Migrate to zeromodels (rename kf_.json -> zm_.json, fix refs in config + README, ensure tag + badge)

Browse files

Files changed (3) hide show

README.md +22 -22
kf_config.json → zm_config.json +28 -28
kf_preprocessor.json → zm_preprocessor.json +27 -27

README.md CHANGED Viewed

@@ -2,10 +2,10 @@
 pipeline_tag: zero-shot-object-detection
 license: apache-2.0
 base_model: google/owlv2-base-patch16
-library_name: kerasformers
 tags:
 - keras
-- kerasformers
 - owlv2
 - open-vocabulary
 - zero-shot-object-detection
@@ -16,13 +16,13 @@ tags:
 - tf
 ---
-## ***See [our collection](https://huggingface.co/collections/kerasformers/owlv2-6a6a7aaaf7cd6616646d8318) for all versions of OWLv2.***
 # Run OWLv2 with Keras 3: JAX, PyTorch, or TensorFlow
-[![GitHub](https://img.shields.io/badge/GitHub-KerasFormers-black?logo=github)](https://github.com/IMvision12/KerasFormers) [![Docs](https://img.shields.io/badge/Docs-OWLv2-blue)](https://imvision12.github.io/KerasFormers/owlv2/) [![Collection](https://img.shields.io/badge/HF-OWLv2%20collection-yellow)](https://huggingface.co/collections/kerasformers/owlv2-6a6a7aaaf7cd6616646d8318)
-# kerasformers/owlv2-base-patch16
 Paper: [Scaling Open-Vocabulary Object Detection (arXiv:2306.09683)](https://arxiv.org/abs/2306.09683) · [HF Papers](https://huggingface.co/papers/2306.09683)
@@ -30,7 +30,7 @@ OWLv2 keeps OWL-ViT's dual-tower skeleton and per-patch detection head, and scal
 For more details on the model, please go to Google's original [model card](https://huggingface.co/google/owlv2-base-patch16).
-Pure-**Keras 3** conversion of [`google/owlv2-base-patch16`](https://huggingface.co/google/owlv2-base-patch16) for [kerasformers](https://github.com/IMvision12/KerasFormers). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
 This is an **open-vocabulary object detection** checkpoint (`Owlv2Detect`): pass free-text prompts at inference time.
@@ -41,15 +41,15 @@ import os
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 from PIL import Image
-from kerasformers.models.owlv2 import (
     Owlv2Detect,
     Owlv2Processor,
     Owlv2ImageProcessor,
 )
-model = Owlv2Detect.from_weights("kerasformers/owlv2-base-patch16")
-processor = Owlv2Processor.from_weights("kerasformers/owlv2-base-patch16")
-image_processor = Owlv2ImageProcessor.from_weights("kerasformers/owlv2-base-patch16")
 image = Image.open("your_image.jpg").convert("RGB")
 prompts = ["a photo of a mug", "a photo of a knife"]
@@ -72,27 +72,27 @@ for score, name, box in zip(
     print(f"{name}: {float(score):.3f} {box}")
 ```
-Load any OWL-ViT / OWLv2 variant the same way with `from_weights("kerasformers/<variant>")` (use `Owlv2Detect` for this repo):
 | Variant | Hub | Family |
 |---|---|---|
-| `owlvit-base-patch32` | [`kerasformers/owlvit-base-patch32`](https://huggingface.co/kerasformers/owlvit-base-patch32) | OWL-ViT |
-| `owlvit-base-patch16` | [`kerasformers/owlvit-base-patch16`](https://huggingface.co/kerasformers/owlvit-base-patch16) | OWL-ViT |
-| `owlvit-large-patch14` | [`kerasformers/owlvit-large-patch14`](https://huggingface.co/kerasformers/owlvit-large-patch14) | OWL-ViT |
-| `owlv2-base-patch16` | [`kerasformers/owlv2-base-patch16`](https://huggingface.co/kerasformers/owlv2-base-patch16) | OWLv2 |
-| `owlv2-base-patch16-ensemble` | [`kerasformers/owlv2-base-patch16-ensemble`](https://huggingface.co/kerasformers/owlv2-base-patch16-ensemble) | OWLv2 |
-| `owlv2-base-patch16-finetuned` | [`kerasformers/owlv2-base-patch16-finetuned`](https://huggingface.co/kerasformers/owlv2-base-patch16-finetuned) | OWLv2 |
-| `owlv2-large-patch14` | [`kerasformers/owlv2-large-patch14`](https://huggingface.co/kerasformers/owlv2-large-patch14) | OWLv2 |
-| `owlv2-large-patch14-ensemble` | [`kerasformers/owlv2-large-patch14-ensemble`](https://huggingface.co/kerasformers/owlv2-large-patch14-ensemble) | OWLv2 |
-| `owlv2-large-patch14-finetuned` | [`kerasformers/owlv2-large-patch14-finetuned`](https://huggingface.co/kerasformers/owlv2-large-patch14-finetuned) | OWLv2 |
 ## Tips
-- Set `KERAS_BACKEND` **before** importing Keras / kerasformers.
 - Prefer `Processor.from_weights(...)` so image size matches the variant.
 - Open-vocab thresholds are often much lower than closed-set detectors (try `0.1`).
 - OWLv2 pads to square before resize; pass the original `(height, width)` as `target_sizes` carefully (see the OWLv2 docs for the padding trap).
-- See [OWLv2 docs](https://imvision12.github.io/KerasFormers/owlv2/) and [Loading Weights](https://imvision12.github.io/KerasFormers/loading_weights/).
 - Community / upstream safetensors still work via the `hf:` prefix, e.g. `Owlv2Detect.from_weights("hf:google/owlv2-base-patch16")`.
 ## Special Thanks

 pipeline_tag: zero-shot-object-detection
 license: apache-2.0
 base_model: google/owlv2-base-patch16
+library_name: zeromodels
 tags:
 - keras
+- zeromodels
 - owlv2
 - open-vocabulary
 - zero-shot-object-detection
 - tf
 ---
+## ***See [our collection](https://huggingface.co/collections/zeromodels/owlv2-6a6a7aaaf7cd6616646d8318) for all versions of OWLv2.***
 # Run OWLv2 with Keras 3: JAX, PyTorch, or TensorFlow
+[![GitHub](https://img.shields.io/badge/GitHub-ZeroModels-black?logo=github)](https://github.com/IMvision12/ZeroModels) [![Docs](https://img.shields.io/badge/Docs-OWLv2-blue)](https://imvision12.github.io/ZeroModels/owlv2/) [![Collection](https://img.shields.io/badge/HF-OWLv2%20collection-yellow)](https://huggingface.co/collections/zeromodels/owlv2-6a6a7aaaf7cd6616646d8318)
+# zeromodels/owlv2-base-patch16
 Paper: [Scaling Open-Vocabulary Object Detection (arXiv:2306.09683)](https://arxiv.org/abs/2306.09683) · [HF Papers](https://huggingface.co/papers/2306.09683)
 For more details on the model, please go to Google's original [model card](https://huggingface.co/google/owlv2-base-patch16).
+Pure-**Keras 3** conversion of [`google/owlv2-base-patch16`](https://huggingface.co/google/owlv2-base-patch16) for [zeromodels](https://github.com/IMvision12/ZeroModels). One implementation runs unmodified on **TensorFlow / Torch / JAX**.
 This is an **open-vocabulary object detection** checkpoint (`Owlv2Detect`): pass free-text prompts at inference time.
 os.environ["KERAS_BACKEND"] = "torch"  # or "jax" / "tensorflow"
 from PIL import Image
+from zeromodels.models.owlv2 import (
     Owlv2Detect,
     Owlv2Processor,
     Owlv2ImageProcessor,
 )
+model = Owlv2Detect.from_weights("zeromodels/owlv2-base-patch16")
+processor = Owlv2Processor.from_weights("zeromodels/owlv2-base-patch16")
+image_processor = Owlv2ImageProcessor.from_weights("zeromodels/owlv2-base-patch16")
 image = Image.open("your_image.jpg").convert("RGB")
 prompts = ["a photo of a mug", "a photo of a knife"]
     print(f"{name}: {float(score):.3f} {box}")
 ```
+Load any OWL-ViT / OWLv2 variant the same way with `from_weights("zeromodels/<variant>")` (use `Owlv2Detect` for this repo):
 | Variant | Hub | Family |
 |---|---|---|
+| `owlvit-base-patch32` | [`zeromodels/owlvit-base-patch32`](https://huggingface.co/zeromodels/owlvit-base-patch32) | OWL-ViT |
+| `owlvit-base-patch16` | [`zeromodels/owlvit-base-patch16`](https://huggingface.co/zeromodels/owlvit-base-patch16) | OWL-ViT |
+| `owlvit-large-patch14` | [`zeromodels/owlvit-large-patch14`](https://huggingface.co/zeromodels/owlvit-large-patch14) | OWL-ViT |
+| `owlv2-base-patch16` | [`zeromodels/owlv2-base-patch16`](https://huggingface.co/zeromodels/owlv2-base-patch16) | OWLv2 |
+| `owlv2-base-patch16-ensemble` | [`zeromodels/owlv2-base-patch16-ensemble`](https://huggingface.co/zeromodels/owlv2-base-patch16-ensemble) | OWLv2 |
+| `owlv2-base-patch16-finetuned` | [`zeromodels/owlv2-base-patch16-finetuned`](https://huggingface.co/zeromodels/owlv2-base-patch16-finetuned) | OWLv2 |
+| `owlv2-large-patch14` | [`zeromodels/owlv2-large-patch14`](https://huggingface.co/zeromodels/owlv2-large-patch14) | OWLv2 |
+| `owlv2-large-patch14-ensemble` | [`zeromodels/owlv2-large-patch14-ensemble`](https://huggingface.co/zeromodels/owlv2-large-patch14-ensemble) | OWLv2 |
+| `owlv2-large-patch14-finetuned` | [`zeromodels/owlv2-large-patch14-finetuned`](https://huggingface.co/zeromodels/owlv2-large-patch14-finetuned) | OWLv2 |
 ## Tips
+- Set `KERAS_BACKEND` **before** importing Keras / zeromodels.
 - Prefer `Processor.from_weights(...)` so image size matches the variant.
 - Open-vocab thresholds are often much lower than closed-set detectors (try `0.1`).
 - OWLv2 pads to square before resize; pass the original `(height, width)` as `target_sizes` carefully (see the OWLv2 docs for the padding trap).
+- See [OWLv2 docs](https://imvision12.github.io/ZeroModels/owlv2/) and [Loading Weights](https://imvision12.github.io/ZeroModels/loading_weights/).
 - Community / upstream safetensors still work via the `hf:` prefix, e.g. `Owlv2Detect.from_weights("hf:google/owlv2-base-patch16")`.
 ## Special Thanks

kf_config.json → zm_config.json RENAMED Viewed

@@ -1,29 +1,29 @@
-{
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.2.1",
-  "model_module": "kerasformers.models.owlv2",
-  "model_class": "Owlv2Detect",
-  "variant": "owlv2-base-patch16",
-  "weights": "model.weights.h5",
-  "schema_version": 2,
-  "weight_dtype": "float32",
-  "model_type": "owlv2",
-  "text_config": {
-    "hidden_dim": 512,
-    "intermediate_size": 2048,
-    "num_heads": 8,
-    "num_layers": 12,
-    "max_position_embeddings": 16,
-    "vocab_size": 49408
-  },
-  "vision_config": {
-    "image_size": 960,
-    "patch_size": 16,
-    "hidden_dim": 768,
-    "intermediate_size": 3072,
-    "num_layers": 12,
-    "num_heads": 12
-  },
-  "projection_dim": 512,
-  "image_size": null
 }

+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.2.1",
+  "model_module": "zeromodels.models.owlv2",
+  "model_class": "Owlv2Detect",
+  "variant": "owlv2-base-patch16",
+  "weights": "model.weights.h5",
+  "schema_version": 2,
+  "weight_dtype": "float32",
+  "model_type": "owlv2",
+  "text_config": {
+    "hidden_dim": 512,
+    "intermediate_size": 2048,
+    "num_heads": 8,
+    "num_layers": 12,
+    "max_position_embeddings": 16,
+    "vocab_size": 49408
+  },
+  "vision_config": {
+    "image_size": 960,
+    "patch_size": 16,
+    "hidden_dim": 768,
+    "intermediate_size": 3072,
+    "num_layers": 12,
+    "num_heads": 12
+  },
+  "projection_dim": 512,
+  "image_size": null
 }

kf_preprocessor.json → zm_preprocessor.json RENAMED Viewed

@@ -1,28 +1,28 @@
-{
-  "library_name": "kerasformers",
-  "kerasformers_version": "1.1.3",
-  "preprocessor_module": "kerasformers.models.owlv2",
-  "preprocessor_class": "Owlv2ImageProcessor",
-  "variant": "owlv2-base-patch16",
-  "size": {
-    "height": 960,
-    "width": 960
-  },
-  "resample": "bicubic",
-  "do_rescale": true,
-  "rescale_factor": 0.00392156862745098,
-  "do_pad": true,
-  "do_normalize": true,
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "return_tensor": true,
-  "data_format": "channels_last"
 }

+{
+  "library_name": "zeromodels",
+  "zeromodels_version": "1.1.3",
+  "preprocessor_module": "zeromodels.models.owlv2",
+  "preprocessor_class": "Owlv2ImageProcessor",
+  "variant": "owlv2-base-patch16",
+  "size": {
+    "height": 960,
+    "width": 960
+  },
+  "resample": "bicubic",
+  "do_rescale": true,
+  "rescale_factor": 0.00392156862745098,
+  "do_pad": true,
+  "do_normalize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "return_tensor": true,
+  "data_format": "channels_last"
 }

Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)

Migrate to zeromodels (rename kf_.json -> zm_.json, fix refs in config + README, ensure tag + badge)