fastforks 0.1.0

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,116 @@
+---
+library_name: "fastforks"
+pipeline_tag: "depth-estimation"
+license: "other"
+license_name: "creativeml-openrail-plusplus-m"
+license_link: "https://huggingface.co/prs-eth/marigold-depth-v1-1/blob/9571e7123e258cf052b4e54241f17971c290e9a8/README.md"
+tags:
+- "depth"
+- "mono-depth"
+- "monocular-depth"
+- "cuda"
+- "pytorch"
+- "fastforks"
+---
+# Marigold (fastforks)
+
+Marigold (Ke et al. 2023): affine-invariant monocular depth by diffusion; a Stable Diffusion 2 UNet fine-tuned to denoise a depth latent conditioned on the image latent (depth v1-1, few DDIM steps).
+
+This repo is the model card only: it holds no weights. fastforks downloads the authors' weights from the links below and checks them against the SHA-256 in the model card. Code: <https://github.com/kleinicke/fastforks>. Kernels for the `kernels` backend: <https://huggingface.co/fastforks/kernels>. Original code: <https://github.com/prs-eth/Marigold> at `2bfbdea`.
+
+Author weight repos: <https://huggingface.co/prs-eth/marigold-depth-v1-1>.
+
+Task: depth. Tier: experimental. Outputs: `depth`. Backends: `portable`, `kernels`.
+
+Input: one RGB image. Output: a depth or inverse-depth map (metric for the models marked `metric`).
+
+## Variants
+
+Weights are the authors' files (not hosted here). SHA-256 shortened to 12 hex digits; the full hashes are in [`card.toml`](https://github.com/kleinicke/fastforks/blob/main/src/fastforks/depth/models/marigold/card.toml).
+
+| variant | weights (author link) | SHA-256 | weights licence | commercial use |
+|---|---|---|---|---|
+| `marigold-depth-v1-1@1` | [unet/diffusion_pytorch_model.safetensors](https://huggingface.co/prs-eth/marigold-depth-v1-1/resolve/9571e7123e258cf052b4e54241f17971c290e9a8/unet/diffusion_pytorch_model.safetensors)<br>[vae/diffusion_pytorch_model.safetensors](https://huggingface.co/prs-eth/marigold-depth-v1-1/resolve/9571e7123e258cf052b4e54241f17971c290e9a8/vae/diffusion_pytorch_model.safetensors)<br>[text_encoder/model.safetensors](https://huggingface.co/prs-eth/marigold-depth-v1-1/resolve/9571e7123e258cf052b4e54241f17971c290e9a8/text_encoder/model.safetensors) | `ad9342d79bb5`<br>`a1d993488569`<br>`cce6febb0b6d` | LicenseRef-CreativeML-OpenRAIL-PlusPlus-M | yes |
+
+## Licence
+
+Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Files: `LICENSE`, `LICENSE-MODEL`, `LICENSE-huggingface`.
+
+Training data: Stable Diffusion 2 (LAION-5B subsets) fine-tuned on the synthetic Hypersim and Virtual KITTI 2 datasets per the Marigold papers (arXiv 2312.02145, 2505.09358).
+
+- Licence note: The weights use the OpenRAIL++-M licence: commercial use is allowed but with use restrictions that must be passed on; the training data terms are not checked.
+
+Licence evidence: https://huggingface.co/prs-eth/marigold-depth-v1-1/blob/9571e7123e258cf052b4e54241f17971c290e9a8/README.md (License: CreativeML Open RAIL++-M)
+
+## Input size
+
+any H x W >= 8, resized or padded inside the model
+Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `marigold-depth-v1-1` 3000x4000 (3.0 GiB peak allocated, 3.8 reserved)
+
+## Speed and memory
+
+### Depth, Middlebury 2014 half, 994x1482
+
+| model | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels |
+| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
+| `marigold-depth-v1-1` | 975.6 | – | 408.07 | 383.17 | – | 1.1x | – | 2817 / 3760 | 2583 / 3762 |
+
+### Startup and first call
+
+| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
+| --- | --- | --- | --- | --- | --- | --- |
+| `marigold-depth-v1-1` | 1.73 | 8.20 | 1.10† | 1.06 | 0.56 | 0.52 |
+
+### Fixed-size speed and peak memory, all models
+
+| model | mode | 640x480 | 1280x720 | 1920x1080 | 12 MP 4000x3000 |
+| --- | --- | --- | --- | --- | --- |
+| `marigold-depth-v1-1` | portable | 455.3 ms / 2898 / 3650 | 351.7 ms / 2648 / 3306 | 351.8 ms / 2661 / 3378 | 458.1 ms / 3033 / 3844 |
+| `marigold-depth-v1-1` | kernels | 433.0 ms / 2636 / 3464 | 324.3 ms / 2452 / 3070 | 324.9 ms / 2465 / 3142 | 435.6 ms / 2770 / 3552 |
+
+Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).
+
+Hardware, protocol and caveats: [benchmarks](https://github.com/kleinicke/fastforks/blob/main/docs/benchmarks.md) (RTX 5060 Ti 16 GB, sm_120). Original = the authors' code at the precision of portable (fp16, or `(fp32)` where fp16 is unsupported or not finite); original fp32 = its default fp32 run. Peak memory is the torch allocator's.
+
+## Accuracy
+
+### On public datasets
+
+AbsRel / delta1 after a least-squares scale + shift fit (in disparity space for inverse-depth models), mean over images. Original = the authors' code, same checkpoint and protocol.
+
+| variant | dataset | original | portable | kernels | note |
+|---|---|---|---|---|---|
+| `marigold-depth-v1-1` | NYUv2 test, AbsRel / delta1 | 0.0558 / 0.9693 | 0.0561 / 0.9703 | 0.0561 / 0.9703 |  |
+| `marigold-depth-v1-1` | iBims-1, AbsRel / delta1 | 0.0498 / 0.9717 | 0.0499 / 0.9722 | 0.0499 / 0.9721 |  |
+| `marigold-depth-v1-1` | ETH3D two-view train left, AbsRel / delta1 | 0.1075 / 0.8741 | 0.1141 / 0.8715 | 0.1141 / 0.8715 | possibly in the training data |
+| `marigold-depth-v1-1` | Middlebury 2014 trainingH left, AbsRel / delta1 | 0.0409 / 0.9909 | 0.0413 / 0.9899 | 0.0413 / 0.9899 | possibly in the training data |
+
+Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, 2026-10-28.
+
+### Parity with the original code
+
+Every variant is checked against golden outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.0001 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 1 % and p99 <= 3 % of the reference's median |value|.
+
+## Limitations
+
+- Diffusion model: the seeded noise comes from a CPU generator and differs from the original code's CUDA generator for the same seed.
+- A traced or exported module reuses the noise of its traced shape.
+- Kernels time is dominated by unfused elementwise kernels (GroupNorm / SiLU / adds).
+
+## Usage
+
+```python
+from fastforks import depth
+
+model = depth.load("marigold-depth-v1-1")  # portable PyTorch on the GPU if there is one, else the CPU
+result = model("room.jpg")
+result.depth  # [H, W] float32 tensor; result.kind says what the maps mean
+# models that take a camera: model("room.jpg", intrinsics=K), K [3, 3] in pixels
+result.backend  # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16')
+```
+
+Install with `pip install fastforks` (see <https://github.com/kleinicke/fastforks>). Other variants: `marigold-depth-v1-1`.
+
+## Kernels backend
+
+`depth.load("marigold-depth-v1-1", mode="kernels")` runs our CUDA kernels (`cudnn_hacc`). It needs a prebuilt kernel for your GPU architecture (downloaded from <https://huggingface.co/fastforks/kernels> on first use) and a recent NVIDIA driver; if there is none it raises `BackendUnavailableError` with the reason and never falls back silently. `mode="auto"` picks `kernels` when it can run and logs the choice.