during a partition. CP systems (like HBase, Zookeeper) choose consistency, potentially refusing requests during partitions. AP systems (like Cassandra, CouchDB) remain available but may return stale data. The theorem applies only during partition events; normal operation can achieve both consistency and availability."), +] + +ANSWER_EXTENSIONS = [ + " Furthermore, it is worth noting that this concept has significant practical implications in modern applications.", + " Research in this area continues to evolve, with recent advances challenging some earlier assumptions.", + " Understanding this requires familiarity with related concepts that form the theoretical foundation.", + " Empirical evidence from numerous studies supports the theoretical framework outlined here.", + " The historical development of this idea reflects broader intellectual trends of the period.", + " Practical applications of this principle can be found across many domains and disciplines.", + " Critics have raised important objections that have led to refinements in the standard account.", + " The mathematical formalization of this concept provides precision lacking in intuitive descriptions.", + " Cross-disciplinary connections to adjacent fields have proven particularly fruitful.", + " Ongoing debates in the field center on questions that remain open to investigation.", +] + + +def generate_sample(idx: int, rng: random.Random) -> dict: + topic_idx = idx % len(TOPICS) + _, question, base_answer = TOPICS[topic_idx] + + # Vary questions slightly + question_prefix = rng.choice(["", "Please ", "Can you ", ""]) + question_suffix = rng.choice(["", " Please be detailed.", " Explain thoroughly.", ""]) + human_text = question_prefix + question + question_suffix + + # Vary answers by appending extensions to hit ~400-600 tokens + answer = base_answer + num_extensions = rng.randint(1, 3) + extensions = rng.sample(ANSWER_EXTENSIONS, min(num_extensions, len(ANSWER_EXTENSIONS))) + answer = answer + "".join(extensions) + + return { + "id": idx, + "conversations": [ + {"from": "human", "value": human_text}, + {"from": "gpt", "value": answer}, + ], + } + + +def main(): + parser = argparse.ArgumentParser() + parser.add_argument("--num-samples", type=int, default=200000) + parser.add_argument( + "--output", + type=str, + default="datasets/text_only_benchmark/label/labels.jsonl", + ) + parser.add_argument("--seed", type=int, default=42) + args = parser.parse_args() + + os.makedirs(os.path.dirname(args.output), exist_ok=True) + # Also create the images dir (required field in dataset_info but never used for text-only) + images_dir = os.path.join(os.path.dirname(os.path.dirname(args.output)), "images") + os.makedirs(images_dir, exist_ok=True) + + rng = random.Random(args.seed) + written = 0 + with open(args.output, "w") as f: + for i in range(args.num_samples): + sample = generate_sample(i, rng) + f.write(json.dumps(sample, ensure_ascii=False) + "\n") + written += 1 + if written % 10000 == 0: + print(f"Written {written}/{args.num_samples} samples...") + + print(f"Done. {written} samples written to {args.output}") + + +if __name__ == "__main__": + main() diff --git a/data/interleave_datasets/__init__.py b/data/interleave_datasets/__init__.py new file mode 100644 index 0000000000000000000000000000000000000000..528e72ab18a4d86179409d5834d19f34466f8c66 --- /dev/null +++ b/data/interleave_datasets/__init__.py @@ -0,0 +1,5 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +from .edit_dataset import UnifiedEditIterableDataset + diff --git a/data/interleave_datasets/any2any_dataset.py b/data/interleave_datasets/any2any_dataset.py new file mode 100644 index 0000000000000000000000000000000000000000..286cf64729c72c5f46486f320cbf1ed4d5db3525 --- /dev/null +++ b/data/interleave_datasets/any2any_dataset.py @@ -0,0 +1,1391 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +import io +import os +import json +import random +from PIL import Image, ImageFile, PngImagePlugin, ImageDraw, ImageFont +import numpy as np +import pycocotools.mask as mask_util +import re + +from .interleave_t2i_dataset import InterleavedBaseIterableDataset, ParquetStandardIterableDataset +from ..data_utils import pil_img2rgb + + +Image.MAX_IMAGE_PIXELS = 200000000 +ImageFile.LOAD_TRUNCATED_IMAGES = True +MaximumDecompressedSize = 1024 +MegaByte = 2 ** 20 +PngImagePlugin.MAX_TEXT_CHUNK = MaximumDecompressedSize * MegaByte + + +class PredIntermediateMissing(Exception): + """Raised in pred-intermediate mode when the saved PNG for this row is + missing. Caller (interleave_t2i_dataset.__iter__) catches it silently + to skip the row without falling back to GT.""" + pass + + +class UnifiedAny2AnyIterableDataset(InterleavedBaseIterableDataset, ParquetStandardIterableDataset): + + IMAGE_LIKE_TARGETS = {'rgb', 'depth', 'normal', 'canny', 'seg', 'samseg', 'samedge'} + FEATURE_TARGETS = {'dino', 'dinolocal', 'clip', 'imagebind', 'imagebindlocal'} + # New direct-PNG image modalities → parquet column name mapping. + SAM_IMAGE_COLUMN = {'samseg': 'sam_seg', 'samedge': 'sam_edge'} + PRED_INTERMEDIATE_IMAGE_MODS = {'depth', 'normal', 'canny', 'seg'} + PRED_INTERMEDIATE_TEXT_MODS = {'caption'} + PRED_INTERMEDIATE_DINO_MODS = {'dino'} + + def _load_pred_text(self, modality): + """Load Phase-1 generated text (caption) keyed by row provenance. + Opt-in: only when pred_intermediate_dir is set. Returns str or None.""" + if getattr(self, 'pred_intermediate_dir', None) is None: + return None + if modality not in self.PRED_INTERMEDIATE_TEXT_MODS: + return None + parquet_path = getattr(self, '_current_parquet_path', None) + rg_id = getattr(self, '_current_rg_id', None) + row_idx = getattr(self, '_current_row_idx', None) + if parquet_path is None or rg_id is None or row_idx is None: + return None + basename = os.path.splitext(os.path.basename(parquet_path))[0] + path = os.path.join( + self.pred_intermediate_dir, modality, + f"{basename}_rg{rg_id}_row{int(row_idx)}_pred.txt", + ) + if not os.path.exists(path): + return None + with open(path, 'r') as f: + return f.read().strip() + + def _load_pred_dino(self, modality): + """Load Phase-1 generated dino feature (.npy) keyed by row provenance. + Returns np.ndarray or None.""" + if getattr(self, 'pred_intermediate_dir', None) is None: + return None + if modality not in self.PRED_INTERMEDIATE_DINO_MODS: + return None + parquet_path = getattr(self, '_current_parquet_path', None) + rg_id = getattr(self, '_current_rg_id', None) + row_idx = getattr(self, '_current_row_idx', None) + if parquet_path is None or rg_id is None or row_idx is None: + return None + basename = os.path.splitext(os.path.basename(parquet_path))[0] + path = os.path.join( + self.pred_intermediate_dir, modality, + f"{basename}_rg{rg_id}_row{int(row_idx)}_pred.npy", + ) + if not os.path.exists(path): + return None + arr = np.load(path) + # Dino tokens are codebook ints; if Phase 1 saved as float (older + # runs) round to nearest int to avoid float16 precision loss. + if arr.dtype.kind == 'f': + arr = np.rint(arr).astype(np.int64) + # Phase 1 saves with leading batch dim (1, 16); _add_dino expects + # a flat (16,) array. Squeeze any singleton leading dims. + while arr.ndim > 1 and arr.shape[0] == 1: + arr = arr.squeeze(0) + return arr + + def _load_pred_pil(self, modality): + """Load a model-generated intermediate image keyed by + (parquet_basename, rg_id, row_idx). Returns PIL or None. + Opt-in: only active when pred_intermediate_dir is set. + Filename convention written by + scripts/paper/modus_stage3/generate_chained_intermediates.py: + //_rg_row_pred.png + """ + if getattr(self, 'pred_intermediate_dir', None) is None: + return None + if modality not in self.PRED_INTERMEDIATE_IMAGE_MODS: + return None + parquet_path = getattr(self, '_current_parquet_path', None) + rg_id = getattr(self, '_current_rg_id', None) + row_idx = getattr(self, '_current_row_idx', None) + if parquet_path is None or rg_id is None or row_idx is None: + return None + basename = os.path.splitext(os.path.basename(parquet_path))[0] + path = os.path.join( + self.pred_intermediate_dir, modality, + f"{basename}_rg{rg_id}_row{int(row_idx)}_pred.png", + ) + if not os.path.exists(path): + return None + return pil_img2rgb(Image.open(path)) + NATIVE_CHAT_SYSTEM_PROMPT = ( + "You are an advanced multimodal model. Given the user's text, visual, " + "or structured inputs, follow the user instruction and produce the " + "requested output modality accurately." + ) + + def _native_aligned_serialization(self): + return os.environ.get("HUNYUAN_NATIVE_ALIGNED_SERIALIZATION", "0") == "1" + + def _native_chat_serialization(self): + return os.environ.get("HUNYUAN_NATIVE_CHAT_SERIALIZATION", "0") == "1" + + def _add_native_chat_preamble(self, data): + data = self._add_text( + data, + self.NATIVE_CHAT_SYSTEM_PROMPT, + need_loss=False, + enable_cfg=False, + modality_type='text', + ) + return self._add_text( + data, + "User:", + need_loss=False, + enable_cfg=False, + modality_type='text', + ) + + def _add_native_chat_assistant_prefix(self, data): + return self._add_text( + data, + "Assistant: ", + need_loss=False, + enable_cfg=False, + modality_type='text', + ) + + def _target_instruction_text_native_chat(self, target_modality): + if target_modality == 'rgb': + return 'Generate an image.' + if target_modality == 'caption': + return 'Describe the image.' + if target_modality in self.IMAGE_LIKE_TARGETS: + return f'Generate the {target_modality} image.' + if target_modality == 'det': + return 'Detect the requested bounding boxes.' + if target_modality == 'grounding': + return 'Ground the requested phrase.' + if target_modality in self.FEATURE_TARGETS: + return f'Extract {target_modality} features.' + return f'Generate the {target_modality}.' + + def _target_instruction_text(self, target_modality): + if not self._native_aligned_serialization(): + return ( + f'[start {target_modality} {target_modality} {target_modality} ' + f'{target_modality} {target_modality} {target_modality} ' + f'{target_modality} {target_modality} {target_modality} {target_modality}]' + ) + if target_modality == 'rgb': + return 'Generate an image.' + if target_modality in self.IMAGE_LIKE_TARGETS: + return f'Generate the {target_modality} image.' + if target_modality == 'caption': + return 'Describe the image.' + return f'Generate the {target_modality}.' + + def parse_row(self, row): + # Parse dataset name to get target modality + # Format: "any2rgb", "any2caption", etc. + target_modality = self.dataset_name.split("2")[-1] + if target_modality == 'grounding' and ('grounding' not in row.index or row['grounding'] is None): + return None + + enable_cfg = False if target_modality in ('caption', 'det', 'cocodet') else True + + # cocodet target: skip rows with no detections (would be an empty + # target sequence). is_mandatory: false lets DataPack pick another row. + if target_modality == 'cocodet': + cd_dets, _ = self._parse_coco_det(row) + if not cd_dets: + return None + + # Get all available modalities except uid + available_modalities = [col for col in row.index if col != 'uid'] + if 'grounding' in available_modalities: + if row['grounding'] is None: + available_modalities.remove('grounding') + + + if 'det_seg' in available_modalities: + available_modalities.remove('det_seg') + # available_modalities.append('det') + available_modalities.append('seg') + + if 'dino' in available_modalities: + available_modalities.remove('dino') + available_modalities.append('dinolocal') + + if 'dino_global' in available_modalities: + available_modalities.remove('dino_global') + available_modalities.append('dino') + + # Remap parquet column 'clip448' to modality name 'clip' + if 'clip448' in available_modalities: + available_modalities.remove('clip448') + available_modalities.append('clip') + + if 'imagebind' in available_modalities: + available_modalities.remove('imagebind') + available_modalities.append('imagebindlocal') + + if 'imagebind_global' in available_modalities: + available_modalities.remove('imagebind_global') + available_modalities.append('imagebind') + + # New modalities: remap parquet column names → modality names. + if 'sam_seg' in available_modalities: + available_modalities.remove('sam_seg') + available_modalities.append('samseg') + if 'sam_edge' in available_modalities: + available_modalities.remove('sam_edge') + available_modalities.append('samedge') + if 'coco_det' in available_modalities: + available_modalities.remove('coco_det') + # Only offer cocodet as a condition when there are detections. + cd_dets, _ = self._parse_coco_det(row) + if cd_dets: + available_modalities.append('cocodet') + + # Remove target modality from available modalities for conditioning + condition_modalities = [mod for mod in available_modalities if mod != target_modality] + condition_sampling_probs = None + + # Drop modalities the active registry doesn't recognise. This codepath + # matters when the parquet predates a remap added later (e.g. the + # `dino` column was renamed to `dinolocal` in cbba109/2026-01-20, but + # a stage3 ckpt trained at 0a337b1/2025-11-06 has no `dinolocal` + # modality). Without this guard the dataset feeds an unrecognised + # modality_type into pack_sequence and triggers KeyError on + # self.modality_to_id[...]. + if self.modality_registry is not None: + known = set(self.modality_registry.name_to_id().keys()) + # `grounding` is a dataset-internal conditioning alias (phrase+bbox). + # Its emitted tokens are tagged `modality_type='det'`/`'text'` (see + # `_add_grounding`), so the registry KeyError that motivated this + # filter doesn't apply. Keep it as a usable selection name. + known.add('grounding') + condition_modalities = [mod for mod in condition_modalities if mod in known] + + # Filter conditions via config-driven modality registry. + if self.modality_registry is not None: + allowed = self.modality_registry.conditions_for(target_modality) + if allowed is not None: + condition_modalities = [mod for mod in condition_modalities if mod in allowed] + configured_probs = self.modality_registry.condition_probs_for(target_modality) + if configured_probs is not None: + prob_by_modality = { + cond: prob for cond, prob in zip(allowed, configured_probs) + } + condition_sampling_probs = [ + prob_by_modality[mod] + for mod in condition_modalities + if mod in prob_by_modality + ] + + if len(condition_modalities) == 0: + return None + + # Validation path: force a single fixed condition modality so the loss + # can be bucketed into a (cond, tgt) matrix. Skip rows where the + # requested modality is not available for this target. + if getattr(self, 'force_condition_modalities', None) is not None: + required = list(self.force_condition_modalities) + if not all(m in condition_modalities for m in required): + return None + selected_conditions = required + elif getattr(self, 'force_condition_modality', None) is not None: + if self.force_condition_modality not in condition_modalities: + return None + selected_conditions = [self.force_condition_modality] + elif self.num_condition_modalities == 0: + num_conditions = random.randint(1, len(condition_modalities)) + selected_conditions = None # set below + else: + if self.strict_num_condition_modalities: + if len(condition_modalities) < self.num_condition_modalities: + return None + num_conditions = self.num_condition_modalities + else: + max_conditions = min(self.num_condition_modalities, len(condition_modalities)) + if max_conditions == 1: + num_conditions = max_conditions + else: + num_conditions = random.randint(1, max_conditions) + selected_conditions = None # set below + + if selected_conditions is None: + if condition_sampling_probs is None: + selected_conditions = random.sample(condition_modalities, num_conditions) + else: + probs = np.array(condition_sampling_probs, dtype=np.float64) + probs_sum = float(probs.sum()) + if probs_sum <= 0.0: + probs = np.full(len(condition_modalities), 1.0 / len(condition_modalities)) + else: + probs = probs / probs_sum + selected_indices = np.random.choice( + len(condition_modalities), + size=num_conditions, + replace=False, + p=probs, + ) + selected_conditions = [condition_modalities[i] for i in selected_indices] + + # Optional monitoring tag for route-specific rgb generation logging. + # Only tag unambiguous single-condition rgb targets. + if target_modality == 'rgb' and len(selected_conditions) == 1: + cond = selected_conditions[0] + if cond in ('caption', 'grounding', 'dinolocal'): + data_route = f"{cond}2rgb" + else: + data_route = None + else: + data_route = None + + + # if num_conditions > 1: + # print("selected conditions:", selected_conditions) + # print("num conditions:", num_conditions) + # print('target modality:', target_modality) + # if 'grounding' in selected_conditions: + # print("grounding instances:", row['grounding']) + data = self._init_data() + if data_route is not None: + data['rgb_loss_route'] = data_route + + native_chat = self._native_chat_serialization() + if native_chat: + data = self._add_native_chat_preamble(data) + + # Add condition modalities in random order + random.shuffle(selected_conditions) + + for modality in selected_conditions: + if self.use_instruction and self.use_condition_instruction: + data = self._add_text(data, f'[start {modality}]', need_loss=False, enable_cfg=enable_cfg, modality_type='text') + if modality == 'caption': + # Pred caption: load from disk if Phase 1 wrote it; else + # use parquet GT. + pred_caption = self._load_pred_text('caption') + if pred_caption is not None: + caption_text = pred_caption + elif (getattr(self, 'pred_intermediate_dir', None) is not None + and 'caption' in self.PRED_INTERMEDIATE_TEXT_MODS): + raise PredIntermediateMissing( + 'no pred TXT for caption at this row') + else: + caption_text = row[modality] + data = self._add_text(data, caption_text, need_loss=False, enable_cfg=enable_cfg, modality_type=modality) + elif modality in ['rgb', 'depth', 'normal', 'canny']: + # Handle image modalities. In pred-intermediate mode, depth/ + # normal/canny conditions come from disk (Phase 1 outputs); + # rgb is always real. If pred mode is on and the file for + # this row is missing, skip the row entirely — do NOT + # silently fall back to GT. + pred_pil = self._load_pred_pil(modality) + if pred_pil is not None: + image = pred_pil + elif (getattr(self, 'pred_intermediate_dir', None) is not None + and modality in self.PRED_INTERMEDIATE_IMAGE_MODS): + raise PredIntermediateMissing( + f'no pred PNG for {modality} at this row') + else: + image = pil_img2rgb(Image.open(io.BytesIO(row[modality]))) + data = self._add_image( + data, + image, + need_loss=False, + enable_cfg=enable_cfg, + need_vae=True, + need_vit=True, + modality_type=modality, + ) + elif modality in ['samseg', 'samedge']: + # Direct-PNG SAM image modalities (samseg is RGBA → pil_img2rgb). + image = pil_img2rgb(Image.open(io.BytesIO(row[self.SAM_IMAGE_COLUMN[modality]]))) + data = self._add_image( + data, + image, + need_loss=False, + enable_cfg=enable_cfg, + need_vae=True, + need_vit=True, + modality_type=modality, + ) + elif modality in ['cocodet']: + cd_dets, cd_size = self._parse_coco_det(row) + data = self._add_cocodet( + data, + detections=cd_dets, + image_size=cd_size, + need_loss=False, + enable_cfg=enable_cfg, + modality_type=modality, + ) + elif modality in ['det']: + det_seg_instances = row['det_seg']['instances'] + det_seg_raw_size = row['det_seg']['size'] + det_seg_prompts = row['det_seg']['prompt'].split(' .') + data = self._add_det( + data, + det_seg_instances=det_seg_instances, + det_seg_raw_size=det_seg_raw_size, + det_seg_prompts=det_seg_prompts, + need_loss=False, + enable_cfg=enable_cfg, + modality_type=modality + ) + + elif modality in ['seg']: + # Pred-mode seg: if Phase 1 saved a pred seg PNG, use it + # via _add_image directly (skip _add_seg's RLE rendering). + pred_seg = self._load_pred_pil('seg') + if pred_seg is not None: + data = self._add_image( + data, + pred_seg, + need_loss=False, + enable_cfg=enable_cfg, + need_vae=True, + need_vit=True, + modality_type='seg', + ) + continue + elif (getattr(self, 'pred_intermediate_dir', None) is not None + and 'seg' in self.PRED_INTERMEDIATE_IMAGE_MODS): + raise PredIntermediateMissing( + 'no pred PNG for seg at this row') + det_seg_instances = row['det_seg']['instances'] + det_seg_raw_size = row['det_seg']['size'] + det_seg_prompts = row['det_seg']['prompt'].split(' .') + data = self._add_seg( + data, + det_seg_instances=det_seg_instances, + det_seg_raw_size=det_seg_raw_size, + det_seg_prompts=det_seg_prompts, + need_loss=False, + enable_cfg=enable_cfg, + need_vae=True, + need_vit=True, + modality_type=modality + ) + + elif modality in ['grounding']: + grounding_instances = row['grounding'] + data = self._add_grounding( + data, + grounding_instances=grounding_instances, + need_loss=False, + enable_cfg=enable_cfg, + modality_type=modality + ) + elif modality in ['dino']: + # Pred dino: load .npy from disk if Phase 1 wrote it. + pred_dino = self._load_pred_dino('dino') + if pred_dino is not None: + dino_tokens = pred_dino + elif (getattr(self, 'pred_intermediate_dir', None) is not None + and 'dino' in self.PRED_INTERMEDIATE_DINO_MODS): + raise PredIntermediateMissing( + 'no pred NPY for dino at this row') + else: + dino_tokens = row['dino_global'] + data = self._add_dino( + data, + dino_tokens=dino_tokens, + need_loss=False, + enable_cfg=enable_cfg, + modality_type=modality + ) + elif modality in ['dinolocal']: + dino_tokens = row['dino'] + data = self._add_dinolocal( + data, + dino_tokens=dino_tokens, + need_loss=False, + enable_cfg=enable_cfg, + modality_type=modality + ) + elif modality in ['clip']: + clip_tokens = row['clip448'] + data = self._add_clip( + data, + clip_tokens=clip_tokens, + need_loss=False, + enable_cfg=enable_cfg, + modality_type=modality + ) + elif modality in ['imagebind']: + imagebind_tokens = row['imagebind_global'] + data = self._add_imagebind( + data, + imagebind_tokens=imagebind_tokens, + need_loss=False, + enable_cfg=enable_cfg, + modality_type=modality + ) + elif modality in ['imagebindlocal']: + imagebind_tokens = row['imagebind'] + data = self._add_imagebindlocal( + data, + imagebind_tokens=imagebind_tokens, + need_loss=False, + enable_cfg=enable_cfg, + modality_type=modality + ) + + if native_chat: + if target_modality not in ('det', 'seg', 'grounding'): + if self.use_instruction and self.use_target_instruction: + data = self._add_text( + data, + self._target_instruction_text_native_chat(target_modality), + need_loss=False, + enable_cfg=False, + modality_type='text', + ) + data = self._add_native_chat_assistant_prefix(data) + elif self.use_instruction and self.use_target_instruction: + if target_modality == 'det' or target_modality == 'seg' or target_modality == 'grounding': + pass # separate instruction in add_det() function + else: + data = self._add_text( + data, + self._target_instruction_text(target_modality), + need_loss=False, + enable_cfg=enable_cfg, + modality_type='text', + ) + # Add target modality at the end with loss=True + if target_modality == 'caption': + # Handle text target + # data = self._add_text(data, row[target_modality], enable_cfg=enable_cfg, need_loss=True, modality_type=target_modality) + caption_text = row[target_modality] + if native_chat: + caption_text = f"{caption_text}" + data = self._add_text(data, caption_text, enable_cfg=enable_cfg, need_loss=True, modality_type=target_modality) + elif target_modality in ['rgb', 'depth', 'normal', 'canny']: + # Handle image target + image = pil_img2rgb(Image.open(io.BytesIO(row[target_modality]))) + data = self._add_image( + data, + image, + need_loss=True, + need_vae=False, + need_vit=False, + modality_type=target_modality, + ) + elif target_modality in ['samseg', 'samedge']: + # Direct-PNG SAM image target (samseg is RGBA → pil_img2rgb). + image = pil_img2rgb(Image.open(io.BytesIO(row[self.SAM_IMAGE_COLUMN[target_modality]]))) + data = self._add_image( + data, + image, + need_loss=True, + need_vae=False, + need_vit=False, + modality_type=target_modality, + ) + elif target_modality == 'cocodet': + cd_dets, cd_size = self._parse_coco_det(row) + data = self._add_cocodet( + data, + detections=cd_dets, + image_size=cd_size, + need_loss=True, + enable_cfg=enable_cfg, + modality_type=target_modality, + ) + elif target_modality == 'det': + det_seg_instances = row['det_seg']['instances'] + det_seg_raw_size = row['det_seg']['size'] + det_seg_prompts = row['det_seg']['prompt'].split(' .') + data = self._add_det( + data, + det_seg_instances=det_seg_instances, + det_seg_raw_size=det_seg_raw_size, + det_seg_prompts=det_seg_prompts, + need_loss=True, + enable_cfg=enable_cfg, + modality_type=target_modality + ) + elif target_modality == 'seg': + det_seg_instances = row['det_seg']['instances'] + det_seg_raw_size = row['det_seg']['size'] + det_seg_prompts = row['det_seg']['prompt'].split(' .') + data = self._add_seg( + data, + det_seg_instances=det_seg_instances, + det_seg_raw_size=det_seg_raw_size, + det_seg_prompts=det_seg_prompts, + need_loss=True, + enable_cfg=enable_cfg, + need_vae=False, + need_vit=False, + modality_type=target_modality + ) + elif target_modality == 'grounding': + grounding_instances = row['grounding'] + data = self._add_grounding( + data, + grounding_instances=grounding_instances, + need_loss=True, + enable_cfg=False, + modality_type=target_modality + ) + elif target_modality == 'dino': + dino_tokens = row['dino_global'] + data = self._add_dino( + data, + dino_tokens=dino_tokens, + need_loss=True, + enable_cfg=False, + modality_type=target_modality + ) + elif target_modality == 'dinolocal': + dino_tokens = row['dino'] + data = self._add_dinolocal( + data, + dino_tokens=dino_tokens, + need_loss=True, + enable_cfg=False, + modality_type=target_modality + ) + elif target_modality == 'clip': + clip_tokens = row['clip448'] + data = self._add_clip( + data, + clip_tokens=clip_tokens, + need_loss=True, + enable_cfg=False, + modality_type=target_modality + ) + elif target_modality == 'imagebind': + imagebind_tokens = row['imagebind_global'] + data = self._add_imagebind( + data, + imagebind_tokens=imagebind_tokens, + need_loss=True, + enable_cfg=False, + modality_type=target_modality + ) + elif target_modality == 'imagebindlocal': + imagebind_tokens = row['imagebind'] + data = self._add_imagebindlocal( + data, + imagebind_tokens=imagebind_tokens, + need_loss=True, + enable_cfg=False, + modality_type=target_modality + ) + + return data + + + def _add_det(self, data, det_seg_instances, det_seg_raw_size, det_seg_prompts, need_loss, enable_cfg, modality_type): + + if not need_loss: + is_all_sampled = False + num_instances = len(det_seg_instances) + num_selected = random.randint(1, num_instances) + # Sample by indices to support containers that aren't proper sequences + selected_indices = random.sample(range(num_instances), num_selected) + selected_instances = [det_seg_instances[i] for i in selected_indices] + is_all_sampled = (num_selected == num_instances) + else: + unique_categories = sorted(set(inst.get('category') for inst in det_seg_instances)) + num_categories = len(unique_categories) + + # num_selected_categories = random.randint(1, num_categories) + num_selected_categories = 1 + selected_categories = random.sample(unique_categories, num_selected_categories) + + selected_instances = [] + for inst in det_seg_instances: + if inst.get('category') in selected_categories: + selected_instances.append(inst) + + # Size assumed as [width, height] + width, height = det_seg_raw_size[0], det_seg_raw_size[1] + width = max(float(width), 1.0) + height = max(float(height), 1.0) + + normalized_dets = '' + # selected_instances = sort_instances_by_distance_to_origin(selected_instances) + selected_instances = sort_instances_by_raster(selected_instances) + + for inst in selected_instances: + bbox = inst.get('bbox') + category = inst.get('category') + score = inst.get('score', None) + + if bbox is None or len(bbox) != 4: + continue + + # bbox assumed [x1, y1, x2, y2] in raw pixel coords + x1, y1, x2, y2 = float(bbox[0]), float(bbox[1]), float(bbox[2]), float(bbox[3]) + + # Normalize to [0,1] + x1_n = x1 / width + y1_n = y1 / height + x2_n = x2 / width + y2_n = y2 / height + + # Clamp + x1_n = min(max(x1_n, 0.0), 0.999) + y1_n = min(max(y1_n, 0.0), 0.999) + x2_n = min(max(x2_n, 0.0), 0.999) + y2_n = min(max(y2_n, 0.0), 0.999) + + # Quantize: keep 3 digits by *1000 and round + def q(v, max_digits=3): + return int(round(v * 10 ** max_digits)) + + bbox_q = [q(x1_n), q(y1_n), q(x2_n), q(y2_n)] + score_q = q(score, max_digits=2) + + coord_types = ['x1', 'y1', 'x2', 'y2'] + coord_tokens = [f'<|{coord_types[i]}_{bbox_q[i]:03d}|>' for i in range(4)] + score_token = f'<|score_{score_q:02d}|>' + # bbox_str = f'{"".join(coord_tokens)}{category}{score_token}' + # bbox_str = f'{"".join(coord_tokens)} || {category} ||{score_token}' + # bbox_str = f'{"".join(coord_tokens)}{category}' + + + bbox_str = f'{"".join(coord_tokens)}' + + # bbox_str = f'{" ".join(coord_tokens)} {category}' + # bbox_str = f'<|box_start|>{"".join(coord_tokens)}<|box_end|>{category},score={score_q}' + + # bbox_str = f'x1={bbox_q[0]},y1={bbox_q[1]},x2={bbox_q[2]},y2={bbox_q[3]},{category},score={score_q}' + + # normalized_dets = normalized_dets + bbox_str + ',' + normalized_dets = normalized_dets + bbox_str + + if need_loss: + # if len(selected_categories) == len(unique_categories): + # instruction_text = "start detect the box of everything" + # else: + # instruction_text = f"start detect the box of {', '.join(selected_categories)}" + if self._native_chat_serialization(): + instruction_text = f"Detect the box of {', '.join(selected_categories)}." + elif self._native_aligned_serialization(): + instruction_text = f"Detect the box of {', '.join(selected_categories)}." + else: + instruction_text = f"start detect the box of {', '.join(selected_categories)}" + data = self._add_text(data, instruction_text, need_loss=False, enable_cfg=enable_cfg, modality_type='text') + if self._native_chat_serialization(): + data = self._add_native_chat_assistant_prefix(data) + # print("det instruction text:", instruction_text) + else: + prefix = "bounding boxes (all): " if is_all_sampled else "bounding boxes (partial): " + # normalized_dets = prefix + normalized_dets + + if self.use_det_image: + # det_image = get_det_image(normalized_dets, det_seg_raw_size) + det_image = get_det_image_new(normalized_dets, det_seg_raw_size) + data = self._add_image(data, det_image, need_loss=False, enable_cfg=enable_cfg, need_vae=True, need_vit=True, modality_type='rgb') + + + data = self._add_text(data, prefix, need_loss=False, enable_cfg=enable_cfg, modality_type='text') + + + data = self._add_text(data, normalized_dets, need_loss=need_loss, enable_cfg=enable_cfg, modality_type=modality_type) + # print("det normalized_dets:", normalized_dets) + + return data + + + def _parse_coco_det(self, row): + """Parse the `coco_det` JSON string column. + + Returns (detections_list, image_size). On missing/blank/malformed + input returns ([], None) so callers can treat it as 'no detections'. + """ + raw = row['coco_det'] if 'coco_det' in row.index else None + if raw is None: + return [], None + try: + obj = json.loads(raw) + except (TypeError, ValueError): + return [], None + dets = obj.get('detections') or [] + size = obj.get('image_size') or None + return dets, size + + def _add_cocodet(self, data, detections, image_size, need_loss, enable_cfg, modality_type): + """Pix2seq-style detection serialization (cocodet). + + Per box: <|x1_q|><|y1_q|><|x2_q|><|y2_q|><|coco_cls_label|>, boxes sorted + by distance-to-origin. Coords reuse det's quantized coordinate tokens; + class is a dedicated token aligned to the COCO id. No score, no separators. + The start/end delimiters are added by the packing layer (modality_type). + """ + width = max(float(image_size[0]), 1.0) if image_size else 1.0 + height = max(float(image_size[1]), 1.0) if image_size else 1.0 + + instances = sort_instances_by_distance_to_origin(detections or []) + + def q(v): + return min(max(int(round(v * 1000)), 0), 999) + + seq = '' + for inst in instances: + bbox = inst.get('bbox') + if bbox is None or len(bbox) != 4: + continue + label = inst.get('label') + if label is None: + continue + label = int(label) + if label < 0 or label > 90: # COCO id range; out-of-range → skip + continue + x1, y1, x2, y2 = (float(bbox[0]), float(bbox[1]), + float(bbox[2]), float(bbox[3])) + x1q, y1q = q(x1 / width), q(y1 / height) + x2q, y2q = q(x2 / width), q(y2 / height) + seq += (f'<|x1_{x1q:03d}|><|y1_{y1q:03d}|>' + f'<|x2_{x2q:03d}|><|y2_{y2q:03d}|><|coco_cls_{label:02d}|>') + + # Empty sequence is valid (e.g. as a "no objects" condition); the + # packing layer still wraps it with the cocodet start/end delimiters. + data = self._add_text(data, seq, need_loss=need_loss, + enable_cfg=enable_cfg, modality_type=modality_type) + return data + + def _add_grounding(self, data, grounding_instances, need_loss, enable_cfg, modality_type): + + selected_grounding = random.choice(grounding_instances) + phrase = selected_grounding['phrase'] + bbox = selected_grounding['bbox'] + + + if need_loss: + if self._native_chat_serialization(): + instruction_text = f"Ground the phrase: {phrase}" + elif self._native_aligned_serialization(): + instruction_text = f"Ground the phrase: {phrase}" + else: + instruction_text = f"[start grounding the phrase] {phrase}" + data = self._add_text(data, instruction_text, need_loss=False, enable_cfg=enable_cfg, modality_type='text') + if self._native_chat_serialization(): + data = self._add_native_chat_assistant_prefix(data) + elif random.random() >= self.grounding_phrase_dropout_prob: + data = self._add_text(data, phrase, need_loss=False, enable_cfg=enable_cfg, modality_type='text') + + coord_types = ['x1', 'y1', 'x2', 'y2'] + coord_tokens = [f'<|{coord_types[i]}_{bbox[i]:03d}|>' for i in range(4)] + bbox_str = f'{"".join(coord_tokens)}' + data = self._add_text(data, bbox_str, need_loss=need_loss, enable_cfg=enable_cfg, modality_type='det') + + return data + + def _add_seg(self, data, det_seg_instances, det_seg_raw_size, det_seg_prompts, need_loss, enable_cfg, need_vae, need_vit, modality_type): + # Helper: decode COCO RLE to binary mask; fallback to empty mask if not available + def decode_rle_to_mask(rle_counts, size): + try: + rle = {'counts': rle_counts, 'size': [int(size[0]), int(size[1])]} + mask = mask_util.decode(rle) + if mask is None: + return None + # pycocotools returns (H,W,1) sometimes; squeeze to (H,W) + if hasattr(mask, 'shape') and len(mask.shape) == 3: + mask = mask[:, :, 0] + return mask.astype('uint8') + except Exception: + try: + height, width = int(size[1]), int(size[0]) + return np.zeros((height, width), dtype='uint8') + except Exception: + return None + + width, height = float(det_seg_raw_size[0]), float(det_seg_raw_size[1]) + width = max(width, 1.0) + height = max(height, 1.0) + + mask_images = get_mask_image(det_seg_instances, det_seg_raw_size) + # Build mask(s) + if not need_loss: + # Conditioning: select at most 2 categories from mask_images, add category name and mask image + if len(mask_images) > 0: + k = random.randint(1, min(2, len(mask_images))) + selected_categories = random.sample(list(mask_images.keys()), k) + else: + selected_categories = [] + + if not selected_categories: + return data + + for category in selected_categories: + # Use pre-computed merged mask for this category + pil_mask = mask_images[category] + + # Add category text + data = self._add_text( + data, + f"mask category: {category}", + need_loss=False, + enable_cfg=enable_cfg, + modality_type='text', + ) + + data = self._add_image( + data, + pil_mask, + need_loss=False, + enable_cfg=enable_cfg, + need_vae=need_vae, + need_vit=need_vit, + modality_type=modality_type, + ) + + return data + else: + # Supervision: select one category, add instruction, then add mask image with loss + if len(mask_images) == 0: + return data + + # Select one category + category = random.choice(list(mask_images.keys())) + + # Create instruction text + if self._native_chat_serialization(): + instruction_text = f"Generate the segmentation mask of {category}." + elif self._native_aligned_serialization(): + instruction_text = f"Generate the segmentation mask of {category}." + else: + instruction_text = f"start segment the mask of {category}" + + data = self._add_text(data, instruction_text, need_loss=False, enable_cfg=enable_cfg, modality_type='text') + if self._native_chat_serialization(): + data = self._add_native_chat_assistant_prefix(data) + + # Use pre-computed mask image for this category + pil_mask = mask_images[category] + + data = self._add_image( + data, + pil_mask, + need_loss=True, + enable_cfg=enable_cfg, + need_vae=False, + need_vit=False, + modality_type=modality_type, + ) + + return data + + + def _add_dino(self, data, dino_tokens, need_loss, enable_cfg, modality_type): + text_ids = dino_tokens + self.tokenizer.encode('<|dino_0000|>')[0] + text_ids = text_ids.tolist() + data['num_tokens'] += len(text_ids) + data['text_ids_list'].append(text_ids) + data['sequence_plan'].append( + { + 'type': 'text', + 'enable_cfg': int(enable_cfg), + 'loss': int(need_loss), + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + return data + + def _add_dinolocal(self, data, dino_tokens, need_loss, enable_cfg, modality_type): + text_ids = dino_tokens + self.tokenizer.encode('<|dinolocal_0000|>')[0] + text_ids = text_ids.tolist() + data['num_tokens'] += len(text_ids) + data['text_ids_list'].append(text_ids) + data['sequence_plan'].append( + { + 'type': 'text', + 'enable_cfg': int(enable_cfg), + 'loss': int(need_loss), + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + return data + + def _add_clip(self, data, clip_tokens, need_loss, enable_cfg, modality_type): + text_ids = clip_tokens + self.tokenizer.encode('<|clip_0000|>')[0] + text_ids = text_ids.tolist() + data['num_tokens'] += len(text_ids) + data['text_ids_list'].append(text_ids) + data['sequence_plan'].append( + { + 'type': 'text', + 'enable_cfg': int(enable_cfg), + 'loss': int(need_loss), + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + return data + + def _add_imagebind(self, data, imagebind_tokens, need_loss, enable_cfg, modality_type): + text_ids = imagebind_tokens + self.tokenizer.encode('<|imagebind_0000|>')[0] + text_ids = text_ids.tolist() + data['num_tokens'] += len(text_ids) + data['text_ids_list'].append(text_ids) + data['sequence_plan'].append( + { + 'type': 'text', + 'enable_cfg': int(enable_cfg), + 'loss': int(need_loss), + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + return data + + def _add_imagebindlocal(self, data, imagebind_tokens, need_loss, enable_cfg, modality_type): + text_ids = imagebind_tokens + self.tokenizer.encode('<|imagebindlocal_0000|>')[0] + text_ids = text_ids.tolist() + data['num_tokens'] += len(text_ids) + data['text_ids_list'].append(text_ids) + data['sequence_plan'].append( + { + 'type': 'text', + 'enable_cfg': int(enable_cfg), + 'loss': int(need_loss), + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + return data + +def get_det_image(normalized_dets, det_seg_raw_size): + """ + Create an image with bounding boxes drawn on it based on normalized detections. + + Args: + normalized_dets (str): String containing normalized bounding box information + det_seg_raw_size (list): [width, height] of the image in pixels + + Returns: + PIL.Image: Image with bounding boxes drawn in random colors + """ + + # Extract image dimensions + width, height = int(det_seg_raw_size[0]), int(det_seg_raw_size[1]) + + # Create a blank white image + image = Image.new('RGB', (width, height), color='black') + draw = ImageDraw.Draw(image) + + # Define a palette of random colors for bounding boxes + colors = [ + (255, 0, 0), # Red + (0, 255, 0), # Green + (0, 0, 255), # Blue + (255, 255, 0), # Yellow + (255, 0, 255), # Magenta + (0, 255, 255), # Cyan + (255, 128, 0), # Orange + (128, 0, 255), # Purple + (255, 192, 203), # Pink + (0, 128, 0), # Dark Green + (128, 128, 0), # Olive + (0, 128, 128), # Teal + ] + + # Dictionary to map categories to colors + category_colors = {} + + # Parse the normalized_dets string + if not normalized_dets or normalized_dets.strip() == '': + return image + + # Split by comma to get individual bounding box strings + bbox_strings = [s.strip() for s in normalized_dets.split(',') if s.strip()] + + for i, bbox_str in enumerate(bbox_strings): + try: + # Parse the bounding box string format: "<|x1_xxx|><|y1_xxx|><|x2_xxx|><|y2_xxx|> || category ||<|score_xx|>" + # We need to be more careful with the splitting since category names might contain "||" + + # First, find the score part at the end + score_match = re.search(r'<\|score_\d+\|>$', bbox_str) + if not score_match: + continue + score_part = score_match.group(0) + + # Remove the score part to get the rest + remaining = bbox_str[:-len(score_part)] + + # Split by " || " to separate coordinates from category + if ' || ' not in remaining: + continue + coord_part, category = remaining.split(' || ', 1) + + # Clean up the category name (remove any trailing "||" that might be left) + category = category.strip().rstrip('||').strip() + + # Extract coordinates from tokens like <|x1_123|><|y1_456|><|x2_789|><|y2_012|> + coord_pattern = r'<\|([xy][12])_(\d+)\|>' + coord_matches = re.findall(coord_pattern, coord_part) + + if len(coord_matches) != 4: + continue + + # Convert to dictionary for easier access + coords = {} + for coord_type, value in coord_matches: + coords[coord_type] = int(value) + + # Convert quantized coordinates back to pixel coordinates + # The coordinates are quantized by multiplying by 1000, so divide by 1000 + x1 = int((coords['x1'] / 1000.0) * width) + y1 = int((coords['y1'] / 1000.0) * height) + x2 = int((coords['x2'] / 1000.0) * width) + y2 = int((coords['y2'] / 1000.0) * height) + + # Clamp coordinates to image bounds + x1 = max(0, min(x1, width)) + y1 = max(0, min(y1, height)) + x2 = max(0, min(x2, width)) + y2 = max(0, min(y2, height)) + + # Skip invalid bounding boxes + if x1 >= x2 or y1 >= y2: + continue + + # Assign color based on category - same category gets same color + if category not in category_colors: + # Assign next available color to this category + color_index = len(category_colors) % len(colors) + category_colors[category] = colors[color_index] + color = category_colors[category] + + # Draw the bounding box rectangle + draw.rectangle([x1, y1, x2, y2], outline=color, width=3) + # Draw the bounding box rectangle (filled) + # draw.rectangle([x1, y1, x2, y2], fill=color) + + # Extract score if available + score_match = re.search(r'<\|score_(\d+)\|>', score_part) + score = float(score_match.group(1)) / 100.0 if score_match else 0.0 + + # Draw label with category and score + label = f"{category}: {score:.2f}" + + # Calculate text position (above the bounding box with better spacing) + text_y = max(5, y1 - 15) + + # Draw text background rectangle aligned to left edge of bounding box + text_bbox = draw.textbbox((x1, text_y), label) + text_x1, text_y1, text_x2, text_y2 = text_bbox + # Keep left edge aligned with bounding box, add padding only on right/bottom + draw.rectangle([x1, text_y1-2, text_x2+4, text_y2+2], fill=color, outline=color) + + font = ImageFont.load_default() + draw.text((x1, text_y), label, fill=(255, 255, 255), font=font) + + except Exception as e: + # Skip malformed bounding box strings + print(f"Warning: Could not parse bounding box string '{bbox_str}': {e}") + continue + + return image + + +def get_det_image_new(normalized_dets, det_seg_raw_size): + """ + Create an image with bounding boxes drawn based on the NEW detections format: + "<|x1_100|><|y1_100|><|x2_499|><|y2_499|>person,<|x1_700|>...>apple," + + Categories can include commas, so we must NOT split by comma. We instead + locate each coordinate token group and take the category text that follows + it up to the start of the next coordinate group (or end of string). + + Args: + normalized_dets (str): Detection string in the new format + det_seg_raw_size (list): [width, height] + + Returns: + PIL.Image: Image with bounding boxes drawn + """ + + width, height = int(det_seg_raw_size[0]), int(det_seg_raw_size[1]) + image = Image.new('RGB', (width, height), color='black') + draw = ImageDraw.Draw(image) + + colors = [ + (255, 0, 0), (0, 255, 0), (0, 0, 255), (255, 255, 0), (255, 0, 255), + (0, 255, 255), (255, 128, 0), (128, 0, 255), (255, 192, 203), + (0, 128, 0), (128, 128, 0), (0, 128, 128), + ] + category_colors = {} + + if not normalized_dets or normalized_dets.strip() == '': + return image + + # Find all coordinate token groups and their spans + group_pattern = re.compile(r"<\|x1_(\d+)\|><\|y1_(\d+)\|><\|x2_(\d+)\|><\|y2_(\d+)\|>") + matches = list(group_pattern.finditer(normalized_dets)) + + for idx, m in enumerate(matches): + try: + x1_q = int(m.group(1)) + y1_q = int(m.group(2)) + x2_q = int(m.group(3)) + y2_q = int(m.group(4)) + + # Determine category slice: after this match to before next match (or end) + start_cat = m.end() + end_cat = matches[idx + 1].start() if idx + 1 < len(matches) else len(normalized_dets) + category = normalized_dets[start_cat:end_cat] + # Strip a single trailing comma and whitespace + category = category.rstrip() + if category.endswith(','): + category = category[:-1] + category = category.strip() + if category == '': + category = 'object' + + # De-quantize from [0,1000) back to pixel coords + x1 = int((x1_q / 1000.0) * width) + y1 = int((y1_q / 1000.0) * height) + x2 = int((x2_q / 1000.0) * width) + y2 = int((y2_q / 1000.0) * height) + + # Clamp + x1 = max(0, min(x1, width)) + y1 = max(0, min(y1, height)) + x2 = max(0, min(x2, width)) + y2 = max(0, min(y2, height)) + + if x1 >= x2 or y1 >= y2: + continue + + if category not in category_colors: + color_index = len(category_colors) % len(colors) + category_colors[category] = colors[color_index] + color = category_colors[category] + + # Draw box + draw.rectangle([x1, y1, x2, y2], outline=color, width=3) + + # Label (category only; no score in new format) + label = f"{category}" + text_y = max(5, y1 - 15) + text_bbox = draw.textbbox((x1, text_y), label) + tb_x1, tb_y1, tb_x2, tb_y2 = text_bbox + draw.rectangle([x1, tb_y1 - 2, tb_x2 + 4, tb_y2 + 2], fill=color, outline=color) + font = ImageFont.load_default() + draw.text((x1, text_y), label, fill=(255, 255, 255), font=font) + + except Exception as e: + print(f"Warning: Could not parse detection entry around index {m.start()}: {e}") + continue + + return image + +def get_mask_image(det_seg_instances, det_seg_raw_size): + """ + Create mask images for each category with different colors for different instances. + + Args: + det_seg_instances: List of detection/segmentation instances + det_seg_raw_size: Raw size of the image [width, height] + + Returns: + dict: Dictionary mapping category_name to PIL Image (RGB mode) + """ + # Helper: decode COCO RLE to binary mask; fallback to empty mask if not available + def decode_rle_to_mask(rle_counts, size): + try: + rle = {'counts': rle_counts, 'size': [int(size[0]), int(size[1])]} + mask = mask_util.decode(rle) + if mask is None: + return None + # pycocotools returns (H,W,1) sometimes; squeeze to (H,W) + if hasattr(mask, 'shape') and len(mask.shape) == 3: + mask = mask[:, :, 0] + return mask.astype('uint8') + except Exception: + try: + height, width = int(size[1]), int(size[0]) + return np.zeros((height, width), dtype='uint8') + except Exception: + return None + + width, height = float(det_seg_raw_size[0]), float(det_seg_raw_size[1]) + width = max(width, 1.0) + height = max(height, 1.0) + + # Group instances by category + category_groups = {} + for inst in det_seg_instances: + category = inst.get('category', 'object') + if category not in category_groups: + category_groups[category] = [] + category_groups[category].append(inst) + + # Define colors for different instances (20 colors) - matplotlib colorblind-friendly palette + colors = [ + (31, 119, 180), # C1 - Blue + (174, 199, 232), # C2 - Light Blue + (255, 127, 14), # C3 - Orange + (255, 187, 120), # C4 - Light Orange + (44, 160, 44), # C5 - Green + (152, 223, 138), # C6 - Light Green + (214, 39, 40), # C7 - Red + (255, 152, 150), # C8 - Light Red + (148, 103, 189), # C9 - Purple + (197, 176, 213), # C10 - Light Purple + (140, 86, 75), # C11 - Brown + (196, 156, 148), # C12 - Light Brown + (227, 119, 194), # C13 - Pink + (247, 182, 210), # C14 - Light Pink + (127, 127, 127), # C15 - Gray + (199, 199, 199), # C16 - Light Gray + (188, 189, 34), # C17 - Olive + (219, 219, 141), # C18 - Light Olive + (23, 190, 207), # C19 - Cyan + (158, 218, 229), # C20 - Light Cyan + ] + + # Create mask images for each category + category_masks = {} + for category, instances in category_groups.items(): + # Initialize merged mask for this category + merged_mask = np.zeros((int(height), int(width), 3), dtype='uint8') + + # Randomly shuffle colors for this category to avoid bias + available_colors = colors.copy() + random.shuffle(available_colors) + + for i, inst in enumerate(instances): + seg = inst.get('segmentation', {}) or {} + rle_counts = seg.get('counts', None) + size = seg.get('size', [int(width), int(height)]) + + mask = None + if rle_counts is not None and size is not None: + mask = decode_rle_to_mask(rle_counts, size) + + if mask is not None: + # Get color for this instance (randomly selected, no overlap within category) + color = available_colors[i % len(available_colors)] + + # Apply color to mask regions + for c in range(3): # RGB channels + merged_mask[:, :, c] = np.where(mask > 0, color[c], merged_mask[:, :, c]) + + # Convert to PIL Image + category_masks[category] = Image.fromarray(merged_mask, mode='RGB') + + return category_masks + +def sort_instances_by_distance_to_origin(instances): + return sorted(instances, key=lambda x: x.get('bbox')[0]**2 + x.get('bbox')[1]**2) + +def sort_instances_by_raster(instances): + return sorted(instances, key=lambda obj: (obj['bbox'][1], obj['bbox'][0])) diff --git a/data/interleave_datasets/edit_dataset.py b/data/interleave_datasets/edit_dataset.py new file mode 100644 index 0000000000000000000000000000000000000000..ec72e2e4490855b3b20a099fb340c3b107358c91 --- /dev/null +++ b/data/interleave_datasets/edit_dataset.py @@ -0,0 +1,72 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +import io +import random +from PIL import Image, ImageFile, PngImagePlugin + +from .interleave_t2i_dataset import InterleavedBaseIterableDataset, ParquetStandardIterableDataset +from ..data_utils import pil_img2rgb + + +Image.MAX_IMAGE_PIXELS = 200000000 +ImageFile.LOAD_TRUNCATED_IMAGES = True +MaximumDecompressedSize = 1024 +MegaByte = 2 ** 20 +PngImagePlugin.MAX_TEXT_CHUNK = MaximumDecompressedSize * MegaByte + + +class UnifiedEditIterableDataset(InterleavedBaseIterableDataset, ParquetStandardIterableDataset): + + def parse_row(self, row): + image_num = len(row["image_list"]) + # randomly choose start and end, return [0, 1] when only two images + start_idx = random.choice(range(image_num - 1)) + max_end = min(start_idx + 3, image_num) + end_idx = random.choice(range(start_idx + 1, max_end)) + + data = self._init_data() + data = self._add_image( + data, + pil_img2rgb(Image.open(io.BytesIO(row["image_list"][start_idx]))), + need_loss=False, + need_vae=True, + need_vit=True, + ) + + if end_idx - start_idx > 1 and random.random() < 0.5: # concat multiple insturction + if end_idx == image_num - 1: + end_idx -= 1 + + instruction = "" + for idx in range(start_idx + 1, end_idx + 1): + instruction += random.choice(row["instruction_list"][idx-1]) + ". " + data = self._add_text(data, instruction.rstrip(), need_loss=False) + data = self._add_image( + data, + pil_img2rgb(Image.open(io.BytesIO(row["image_list"][end_idx]))), + need_loss=True, + need_vae=False, + need_vit=False, + ) + else: + for idx in range(start_idx + 1, end_idx + 1): + instruction = random.choice(row["instruction_list"][idx-1]) + data = self._add_text(data, instruction, need_loss=False) + if idx != end_idx: + data = self._add_image( + data, + pil_img2rgb(Image.open(io.BytesIO(row["image_list"][idx]))), + need_loss=True, + need_vae=True, + need_vit=True, + ) + else: + data = self._add_image( + data, + pil_img2rgb(Image.open(io.BytesIO(row["image_list"][idx]))), + need_loss=True, + need_vae=False, + need_vit=False, + ) + return data diff --git a/data/interleave_datasets/hunyuan_native_chat_any2any_dataset.py b/data/interleave_datasets/hunyuan_native_chat_any2any_dataset.py new file mode 100644 index 0000000000000000000000000000000000000000..ae8eaba467b356ba350f6f3fa33e7adc4c48ab30 --- /dev/null +++ b/data/interleave_datasets/hunyuan_native_chat_any2any_dataset.py @@ -0,0 +1,257 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +"""Hunyuan-native chat serialization for MODUS any2any parquet datasets. + +This file is intentionally separate from ``any2any_dataset.py`` so v59 can +change the Hunyuan training contract without changing the default MODUS/BAGEL +dataloader class. +""" + +import os + +from .any2any_dataset import UnifiedAny2AnyIterableDataset + + +class HunyuanNativeChatAny2AnyIterableDataset(UnifiedAny2AnyIterableDataset): + """v59 dataset: native chat shell plus MODUS modality blocks. + + Text that belongs to the chat template is emitted as raw tokenizer ids, so + it is not wrapped by MODUS text BOS/EOS tokens. Supervised text targets keep + the legacy ``text`` item type because the shared packer already implements + shifted CE labels for that path. + """ + + def _native_chat_serialization(self): + return True + + def _native_aligned_serialization(self): + return True + + def _strict_native_image_block(self): + return os.environ.get("HUNYUAN_STRICT_NATIVE_IMAGE_BLOCK", "0") == "1" + + # --- native multi-resolution helpers --------------------------------- + # Generation-target size tiers (base_size), capped at 1024 so a 512 image + # keeps 512 instead of being forced to a single fixed 1024 tier. Each tier + # is a real token the model was pretrained with. + _NATIVE_SIZE_TIERS = [256, 512, 768, 1024] + + def _native_reso_groups(self): + groups = getattr(self, "_native_reso_groups_cache", None) + if groups is None: + from modeling.hunyuan_image_3.src.tokenization_hunyuan_image_3 import ResolutionGroup + stride = self.transform.stride + groups = {b: ResolutionGroup(base_size=b, align=stride) for b in self._NATIVE_SIZE_TIERS} + self._native_reso_groups_cache = groups + return groups + + def _pick_native_size_ratio(self, width, height): + """Map an actual (per-image, <=1024) gen-target tensor to the nearest + native (size-tier, aspect-ratio) bucket, so the emitted + / tokens honestly describe the latent instead of + a hardcoded 1024. Bucket dims are stride-aligned -> exact token count. + Returns (base_size, ratio_idx, bucket_w, bucket_h).""" + import numpy as np + groups = self._native_reso_groups() + eff = (width * height) ** 0.5 + base_size = min(self._NATIVE_SIZE_TIERS, key=lambda b: abs(b - eff)) + group = groups[base_size] + ratio_idx = int(np.argmin(np.abs(group.ratio - (height / width)))) + reso = group.data[ratio_idx] + return base_size, ratio_idx, reso.w, reso.h + + def _add_raw_text(self, data, text, need_loss=False, enable_cfg=True, modality_type='text'): + if need_loss: + raise NotImplementedError("raw_text is only used for no-loss chat scaffolding") + text_ids = self.tokenizer.encode(text) + data['num_tokens'] += len(text_ids) + data['text_ids_list'].append(text_ids) + data['sequence_plan'].append( + { + 'type': 'raw_text', + 'enable_cfg': int(enable_cfg), + 'loss': 0, + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + return data + + def _add_native_chat_preamble(self, data): + data = self._add_raw_text( + data, + f"{self.NATIVE_CHAT_SYSTEM_PROMPT}\n\nUser:\n", + need_loss=False, + enable_cfg=False, + modality_type='text', + ) + return data + + def _add_native_chat_assistant_prefix(self, data): + return self._add_raw_text( + data, + "\nAssistant: ", + need_loss=False, + enable_cfg=False, + modality_type='text', + ) + + def _add_answer_suffix(self, data): + return self._add_raw_text( + data, + "", + need_loss=False, + enable_cfg=False, + modality_type='text', + ) + + def _feature_boundary(self, modality_type, close=False): + if close: + return f"" + return f"" + + def _add_text(self, data, text, need_loss, enable_cfg=True, modality_type=None): + if not need_loss: + return self._add_raw_text( + data, + f"{text}\n", + need_loss=False, + enable_cfg=enable_cfg, + modality_type='text', + ) + + if modality_type in ('caption', 'det', 'grounding') and not str(text).endswith(""): + text = f"{text}" + return super()._add_text(data, text, need_loss, enable_cfg, modality_type) + + def _add_image(self, data, image, need_loss, need_vae, need_vit, enable_cfg=True, modality_type=None): + if self._strict_native_image_block() and need_loss and not need_vae and not need_vit: + image_tensor = self.transform(image) + height, width = image_tensor.shape[1:] + # Native multi-resolution: snap the per-image gen target to the + # nearest (size-tier, aspect-ratio) bucket (tiers capped at 1024) so + # the / metadata honestly matches the latent + # token count -- a 512 image emits , not a fixed 1024. + base_size, ratio_idx, bw, bh = self._pick_native_size_ratio(width, height) + if (width, height) != (bw, bh): + import torch.nn.functional as _F + image_tensor = _F.interpolate( + image_tensor.unsqueeze(0), size=(bh, bw), + mode='bilinear', align_corners=False, + ).squeeze(0) + height, width = bh, bw + data['num_tokens'] += width * height // self.transform.stride ** 2 + 5 + data['image_tensor_list'].append(image_tensor) + data['sequence_plan'].append( + { + 'type': 'native_gen_image', + 'enable_cfg': 0, + 'loss': 1, + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + 'base_size': base_size, + 'ratio_idx': ratio_idx, + } + ) + data = self._add_answer_suffix(data) + return data + + if self._strict_native_image_block() and (not need_loss) and need_vae and need_vit: + vae_image_tensor = self.transform(image) + vit_image_tensor = self.vit_transform(image) + vh, vw = vae_image_tensor.shape[1:] + th, tw = vit_image_tensor.shape[1:] + data['num_tokens'] += ( + vh * vw // self.transform.stride ** 2 + + th * tw // self.vit_transform.stride ** 2 + + 3 + ) + data['image_tensor_list'].append(vae_image_tensor) + data['image_tensor_list'].append(vit_image_tensor) + data['sequence_plan'].append( + { + 'type': 'native_cond_joint_image', + 'enable_cfg': int(enable_cfg), + 'loss': 0, + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + return data + + data = super()._add_image( + data, + image, + need_loss=need_loss, + need_vae=need_vae, + need_vit=need_vit, + enable_cfg=enable_cfg, + modality_type=modality_type, + ) + if need_loss: + data = self._add_answer_suffix(data) + return data + + def _add_dino(self, data, dino_tokens, need_loss, enable_cfg, modality_type): + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"{self._feature_boundary(modality_type)}\n", False, False, 'text') + data = super()._add_dino(data, dino_tokens, need_loss, enable_cfg, modality_type) + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"\n{self._feature_boundary(modality_type, close=True)}", False, False, 'text') + if need_loss: + data = self._add_answer_suffix(data) + return data + + def _add_dinolocal(self, data, dino_tokens, need_loss, enable_cfg, modality_type): + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"{self._feature_boundary(modality_type)}\n", False, False, 'text') + data = super()._add_dinolocal(data, dino_tokens, need_loss, enable_cfg, modality_type) + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"\n{self._feature_boundary(modality_type, close=True)}", False, False, 'text') + if need_loss: + data = self._add_answer_suffix(data) + return data + + def _add_clip(self, data, clip_tokens, need_loss, enable_cfg, modality_type): + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"{self._feature_boundary(modality_type)}\n", False, False, 'text') + data = super()._add_clip(data, clip_tokens, need_loss, enable_cfg, modality_type) + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"\n{self._feature_boundary(modality_type, close=True)}", False, False, 'text') + if need_loss: + data = self._add_answer_suffix(data) + return data + + def _add_imagebind(self, data, imagebind_tokens, need_loss, enable_cfg, modality_type): + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"{self._feature_boundary(modality_type)}\n", False, False, 'text') + data = super()._add_imagebind(data, imagebind_tokens, need_loss, enable_cfg, modality_type) + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"\n{self._feature_boundary(modality_type, close=True)}", False, False, 'text') + if need_loss: + data = self._add_answer_suffix(data) + return data + + def _add_imagebindlocal(self, data, imagebind_tokens, need_loss, enable_cfg, modality_type): + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"{self._feature_boundary(modality_type)}\n", False, False, 'text') + data = super()._add_imagebindlocal(data, imagebind_tokens, need_loss, enable_cfg, modality_type) + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"\n{self._feature_boundary(modality_type, close=True)}", False, False, 'text') + if need_loss: + data = self._add_answer_suffix(data) + return data + + def _add_cocodet(self, data, detections, image_size, need_loss, enable_cfg, modality_type): + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"{self._feature_boundary(modality_type)}\n", False, False, 'text') + data = super()._add_cocodet(data, detections, image_size, need_loss, enable_cfg, modality_type) + if self._strict_native_image_block(): + data = self._add_raw_text(data, f"\n{self._feature_boundary(modality_type, close=True)}", False, False, 'text') + if need_loss: + data = self._add_answer_suffix(data) + return data diff --git a/data/interleave_datasets/interleave_t2i_dataset.py b/data/interleave_datasets/interleave_t2i_dataset.py new file mode 100644 index 0000000000000000000000000000000000000000..4738fe0274766e86c66ee5931c91722e5e212406 --- /dev/null +++ b/data/interleave_datasets/interleave_t2i_dataset.py @@ -0,0 +1,376 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +import json +import os + +import pyarrow.parquet as pq + +from ..distributed_iterable_dataset import DistributedIterableDataset +from ..parquet_utils import get_parquet_data_paths, init_arrow_pf_fs, strip_s3_scheme + + +class InterleavedBaseIterableDataset(DistributedIterableDataset): + + def _init_data(self): + data = { + 'sequence_plan': [], + 'text_ids_list': [], + 'image_tensor_list': [], + 'num_tokens': 0, + } + return data + + def _add_text(self, data, text, need_loss, enable_cfg=True, modality_type=None): + text_ids = self.tokenizer.encode(text) + data['num_tokens'] += len(text_ids) + data['text_ids_list'].append(text_ids) + data['sequence_plan'].append( + { + 'type': 'text', + 'enable_cfg': int(enable_cfg), + 'loss': int(need_loss), + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + return data + + def _add_image(self, data, image, need_loss, need_vae, need_vit, enable_cfg=True, modality_type=None): + assert need_loss or need_vae or need_vit + + if need_loss: + data['sequence_plan'].append( + { + 'type': 'vae_image', + 'enable_cfg': 0, + 'loss': 1, + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + + image_tensor = self.transform(image) + height, width = image_tensor.shape[1:] + data['num_tokens'] += width * height // self.transform.stride ** 2 + data['image_tensor_list'].append(image_tensor) + + if need_vae: + data['sequence_plan'].append( + { + 'type': 'vae_image', + 'enable_cfg': int(enable_cfg), + 'loss': 0, + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + } + ) + + image_tensor = self.transform(image) + height, width = image_tensor.shape[1:] + data['num_tokens'] += width * height // self.transform.stride ** 2 + data['image_tensor_list'].append(image_tensor.clone()) + + if need_vit: + data['sequence_plan'].append( + { + 'type': 'vit_image', + 'enable_cfg': int(enable_cfg), + 'loss': 0, + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': modality_type, + }, + ) + vit_image_tensor = self.vit_transform(image) + height, width = vit_image_tensor.shape[1:] + data['num_tokens'] += width * height // self.vit_transform.stride ** 2 + data['image_tensor_list'].append(vit_image_tensor) + + return data + + def _add_video(self, data, frames, frame_indexes, need_loss, need_vae, enable_cfg=True): + assert int(need_loss) + int(need_vae) == 1 + + if need_loss: + for idx, (image, frame_idx) in enumerate(zip(frames, frame_indexes)): + current_sequence_plan = { + 'type': 'vae_image', + 'enable_cfg': 0, + 'loss': 1, + 'special_token_loss': 0, + 'special_token_label': None, + 'split_start': idx == 0, + 'split_end': idx == len(frames) - 1, + } + if idx < len(frame_indexes) - 1: + current_sequence_plan['frame_delta'] = frame_indexes[idx + 1] - frame_idx + data['sequence_plan'].append(current_sequence_plan) + image_tensor = self.transform(image) + height, width = image_tensor.shape[1:] + data['image_tensor_list'].append(image_tensor) + data['num_tokens'] += width * height // self.transform.stride ** 2 + + elif need_vae: + for idx, (image, frame_idx) in enumerate(zip(frames, frame_indexes)): + current_sequence_plan = { + 'type': 'vae_image', + 'enable_cfg': int(enable_cfg), + 'loss': 0, + 'special_token_loss': 0, + 'special_token_label': None, + 'split_start': idx == 0, + 'split_end': idx == len(frames) - 1, + } + if idx < len(frame_indexes) - 1: + current_sequence_plan['frame_delta'] = frame_indexes[idx + 1] - frame_idx + data['sequence_plan'].append(current_sequence_plan) + image_tensor = self.transform(image) + height, width = image_tensor.shape[1:] + data['image_tensor_list'].append(image_tensor) + data['num_tokens'] += width * height // self.transform.stride ** 2 + + return data + + +class ParquetStandardIterableDataset(DistributedIterableDataset): + + def __init__( + self, dataset_name, transform, tokenizer, vit_transform, + data_dir_list, num_used_data, parquet_info, + local_rank=0, world_size=1, num_workers=8, data_status=None, + use_instruction=False, use_condition_instruction=True, use_target_instruction=True, + num_condition_modalities=1, + strict_num_condition_modalities=False, + use_det_image=False, + modality_registry=None, + tail_n_rows=None, + force_condition_modality=None, + force_condition_modalities=None, + pred_intermediate_dir=None, + gt_restricted_dir=None, + fixed_row_list_path=None, + ): + """ + data_dir_list: list of data directories contains parquet files + num_used_data: list of number of sampled data paths for each data directory + vit_transform: input transform for vit model. + tail_n_rows: if set, only the last N rows of each row-group are yielded + (held-out validation slice; default None preserves training behavior). + force_condition_modality: if set, every sample uses exactly this single + condition modality (used by the validation matrix script). Default + None preserves training behavior (random sampling). + """ + super().__init__(dataset_name, local_rank, world_size, num_workers) + self.transform = transform + self.vit_transform = vit_transform + self.tokenizer = tokenizer + self.data_status = data_status + self.data_paths = self.get_data_paths(data_dir_list, num_used_data, parquet_info) + # Pred-intermediate mode: keep only (file, rg) pairs that have at + # least one Phase-1-saved PNG. Otherwise distributed ranks whose + # data slice contains no pred PNGs would iterate forever skipping + # every row and deadlock at NCCL all-reduce. Done BEFORE set_epoch + # so the shuffle+chunk operates on the filtered set. + # + # gt_restricted_dir is the apples-to-apples sibling: applies the + # SAME pair filter (so the GT matrix runs on the exact same 8 pairs + # PRED uses) but does NOT substitute pred PNGs — the intermediate + # condition is still loaded from parquet GT. Used to compare GT vs + # PRED on identical sample slices. + self.pred_intermediate_dir = pred_intermediate_dir + self.gt_restricted_dir = gt_restricted_dir + _filter_dir = pred_intermediate_dir or gt_restricted_dir + if _filter_dir is not None: + self.data_paths = self._filter_data_paths_by_pred( + self.data_paths, _filter_dir) + + # Fixed val set mode: V_fixed.json lists exact (basename, rg, row) + # tuples to use. Each row is keyed (basename, rg, row_idx) → + # global_idx for deterministic rank striping. Pairs are filtered + # to only those touched by V_fixed. + self.fixed_row_list_path = fixed_row_list_path + self._fixed_rows_by_pair = None # (basename, rg) -> set(row_idx) + self._fixed_global_idx = None # (basename, rg, row_idx) -> global_idx + if fixed_row_list_path is not None: + with open(fixed_row_list_path, "r") as _f: + _payload = json.load(_f) + _rows = _payload.get("rows", _payload) # accept bare list too + _by_pair = {} + _gidx = {} + for r in _rows: + key_pair = (r["parquet_basename"], int(r["rg_id"])) + _by_pair.setdefault(key_pair, set()).add(int(r["row_idx"])) + _gidx[(r["parquet_basename"], int(r["rg_id"]), int(r["row_idx"]))] = ( + int(r.get("global_idx", len(_gidx)))) + self._fixed_rows_by_pair = _by_pair + self._fixed_global_idx = _gidx + # Filter data_paths to only the (file, rg) pairs touched by V_fixed. + _keep = set(_by_pair.keys()) + _filtered = [] + for path, rg in self.data_paths: + base = os.path.splitext(os.path.basename(path))[0] + if (base, int(rg)) in _keep: + _filtered.append((path, rg)) + print(f"[fixed-row] V_fixed has {len(_rows)} rows across " + f"{len(_by_pair)} pairs; kept {len(_filtered)} matching " + f"data_paths (out of {len(self.data_paths)})") + self.data_paths = _filtered + + self.set_epoch() + self.use_instruction = use_instruction + self.use_condition_instruction = use_condition_instruction + self.use_target_instruction = use_target_instruction + self.num_condition_modalities = num_condition_modalities + self.strict_num_condition_modalities = strict_num_condition_modalities + self.use_det_image = use_det_image + self.modality_registry = modality_registry + self.tail_n_rows = tail_n_rows + self.force_condition_modality = force_condition_modality + self.force_condition_modalities = force_condition_modalities + print(f"use_instruction: {self.use_instruction}") + + def _filter_data_paths_by_pred(self, data_paths, pred_intermediate_dir): + """Keep only (parquet_path, rg_id) pairs covered by Phase-1 outputs. + Phase 1 writes files as + //_rg_row*_pred.png + We consider a pair 'covered' if ANY modality subdir has at least + one PNG matching `_rg_row*_pred.png`. + Backward compat: only invoked when pred_intermediate_dir is set. + """ + import glob as _glob + covered = set() + if not os.path.isdir(pred_intermediate_dir): + print(f'[pred-filter] WARN: pred_intermediate_dir not found: {pred_intermediate_dir}') + return [] + # Scan each modality subdir, harvest (basename, rg_id) keys. + for sub in os.listdir(pred_intermediate_dir): + sub_dir = os.path.join(pred_intermediate_dir, sub) + if not os.path.isdir(sub_dir): + continue + for fn in os.listdir(sub_dir): + if not fn.endswith('_pred.png'): + continue + # filename: _rg_row_pred.png + # split from the right: ['_pred.png'] then row, rg, basename + stem = fn[:-len('_pred.png')] + # find last '_row' before number + idx_row = stem.rfind('_row') + if idx_row < 0: + continue + pre_row = stem[:idx_row] # _rg + idx_rg = pre_row.rfind('_rg') + if idx_rg < 0: + continue + basename = pre_row[:idx_rg] + try: + rg_id = int(pre_row[idx_rg + len('_rg'):]) + except ValueError: + continue + covered.add((basename, rg_id)) + filtered = [] + for path, rg in data_paths: + base = os.path.splitext(os.path.basename(path))[0] + if (base, rg) in covered: + filtered.append((path, rg)) + print(f'[pred-filter] kept {len(filtered)}/{len(data_paths)} (file, rg) pairs ' + f'covered by pred_intermediate_dir={pred_intermediate_dir}') + return filtered + + def get_data_paths(self, data_dir_list, num_used_data, parquet_info): + # Index parquet_info by basename too, so the lookup is independent of the + # data_dir prefix (local path vs s3://...). Basenames are unique within a + # dataset's parquet_info, so this is equivalent to exact-path matching for + # existing local runs (forward-compatible) while letting an s3:// data_dir + # reuse the same JSON unchanged. + info_by_base = {os.path.basename(k): v for k, v in parquet_info.items()} + row_groups = [] + for data_dir, num_data_path in zip(data_dir_list, num_used_data): + data_paths = get_parquet_data_paths([data_dir], [num_data_path]) + for data_path in data_paths: + info = parquet_info.get(data_path) or info_by_base.get(os.path.basename(data_path)) + if info is not None: + num_row_groups = info['num_row_groups'] + for rg_idx in range(num_row_groups): + row_groups.append((data_path, rg_idx)) + return row_groups + + def parse_row(self, row): + raise NotImplementedError + + def __iter__(self): + file_paths_per_worker, worker_id = self.get_data_paths_per_worker() + if self.data_status is not None: + global_row_group_start_id = self.data_status[worker_id][0] + row_start_id = self.data_status[worker_id][1] + 1 + else: + global_row_group_start_id = 0 + row_start_id = 0 + + print( + f"rank-{self.local_rank} worker-{worker_id} dataset-{self.dataset_name}: " + f"resuming data at global_rg#{global_row_group_start_id}, row#{row_start_id}" + ) + + while True: + file_paths_per_worker_ = file_paths_per_worker[global_row_group_start_id:] + for global_row_group_idx, (parquet_file_path, row_group_id) in enumerate( + file_paths_per_worker_, start=global_row_group_start_id + ): + fs = init_arrow_pf_fs(parquet_file_path) + with fs.open_input_file(strip_s3_scheme(parquet_file_path)) as f: + try: + fr = pq.ParquetFile(f) + df = fr.read_row_group(row_group_id).to_pandas() + if self.tail_n_rows is not None and self.tail_n_rows > 0: + df = df.iloc[-int(self.tail_n_rows):] + df = df.iloc[row_start_id:] + except Exception as e: + print(f'Error {e} in rg#{row_group_id}, {parquet_file_path}') + continue + + # Fixed val set: pre-compute which row_idxs of THIS + # (file, rg) pair are in V_fixed. Skip rows not in the + # set. No-op when fixed_row_list_path is None. + _fixed_set_for_pair = None + if self._fixed_rows_by_pair is not None: + _basename = os.path.splitext( + os.path.basename(parquet_file_path))[0] + _fixed_set_for_pair = self._fixed_rows_by_pair.get( + (_basename, int(row_group_id)), set()) + + for row_idx, row in df.iterrows(): + try: + if _fixed_set_for_pair is not None and int(row_idx) not in _fixed_set_for_pair: + continue + # Expose per-row parquet provenance to subclasses + # via transient attrs (subclasses ignore if unused). + # Backward compatible — old code paths don't read these. + self._current_parquet_path = parquet_file_path + self._current_rg_id = row_group_id + self._current_row_idx = row_idx + data = self.parse_row(row) + if data is None or len(data) == 0: + continue + data['data_indexes'] = { + "data_indexes": [global_row_group_idx, row_idx], + "worker_id": worker_id, + "dataset_name": self.dataset_name, + } + except Exception as e: + # Silently skip rows whose pred-intermediate + # PNG is missing — that's the expected case + # outside Phase 1's generated subset, not an + # error. + if type(e).__name__ == 'PredIntermediateMissing': + continue + print(f'Error {e} in rg#{row_group_id}, {parquet_file_path}') + continue + yield data + + row_start_id = 0 + global_row_group_start_id = 0 + print(f"{self.dataset_name} repeat in rank-{self.local_rank} worker-{worker_id}") diff --git a/data/parquet_utils.py b/data/parquet_utils.py new file mode 100644 index 0000000000000000000000000000000000000000..aabd5d3cbbac1081bc95e35bc1748a181bc05594 --- /dev/null +++ b/data/parquet_utils.py @@ -0,0 +1,153 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + + +import os +import subprocess +import logging + +import pyarrow.fs as pf +import torch.distributed as dist + +logger = logging.getLogger(__name__) + + +def apply_data_root_override(path): + # If MODUS_DATA_ROOT is set, replace the local 'datasets/' prefix with it, + # preserving the sub-path. This mirrors the datasets/ tree under the root and + # works for BOTH parquet dirs (datasets/blip3o/parquet_...) and vlm_sft + # image/jsonl paths (datasets/llava_onevision_vqa//...). Switching + # local<->S3 — and 13mod<->16mod<->Hunyuan — becomes a pure env/config change + # with NO edit to dataset_info.py. Paths not under datasets/ and the unset + # case are returned unchanged (forward-compatible). + root = os.environ.get("MODUS_DATA_ROOT") + if not root: + return path + for prefix in ("./datasets/", "datasets/"): + if path.startswith(prefix): + return root.rstrip("/") + "/" + path[len(prefix):] + return path + + +def read_file_bytes(path): + # Read a whole file as bytes, scheme-selected (local / hdfs / s3) via the same + # filesystem logic as parquet. Used for S3 streaming of vlm_sft jsonl + images. + fs = init_arrow_pf_fs(path) + with fs.open_input_file(strip_s3_scheme(path)) as f: + return f.read() + + +def get_parquet_data_paths(data_dir_list, num_sampled_data_paths, rank=0, world_size=1): + data_dir_list = [apply_data_root_override(d) for d in data_dir_list] + num_data_dirs = len(data_dir_list) + if world_size > 1: + chunk_size = (num_data_dirs + world_size - 1) // world_size + start_idx = rank * chunk_size + end_idx = min(start_idx + chunk_size, num_data_dirs) + local_data_dir_list = data_dir_list[start_idx:end_idx] + local_num_sampled_data_paths = num_sampled_data_paths[start_idx:end_idx] + else: + local_data_dir_list = data_dir_list + local_num_sampled_data_paths = num_sampled_data_paths + + local_data_paths = [] + for data_dir, num_data_path in zip(local_data_dir_list, local_num_sampled_data_paths): + if data_dir.startswith("hdfs://"): + files = hdfs_ls_cmd(data_dir) + data_paths_per_dir = [ + file for file in files if file.endswith(".parquet") + ] + elif data_dir.startswith("s3://"): + fs = init_arrow_pf_fs(data_dir) + selector = pf.FileSelector(strip_s3_scheme(data_dir), recursive=False) + data_paths_per_dir = [ + "s3://" + info.path + for info in fs.get_file_info(selector) + if info.path.endswith(".parquet") + ] + else: + files = os.listdir(data_dir) + data_paths_per_dir = [ + os.path.join(data_dir, name) + for name in files + if name.endswith(".parquet") + ] + if num_data_path is None: + # None → use every parquet file in the dir exactly once + # (no repeat/truncate). Used by vlm_sft_parquet where the + # sample selection is already baked in at conversion time. + local_data_paths.extend(data_paths_per_dir) + continue + repeat = num_data_path // len(data_paths_per_dir) + data_paths_per_dir = data_paths_per_dir * (repeat + 1) + local_data_paths.extend(data_paths_per_dir[:num_data_path]) + + if world_size > 1: + gather_list = [None] * world_size + dist.all_gather_object(gather_list, local_data_paths) + + combined_chunks = [] + for chunk_list in gather_list: + if chunk_list is not None: + combined_chunks.extend(chunk_list) + else: + combined_chunks = local_data_paths + + return combined_chunks + + +# NOTE: cumtomize this function for your cluster +def get_hdfs_host(): + return "hdfs://xxx" + + +# NOTE: cumtomize this function for your cluster +def get_hdfs_block_size(): + return 134217728 + + +# NOTE: cumtomize this function for your cluster +def get_hdfs_extra_conf(): + return None + + +def strip_s3_scheme(path): + # pyarrow's S3FileSystem operates on 'bucket/key' (no scheme). Local/hdfs + # paths are returned unchanged, so their behavior is untouched. + if path.startswith("s3://"): + return path[len("s3://"):] + return path + + +def init_arrow_pf_fs(parquet_file_path): + if parquet_file_path.startswith("hdfs://"): + fs = pf.HadoopFileSystem( + host=get_hdfs_host(), + port=0, + buffer_size=get_hdfs_block_size(), + extra_conf=get_hdfs_extra_conf(), + ) + elif parquet_file_path.startswith("s3://"): + # Credentials + endpoint come from the environment so no secrets live in + # code/config. Standard AWS_* names work; MODUS_S3_ENDPOINT/REGION/SCHEME + # cover custom (non-AWS) S3 endpoints (e.g. Apple conductor, SCITAS). + s3_kwargs = dict( + access_key=os.environ.get("AWS_ACCESS_KEY_ID"), + secret_key=os.environ.get("AWS_SECRET_ACCESS_KEY"), + scheme=os.environ.get("MODUS_S3_SCHEME", "https"), + ) + if os.environ.get("MODUS_S3_ENDPOINT"): + s3_kwargs["endpoint_override"] = os.environ["MODUS_S3_ENDPOINT"] + if os.environ.get("MODUS_S3_REGION"): + s3_kwargs["region"] = os.environ["MODUS_S3_REGION"] + if os.environ.get("AWS_SESSION_TOKEN"): + s3_kwargs["session_token"] = os.environ["AWS_SESSION_TOKEN"] + fs = pf.S3FileSystem(**s3_kwargs) + else: + fs = pf.LocalFileSystem() + return fs + + +def hdfs_ls_cmd(dir): + result = subprocess.run(["hdfs", "dfs", "ls", dir], capture_output=True, text=True).stdout + return ['hdfs://' + i.split('hdfs://')[-1].strip() for i in result.split('\n') if 'hdfs://' in i] diff --git a/data/t2i_dataset.py b/data/t2i_dataset.py new file mode 100644 index 0000000000000000000000000000000000000000..0d2cce17563f6805abd785dcdecf1b47f7db6c0b --- /dev/null +++ b/data/t2i_dataset.py @@ -0,0 +1,131 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +import io +import json +import pyarrow.parquet as pq +import random +from PIL import Image + +from .data_utils import pil_img2rgb +from .distributed_iterable_dataset import DistributedIterableDataset +from .parquet_utils import get_parquet_data_paths, init_arrow_pf_fs, strip_s3_scheme + +Image.MAX_IMAGE_PIXELS = 20_000_000 + + +class T2IIterableDataset(DistributedIterableDataset): + def __init__( + self, dataset_name, transform, tokenizer, data_dir_list, num_used_data, + local_rank=0, world_size=1, num_workers=8, data_status=None, use_instruction=False, + use_condition_instruction=False, use_target_instruction=False, num_condition_modalities=0, + strict_num_condition_modalities=False, + use_det_image=False, modality_registry=None, + ): + """ + data_dir_list: list of data directories contains parquet files + num_used_data: list of number of sampled data paths for each data directory + """ + super().__init__(dataset_name, local_rank, world_size, num_workers) + self.transform = transform + self.tokenizer = tokenizer + self.data_status = data_status + self.data_paths = self.get_data_paths(data_dir_list, num_used_data) + self.set_epoch() + + def get_data_paths(self, data_dir_list, num_used_data): + return get_parquet_data_paths(data_dir_list, num_used_data) + + def __iter__(self): + data_paths_per_worker, worker_id = self.get_data_paths_per_worker() + if self.data_status is not None: + parquet_start_id = self.data_status[worker_id][0] + row_group_start_id = self.data_status[worker_id][1] + row_start_id = self.data_status[worker_id][2] + 1 + else: + parquet_start_id = 0 + row_group_start_id = 0 + row_start_id = 0 + transform_stride = self.transform.stride + + print( + f"rank-{self.local_rank} worker-{worker_id} dataset-{self.dataset_name}: " + f"resuming data at parquet#{parquet_start_id}, rg#{row_group_start_id}, row#{row_start_id}" + ) + + while True: + data_paths_per_worker_ = data_paths_per_worker[parquet_start_id:] + for parquet_idx, parquet_file_path in enumerate(data_paths_per_worker_, start=parquet_start_id): + fs = init_arrow_pf_fs(parquet_file_path) + with fs.open_input_file(strip_s3_scheme(parquet_file_path)) as f: + fr = pq.ParquetFile(f) + row_group_ids = list(range(fr.num_row_groups)) + row_group_ids_ = row_group_ids[row_group_start_id:] + + for row_group_id in row_group_ids_: + df = fr.read_row_group(row_group_id).to_pandas() + df = df.iloc[row_start_id:] + + for row_idx, row in df.iterrows(): + num_tokens = 0 + try: + image_byte = row['image'] + image = pil_img2rgb(Image.open(io.BytesIO(image_byte))) + except Exception as e: + print(f'Error: {e} in rg#{row_group_id}, {parquet_file_path}') + continue + image_tensor = self.transform(image) + height, width = image_tensor.shape[1:] + num_tokens += width * height // transform_stride ** 2 + + try: + caption_dict = row['captions'] + caption_dict = json.loads(caption_dict) + except Exception as e: + print(f'Error: {e} in rg#{row_group_id}, {parquet_file_path}') + continue + + caps_token = [self.tokenizer.encode(v) for _, v in caption_dict.items()] + if len(caps_token) == 0: + print(f'no caption in rg#{row_group_id}, {parquet_file_path}') + caption_token = self.tokenizer.encode(' ') + else: + caption_token = random.choice(caps_token) + + sequence_plan, text_ids_list = [], [] + text_ids = caption_token + num_tokens += len(caption_token) + text_ids_list.append(text_ids) + sequence_plan.append({ + 'type': 'text', + 'enable_cfg': 1, + 'loss': 0, + 'special_token_loss': 0, + 'special_token_label': None, + }) + + sequence_plan.append({ + 'type': 'vae_image', + 'enable_cfg': 0, + 'loss': 1, + 'special_token_loss': 0, + 'special_token_label': None, + }) + + sample = dict( + image_tensor_list=[image_tensor], + text_ids_list=text_ids_list, + num_tokens=num_tokens, + sequence_plan=sequence_plan, + data_indexes={ + "data_indexes": [parquet_idx, row_group_id, row_idx], + "worker_id": worker_id, + "dataset_name": self.dataset_name, + } + ) + yield sample + + row_start_id = 0 + row_group_start_id = 0 + parquet_start_id = 0 + print(f"{self.dataset_name} repeat in rank-{self.local_rank} worker-{worker_id}") diff --git a/data/transforms.py b/data/transforms.py new file mode 100644 index 0000000000000000000000000000000000000000..89953b8bd5d6738fef7f611951e41d40941844aa --- /dev/null +++ b/data/transforms.py @@ -0,0 +1,322 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +import random +from PIL import Image + +import cv2 +import numpy as np +import torch +import torch.nn.functional as _F + +# torchvision-free replacements: the HF ZeroGPU base image ships a custom torch +# with no matching torchvision wheel, and installing one downgrades torch and +# breaks ZeroGPU. For PIL inputs these are numerically identical to torchvision +# (F.resize on a PIL image delegates to PIL.Image.resize; ToTensor/Normalize are +# plain arithmetic). Set MODUS_FORCE_SDPA_ATTN-style parity was validated on-cluster. +_PIL_RESAMPLE = {"bicubic": Image.BICUBIC, "bilinear": Image.BILINEAR, "nearest": Image.NEAREST} + + +class InterpolationMode: + BICUBIC = "bicubic" + BILINEAR = "bilinear" + NEAREST = "nearest" + + +def _resize(img, size, interpolation="bicubic", antialias=True): + new_h, new_w = size + if isinstance(img, torch.Tensor): + x = img if img.dim() == 4 else img.unsqueeze(0) + aa = antialias and interpolation in ("bicubic", "bilinear") + x = _F.interpolate(x.float(), size=(new_h, new_w), mode=interpolation, + align_corners=False if interpolation != "nearest" else None, + antialias=aa) + return x if img.dim() == 4 else x.squeeze(0) + return img.resize((new_w, new_h), resample=_PIL_RESAMPLE[interpolation]) + + +def _to_tensor(img): + """PIL image -> C×H×W float tensor in [0, 1] (matches transforms.ToTensor).""" + arr = np.asarray(img if img.mode == "RGB" else img.convert("RGB"), dtype=np.uint8) + return torch.from_numpy(arr).permute(2, 0, 1).contiguous().float().div_(255.0) + + +def _normalize(t, mean, std): + m = torch.as_tensor(mean, dtype=t.dtype, device=t.device).view(-1, 1, 1) + s = torch.as_tensor(std, dtype=t.dtype, device=t.device).view(-1, 1, 1) + return t.sub_(m).div_(s) + + +class MaxLongEdgeMinShortEdgeResize(torch.nn.Module): + """Resize the input image so that its longest side and shortest side are within a specified range, + ensuring that both sides are divisible by a specified stride. + + Args: + max_size (int): Maximum size for the longest edge of the image. + min_size (int): Minimum size for the shortest edge of the image. + stride (int): Value by which the height and width of the image must be divisible. + max_pixels (int): Maximum pixels for the full image. + interpolation (InterpolationMode): Desired interpolation enum defined by + :class:`torchvision.transforms.InterpolationMode`. Default is ``InterpolationMode.BILINEAR``. + If input is Tensor, only ``InterpolationMode.NEAREST``, ``InterpolationMode.NEAREST_EXACT``, + ``InterpolationMode.BILINEAR``, and ``InterpolationMode.BICUBIC`` are supported. + The corresponding Pillow integer constants, e.g., ``PIL.Image.BILINEAR`` are also accepted. + antialias (bool, optional): Whether to apply antialiasing (default is True). + """ + + def __init__( + self, + max_size: int, + min_size: int, + stride: int, + max_pixels: int, + interpolation=InterpolationMode.BICUBIC, + antialias=True + ): + super().__init__() + self.max_size = max_size + self.min_size = min_size + self.stride = stride + self.max_pixels = max_pixels + self.interpolation = interpolation + self.antialias = antialias + + def _make_divisible(self, value, stride): + """Ensure the value is divisible by the stride.""" + return max(stride, int(round(value / stride) * stride)) + + def _apply_scale(self, width, height, scale): + new_width = round(width * scale) + new_height = round(height * scale) + new_width = self._make_divisible(new_width, self.stride) + new_height = self._make_divisible(new_height, self.stride) + return new_width, new_height + + def forward(self, img, img_num=1): + """ + Args: + img (PIL Image): Image to be resized. + img_num (int): Number of images, used to change max_tokens. + Returns: + PIL Image or Tensor: Rescaled image with divisible dimensions. + """ + if isinstance(img, torch.Tensor): + height, width = img.shape[-2:] + else: + width, height = img.size + + scale = min(self.max_size / max(width, height), 1.0) + scale = max(scale, self.min_size / min(width, height)) + new_width, new_height = self._apply_scale(width, height, scale) + + # Ensure the number of pixels does not exceed max_pixels + if new_width * new_height > self.max_pixels / img_num: + scale = self.max_pixels / img_num / (new_width * new_height) + new_width, new_height = self._apply_scale(new_width, new_height, scale) + + # Ensure longest edge does not exceed max_size + if max(new_width, new_height) > self.max_size: + scale = self.max_size / max(new_width, new_height) + new_width, new_height = self._apply_scale(new_width, new_height, scale) + + return _resize(img, (new_height, new_width), self.interpolation, antialias=self.antialias) + + +class ImageTransform: + def __init__( + self, + max_image_size, + min_image_size, + image_stride, + max_pixels=14*14*9*1024, + image_mean=[0.5, 0.5, 0.5], + image_std=[0.5, 0.5, 0.5] + ): + self.stride = image_stride + + self.resize_transform = MaxLongEdgeMinShortEdgeResize( + max_size=max_image_size, + min_size=min_image_size, + stride=image_stride, + max_pixels=max_pixels, + ) + self.to_tensor_transform = _to_tensor + self.normalize_transform = lambda t: _normalize(t, image_mean, image_std) + + def __call__(self, img, img_num=1): + img = self.resize_transform(img, img_num=img_num) + img = self.to_tensor_transform(img) + img = self.normalize_transform(img) + return img + + +def decolorization(image): + gray_image = image.convert('L') + return Image.merge(image.mode, [gray_image] * 3) if image.mode in ('RGB', 'L') else gray_image + + +def downscale(image, scale_factor): + new_width = int(round(image.width * scale_factor)) + new_height = int(round(image.height * scale_factor)) + new_width = max(1, new_width) + new_height = max(1, new_height) + return image.resize((new_width, new_height), resample=Image.BICUBIC) + + +def crop(image, crop_factors): + target_h, target_w = crop_factors + img_w, img_h = image.size + + if target_h > img_h or target_w > img_w: + raise ValueError("Crop size exceeds image dimensions") + + x = random.randint(0, img_w - target_w) + y = random.randint(0, img_h - target_h) + + return image.crop((x, y, x + target_w, y + target_h)), [[x, y], [x + target_w, y + target_h]] + + +def motion_blur_opencv(image, kernel_size=15, angle=0): + # 线性核 + kernel = np.zeros((kernel_size, kernel_size), dtype=np.float32) + kernel[kernel_size // 2, :] = np.ones(kernel_size, dtype=np.float32) + + # 旋转核 + center = (kernel_size / 2 - 0.5, kernel_size / 2 - 0.5) + M = cv2.getRotationMatrix2D(center, angle, 1) + rotated_kernel = cv2.warpAffine(kernel, M, (kernel_size, kernel_size)) + + # 归一化核 + rotated_kernel /= rotated_kernel.sum() if rotated_kernel.sum() != 0 else 1 + + img = np.array(image) + if img.ndim == 2: + blurred = cv2.filter2D(img, -1, rotated_kernel, borderType=cv2.BORDER_REFLECT) + else: + # 对于彩色图像,各通道独立卷积 + blurred = np.zeros_like(img) + for c in range(img.shape[2]): + blurred[..., c] = cv2.filter2D(img[..., c], -1, rotated_kernel, borderType=cv2.BORDER_REFLECT) + + return Image.fromarray(blurred.astype(np.uint8)) + + +def shuffle_patch(image, num_splits, gap_size=2): + """将图像分割为块(允许尺寸不整除),随机打乱后拼接,块间保留间隙""" + h_splits, w_splits = num_splits + img_w, img_h = image.size + + base_patch_h = img_h // h_splits + patch_heights = [base_patch_h] * (h_splits - 1) + patch_heights.append(img_h - sum(patch_heights)) + + base_patch_w = img_w // w_splits + patch_widths = [base_patch_w] * (w_splits - 1) + patch_widths.append(img_w - sum(patch_widths)) + + patches = [] + current_y = 0 + for i in range(h_splits): + current_x = 0 + patch_h = patch_heights[i] + for j in range(w_splits): + patch_w = patch_widths[j] + patch = image.crop((current_x, current_y, current_x + patch_w, current_y + patch_h)) + patches.append(patch) + current_x += patch_w + current_y += patch_h + + random.shuffle(patches) + + total_width = sum(patch_widths) + (w_splits - 1) * gap_size + total_height = sum(patch_heights) + (h_splits - 1) * gap_size + new_image = Image.new(image.mode, (total_width, total_height), color=(255, 255, 255)) + + current_y = 0 # 当前行的起始 Y 坐标 + patch_idx = 0 # 当前处理的块索引 + for i in range(h_splits): + current_x = 0 # 当前列的起始 X 坐标 + patch_h = patch_heights[i] # 当前行块的高度 + for j in range(w_splits): + # 取出打乱后的块 + patch = patches[patch_idx] + patch_w = patch_widths[j] # 当前列块的宽度 + # 粘贴块(左上角坐标为 (current_x, current_y)) + new_image.paste(patch, (current_x, current_y)) + # 更新 X 坐标(下一个块的起始位置 = 当前块宽度 + 间隙) + current_x += patch_w + gap_size + patch_idx += 1 + # 更新 Y 坐标(下一行的起始位置 = 当前行高度 + 间隙) + current_y += patch_h + gap_size + + return new_image + + +def inpainting(image, num_splits, blank_ratio=0.3, blank_color=(255, 255, 255)): + """ + 图像分割后随机空白部分patch,用于inpainting任务 + + 参数: + image: PIL.Image 输入图像(RGB模式) + h_splits: int 行分割数(垂直方向分割块数) + w_splits: int 列分割数(水平方向分割块数) + blank_ratio: float 空白patch的比例(0~1) + blank_color: tuple 空白区域的颜色(RGB,如白色(255,255,255)) + + 返回: + PIL.Image 处理后拼接的图像 + """ + h_splits, w_splits = num_splits + img_w, img_h = image.size + + base_patch_h = img_h // h_splits + patch_heights = [base_patch_h] * (h_splits - 1) + patch_heights.append(img_h - sum(patch_heights)) + + base_patch_w = img_w // w_splits + patch_widths = [base_patch_w] * (w_splits - 1) + patch_widths.append(img_w - sum(patch_widths)) + + patches = [] + current_y = 0 + for i in range(h_splits): + current_x = 0 + patch_h = patch_heights[i] + for j in range(w_splits): + patch_w = patch_widths[j] + patch = image.crop((current_x, current_y, current_x + patch_w, current_y + patch_h)) + patches.append(patch) + current_x += patch_w + current_y += patch_h + + total_patches = h_splits * w_splits + num_blank = int(total_patches * blank_ratio) + num_blank = max(0, min(num_blank, total_patches)) + blank_indices = random.sample(range(total_patches), num_blank) + + processed_patches = [] + for idx, patch in enumerate(patches): + if idx in blank_indices: + blank_patch = Image.new("RGB", patch.size, color=blank_color) + processed_patches.append(blank_patch) + else: + processed_patches.append(patch) + + # 创建结果图像(尺寸与原图一致) + result_image = Image.new("RGB", (img_w, img_h)) + current_y = 0 + patch_idx = 0 + for i in range(h_splits): + current_x = 0 + patch_h = patch_heights[i] + for j in range(w_splits): + # 取出处理后的patch + patch = processed_patches[patch_idx] + patch_w = patch_widths[j] + # 粘贴到原位置 + result_image.paste(patch, (current_x, current_y)) + current_x += patch_w + patch_idx += 1 + current_y += patch_h + + return result_image diff --git a/data/video_utils.py b/data/video_utils.py new file mode 100644 index 0000000000000000000000000000000000000000..9b72fc5096207e69333a81388c82609c24e7f48a --- /dev/null +++ b/data/video_utils.py @@ -0,0 +1,165 @@ +# Copyright (c) 2023 OpenGVLab +# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: MIT +# +# This file has been modified by ByteDance Ltd. and/or its affiliates. on 2025-05-20. +# +# Original file was released under MIT, with the full license text +# available at https://github.com/OpenGVLab/InternVL/blob/main/LICENSE. +# +# This modified file is released under the same license. + + +import io +import os +import random +import re + +import numpy as np +import decord +from PIL import Image + + +def get_frame_indices(num_frames, vlen, sample='rand', fix_start=None, input_fps=1, max_num_frames=-1): + if sample in ['rand', 'middle']: # uniform sampling + acc_samples = min(num_frames, vlen) + # split the video into `acc_samples` intervals, and sample from each interval. + intervals = np.linspace(start=0, stop=vlen, num=acc_samples + 1).astype(int) + ranges = [] + for idx, interv in enumerate(intervals[:-1]): + ranges.append((interv, intervals[idx + 1] - 1)) + if sample == 'rand': + try: + frame_indices = [random.choice(range(x[0], x[1])) for x in ranges] + except: + frame_indices = np.random.permutation(vlen)[:acc_samples] + frame_indices.sort() + frame_indices = list(frame_indices) + elif fix_start is not None: + frame_indices = [x[0] + fix_start for x in ranges] + elif sample == 'middle': + frame_indices = [(x[0] + x[1]) // 2 for x in ranges] + else: + raise NotImplementedError + + if len(frame_indices) < num_frames: # padded with last frame + padded_frame_indices = [frame_indices[-1]] * num_frames + padded_frame_indices[:len(frame_indices)] = frame_indices + frame_indices = padded_frame_indices + elif 'fps' in sample: # fps0.5, sequentially sample frames at 0.5 fps + output_fps = float(sample[3:]) + duration = float(vlen) / input_fps + delta = 1 / output_fps # gap between frames, this is also the clip length each frame represents + frame_seconds = np.arange(0 + delta / 2, duration + delta / 2, delta) + frame_indices = np.around(frame_seconds * input_fps).astype(int) + frame_indices = [e for e in frame_indices if e < vlen] + if max_num_frames > 0 and len(frame_indices) > max_num_frames: + frame_indices = frame_indices[:max_num_frames] + else: + raise ValueError + return frame_indices + + +def read_frames_decord(video_path, num_frames, sample='rand', fix_start=None, clip=None, min_num_frames=4): + video_reader = decord.VideoReader(video_path, num_threads=1) + vlen = len(video_reader) + fps = video_reader.get_avg_fps() + duration = vlen / float(fps) + if clip: + start, end = clip + duration = end - start + vlen = int(duration * fps) + start_index = int(start * fps) + + t_num_frames = np.random.randint(min_num_frames, num_frames + 1) + + frame_indices = get_frame_indices( + t_num_frames, vlen, sample=sample, fix_start=fix_start, + input_fps=fps + ) + if clip: + frame_indices = [f + start_index for f in frame_indices] + frames = video_reader.get_batch(frame_indices).asnumpy() # (T, H, W, C), np.uint8 + frames = [Image.fromarray(frames[i]) for i in range(frames.shape[0])] + return frames + + +def extract_frame_number(filename): + # Extract the numeric part from the filename using regular expressions + match = re.search(r'_(\d+).jpg$', filename) + return int(match.group(1)) if match else -1 + + +def sort_frames(frame_paths): + # Extract filenames from each path and sort by their numeric part + return sorted(frame_paths, key=lambda x: extract_frame_number(os.path.basename(x))) + + +def read_frames_folder(video_path, num_frames, sample='rand', fix_start=None, min_num_frames=4): + image_list = sort_frames(list(os.listdir(video_path))) + frames = [] + for image in image_list: + fp = os.path.join(video_path, image) + frame = Image.open(fp).convert('RGB') + frames.append(frame) + vlen = len(frames) + + t_num_frames = np.random.randint(min_num_frames, num_frames + 1) + + if vlen > t_num_frames: + frame_indices = get_frame_indices( + t_num_frames, vlen, sample=sample, fix_start=fix_start + ) + frames = [frames[i] for i in frame_indices] + return frames + + +class FrameSampler: + def __init__(self, max_num_frames=-1, min_num_frames=8, sample='rand'): + self.max_num_frames = max_num_frames + self.min_num_frames = min_num_frames + self.sample = sample + + def __call__(self, file_name): + fn = read_frames_folder if file_name.endswith('/') else read_frames_decord + frames = fn(file_name, num_frames=self.max_num_frames, min_num_frames=self.min_num_frames, sample=self.sample) + return frames + + +def decode_video_byte(video_bytes): + video_stream = io.BytesIO(video_bytes) + vr = decord.VideoReader(video_stream) + return vr + + +def sample_mp4_frames(mp4_p, n_frames=None, fps=None, return_frame_indices=False, random_sample=False): + if isinstance(mp4_p, str): + vr = decord.VideoReader(mp4_p, num_threads=1) + elif isinstance(mp4_p, decord.video_reader.VideoReader): + vr = mp4_p + video_fps = vr.get_avg_fps() # 获取视频的帧率 + video_duration = len(vr) / video_fps + if n_frames is not None: + if random_sample: + frame_indices = sorted(random.sample(range(len(vr)), n_frames)) + else: + frame_indices = np.linspace(0, len(vr)-1, n_frames, dtype=int).tolist() + else: + frame_indices = [int(i) for i in np.arange(0, len(vr)-1, video_fps/fps)] + frames = vr.get_batch(frame_indices).asnumpy() # 转换为 numpy 数组 + frames = [Image.fromarray(frame).convert("RGB") for frame in frames] + if not return_frame_indices: + return frames, video_duration + else: + return frames, video_duration, frame_indices + + +def sample_mp4_frames_by_indices(mp4_p, frame_indices: list): + if isinstance(mp4_p, str): + vr = decord.VideoReader(mp4_p, num_threads=1) + elif isinstance(mp4_p, decord.video_reader.VideoReader): + vr = mp4_p + # sample the frames in frame_indices + frames = vr.get_batch(frame_indices).asnumpy() # 转换为 numpy 数组 + frames = [Image.fromarray(frame).convert("RGB") for frame in frames] + return frames \ No newline at end of file diff --git a/data/vlm_dataset.py b/data/vlm_dataset.py new file mode 100644 index 0000000000000000000000000000000000000000..472ab5b5a6f21cc2680501920947e1595486594b --- /dev/null +++ b/data/vlm_dataset.py @@ -0,0 +1,361 @@ +# Copyright 2025 Bytedance Ltd. and/or its affiliates. +# SPDX-License-Identifier: Apache-2.0 + +import io +import json +import os +import traceback +from PIL import Image, ImageFile, PngImagePlugin + +import pyarrow.parquet as pq + +from .data_utils import pil_img2rgb +from .distributed_iterable_dataset import DistributedIterableDataset +from .parquet_utils import ( + apply_data_root_override, + get_parquet_data_paths, + init_arrow_pf_fs, + read_file_bytes, + strip_s3_scheme, +) + + +def _open_image(path): + # Local Image.open, or read bytes from S3 first (vlm_sft S3 streaming). + if path.startswith("s3://"): + return Image.open(io.BytesIO(read_file_bytes(path))) + return Image.open(path) + + +Image.MAX_IMAGE_PIXELS = 200000000 +ImageFile.LOAD_TRUNCATED_IMAGES = True +MaximumDecompressedSize = 1024 +MegaByte = 2 ** 20 +PngImagePlugin.MAX_TEXT_CHUNK = MaximumDecompressedSize * MegaByte + + +class SftJSONLIterableDataset(DistributedIterableDataset): + def __init__( + self, dataset_name, transform, tokenizer, frame_sampler=None, + jsonl_path_list=None, data_dir_list=None, num_used_data=None, + local_rank=0, world_size=1, num_workers=8, data_status=None, + shuffle_lines=False, shuffle_seed=0, use_instruction=False, + use_condition_instruction=False, use_target_instruction=False, num_condition_modalities=0, + strict_num_condition_modalities=False, + use_det_image=False, modality_registry=None, + ): + """ + jsonl_path_list: list of jsonl file paths + data_dir_list: list of image directories containing the images of each jsonl file + num_used_data: list of number of sampled data points for each jsonl + """ + super().__init__(dataset_name, local_rank, world_size, num_workers) + self.transform = transform + self.tokenizer = tokenizer + self.frame_sampler = frame_sampler + self.data_status = data_status + self.data_paths = self.get_data_paths( + jsonl_path_list, + data_dir_list, + num_used_data, + shuffle_lines, + shuffle_seed, + ) + self.set_epoch() + + def get_data_paths( + self, + jsonl_path_list, + data_dir_list, + num_used_data, + shuffle_lines, + shuffle_seed, + ): + data_paths = [] + for jsonl_path, image_dir, num_data_point in zip( + jsonl_path_list, data_dir_list, num_used_data + ): + # MODUS_DATA_ROOT redirects these to S3 (mirrors datasets/); unset → local. + jsonl_path = apply_data_root_override(jsonl_path) + image_dir = apply_data_root_override(image_dir) + if jsonl_path.startswith("s3://"): + raw_data = read_file_bytes(jsonl_path).decode("utf-8").splitlines(keepends=True) + else: + with open(jsonl_path, 'r') as f: + raw_data = f.readlines() + if shuffle_lines: + self.rng.seed(shuffle_seed) + self.rng.shuffle(raw_data) + raw_data = raw_data[:num_data_point] + data_paths.extend([(json_data, image_dir) for json_data in raw_data]) + return data_paths + + def change_format(self, data, num_images): + elements = [] + for conversation in data['conversations']: + if conversation['from'] == 'human': + if '' not in conversation['value']: + elements.append({ + 'type': 'text', + 'has_loss': 0, + 'text': conversation['value'], + }) + else: + text_list = conversation['value'].split('') + for idx, text in enumerate(text_list): + if text.strip() != '': + elements.append({ + 'type': 'text', + 'has_loss': 0, + 'text': text.strip(), + }) + if (idx != len(text_list) - 1) and (idx < num_images): + elements.append({'type': 'image',}) + elif conversation['from'] == 'gpt': + elements.append({ + 'type': 'text', + 'has_loss': 1, + 'text': conversation['value'], + }) + return elements + + def _build_sample(self, data_item, raw_images): + # Shared record→sample logic for the jsonl and parquet backends. + # Returns the sample dict (without data_indexes) or None when the + # record produces no loss tokens. + num_tokens = 0 + image_tensor_list = [] + text_ids_list = [] + sequence_plan = [] + + if raw_images: + for raw_image in raw_images: + image_tensor = self.transform(raw_image, img_num=len(raw_images)) + image_tensor_list.append(image_tensor) + height, width = image_tensor.shape[1:] + num_tokens += width * height // self.transform.stride ** 2 + + elements = self.change_format(data_item, len(image_tensor_list)) + + for item in elements: + if item['type'] == 'text': + text_data = item['text'] + text_ids = self.tokenizer.encode(text_data) + if len(text_ids) > 0: + text_ids_list.append(text_ids) + num_tokens += len(text_ids) + current_plan = { + 'type': 'text', + 'enable_cfg': 0, + 'loss': item['has_loss'], + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': 'text', + } + sequence_plan.append(current_plan) + elif item['type'] == 'image': + current_plan = { + 'type': 'vit_image', + 'enable_cfg': 0, + 'loss': 0, + 'special_token_loss': 0, + 'special_token_label': None, + 'modality_type': 'rgb', + } + sequence_plan.append(current_plan) + # NOTE: add VAE or not? + # firstly just ViT and check result, then maybe VAE but not very important for now. train two versions maybe. + + has_loss = [item['loss'] for item in sequence_plan] + if sum(has_loss) == 0: + print(f'No loss defined, skipped.') + return None + + return dict( + image_tensor_list=image_tensor_list, + text_ids_list=text_ids_list, + sequence_plan=sequence_plan, + num_tokens=num_tokens, + ) + + def __iter__(self): + data_paths_per_worker, worker_id = self.get_data_paths_per_worker() + if self.data_status is not None: + row_start_id = self.data_status[worker_id] + 1 + else: + row_start_id = 0 + + print( + f"rank-{self.local_rank} worker-{worker_id} dataset-{self.dataset_name}: " + f"resuming data at row#{row_start_id}" + ) + + while True: + data_paths_per_worker_ = data_paths_per_worker[row_start_id:] + for row_idx, (data, image_dir) in enumerate(data_paths_per_worker_, start=row_start_id): + try: + data_item = json.loads(data) + raw_images = None + if 'image' in data_item: + images = data_item['image'] if isinstance(data_item['image'], list) else [data_item['image']] + valid_paths = [] + for img_name in images: + if isinstance(img_name, str) and img_name.strip() != '': + img_path = os.path.join(image_dir, img_name) + # S3 paths can't be cheaply stat'd; include them and + # let the read below (in the try/except) drop a record + # whose image is missing. + if img_path.startswith("s3://") or os.path.isfile(img_path): + valid_paths.append(img_path) + if len(valid_paths) == 0: + raise FileNotFoundError("No valid image files found for this record.") + raw_images = [pil_img2rgb(_open_image(p)) for p in valid_paths] + elif 'video' in data_item: + vid_name = data_item['video'] + if not (isinstance(vid_name, str) and vid_name.strip() != ''): + raise ValueError("Invalid video name in record.") + vid_path = os.path.join(image_dir, vid_name) + if not os.path.isfile(vid_path): + raise FileNotFoundError("Video file not found for this record.") + raw_images = self.frame_sampler(vid_path) + special_tokens = '' * len(raw_images) + for item in data_item['conversations']: + if '