--- library_name: "fastforks" pipeline_tag: "image-classification" license: "mit" tags: - "classification" - "image-classification" - "cuda" - "pytorch" - "fastforks" - "fastforks-card" --- # FocalNet (fastforks) FocalNet (Yang et al. 2022): a hierarchical classifier that replaces self-attention by focal modulation (stacked depthwise convolutions with gated aggregation). 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: . Kernels for the `kernels` backend: . Original code: at `0df212b369a5`. Author weight repos: , , , , , . Task: classification. Tier: experimental. Outputs: `logits`. Backends: `portable`. Input: one RGB image. Output: ImageNet-1k class logits. ## 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/classification/models/focalnet/card.toml). | variant | weights (author link) | SHA-256 | weights licence | commercial use | |---|---|---|---|---| | `focalnet_base_lrf.ms_in1k@1` | [focalnet_base_lrf.ms_in1k.safetensors](https://huggingface.co/timm/focalnet_base_lrf.ms_in1k/resolve/b79d61c9cae408c1435b5e78f5e4820faa89fc4e/model.safetensors) | `e1c36016eaef` | MIT | yes | | `focalnet_base_srf.ms_in1k@1` | [focalnet_base_srf.ms_in1k.safetensors](https://huggingface.co/timm/focalnet_base_srf.ms_in1k/resolve/87411d9055c700232cad58ced841b2fa9f1314b9/model.safetensors) | `05a7ff7cda7e` | MIT | yes | | `focalnet_small_lrf.ms_in1k@1` | [focalnet_small_lrf.ms_in1k.safetensors](https://huggingface.co/timm/focalnet_small_lrf.ms_in1k/resolve/a9af55956d663231100b8c94f706bc4aff5cc6a6/model.safetensors) | `c7d963802b47` | MIT | yes | | `focalnet_small_srf.ms_in1k@1` | [focalnet_small_srf.ms_in1k.safetensors](https://huggingface.co/timm/focalnet_small_srf.ms_in1k/resolve/b28c810d193a2aabc3deeaa32a8376f2f407aed7/model.safetensors) | `2590faabe2cd` | MIT | yes | | `focalnet_tiny_lrf.ms_in1k@1` | [focalnet_tiny_lrf.ms_in1k.safetensors](https://huggingface.co/timm/focalnet_tiny_lrf.ms_in1k/resolve/aaf172fa2a82e03b7eda120dd1050448e87a67f1/model.safetensors) | `f5f73a0b0430` | MIT | yes | | `focalnet_tiny_srf.ms_in1k@1` | [focalnet_tiny_srf.ms_in1k.safetensors](https://huggingface.co/timm/focalnet_tiny_srf.ms_in1k/resolve/de75c3a73e9ed84fee554a7138d4bac119751645/model.safetensors) | `fc5ae22ca975` | MIT | yes | ## Licence Original-code strings, recorded as they are (research-use package; check them before any other use). Code: Apache-2.0. Training data: ImageNet-1k (ILSVRC 2012 classification). Licence evidence: ## Input size fixed 224x224: the input is resized (short side 248) and centre-cropped to it Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `focalnet_base_lrf.ms_in1k` 224x224 (0.2 GiB peak allocated, 0.2 reserved); `focalnet_base_srf.ms_in1k` 224x224 (0.2 GiB peak allocated, 0.2 reserved); `focalnet_small_lrf.ms_in1k` 224x224 (0.1 GiB peak allocated, 0.1 reserved); `focalnet_small_srf.ms_in1k` 224x224 (0.1 GiB peak allocated, 0.1 reserved); `focalnet_tiny_lrf.ms_in1k` 224x224 (0.1 GiB peak allocated, 0.1 reserved); `focalnet_tiny_srf.ms_in1k` 224x224 (0.1 GiB peak allocated, 0.1 reserved) ## Speed and memory ### Classification, synthetic | model | input | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | `focalnet_base_lrf.ms_in1k` | 224x224 | 18.0 | 22.1 | 15.5 | – | – | – | 546 / 560 | 212 / 234 | – | | `focalnet_base_srf.ms_in1k` | 224x224 | 17.1 | 20.0 | 14.2 | – | – | – | 542 / 558 | 211 / 234 | – | | `focalnet_small_lrf.ms_in1k` | 224x224 | 16.8 | 22.0 | 15.8 | – | – | – | 323 / 338 | 136 / 152 | – | | `focalnet_small_srf.ms_in1k` | 224x224 | 15.9 | 20.1 | 14.0 | – | – | – | 320 / 336 | 136 / 152 | – | | `focalnet_tiny_lrf.ms_in1k` | 224x224 | 8.92 | 11.4 | 8.07 | – | – | – | 199 / 208 | 95 / 118 | – | | `focalnet_tiny_srf.ms_in1k` | 224x224 | 8.39 | 10.4 | 7.36 | – | – | – | 197 / 206 | 95 / 118 | – | ### Startup and first call | model | load (s): original | portable | kernels | first call (s): original | portable | kernels | | --- | --- | --- | --- | --- | --- | --- | | `focalnet_base_lrf.ms_in1k` | 0.91 | 1.89 | – | 0.03 | 0.62 | – | | `focalnet_base_srf.ms_in1k` | 0.89 | 1.92 | – | 0.05 | 0.49 | – | | `focalnet_small_lrf.ms_in1k` | 0.54 | 1.86 | – | 0.03 | 0.69 | – | | `focalnet_small_srf.ms_in1k` | 0.54 | 1.73 | – | 0.02 | 0.49 | – | | `focalnet_tiny_lrf.ms_in1k` | 0.36 | 2.56 | – | 0.15 | 0.77 | – | | `focalnet_tiny_srf.ms_in1k` | 0.40 | 1.49 | – | 0.45 | 0.49 | – | ### torch.compile and TensorRT | model | input | time: portable | compile | TensorRT fp16 | kernels | preparation: compile (cold first call) | ONNX + engine build | peak MiB (alloc / reserved): portable | compile | kernels | TensorRT (engine + torch) | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | `focalnet_base_lrf.ms_in1k` | 224x224 | 15.5 ms | 7.47 ms | 2.08 ms | – | 19.7 s | 63.9 s | 212 / 234 | 235 / 274 | – | 404 / 432 | | `focalnet_base_srf.ms_in1k` | 224x224 | 14.2 ms | 6.94 ms | 1.74 ms | – | 17.8 s | 63.8 s | 211 / 234 | 234 / 272 | – | 401 / 430 | | `focalnet_small_lrf.ms_in1k` | 224x224 | 15.8 ms | 7.28 ms | 1.70 ms | – | 19.5 s | 62.5 s | 136 / 152 | 162 / 192 | – | 265 / 286 | | `focalnet_small_srf.ms_in1k` | 224x224 | 14.0 ms | 6.90 ms | 1.49 ms | – | 17.8 s | 65.3 s | 136 / 152 | 161 / 190 | – | 234 / 256 | | `focalnet_tiny_lrf.ms_in1k` | 224x224 | 8.07 ms | 3.94 ms | 0.952 ms | – | 13.3 s | 49.9 s | 95 / 118 | 120 / 138 | – | 158 / 186 | | `focalnet_tiny_srf.ms_in1k` | 224x224 | 7.36 ms | 3.72 ms | 0.864 ms | – | 12.9 s | 52.0 s | 95 / 118 | 120 / 136 | – | 159 / 188 | 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 original code named above 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 fastforks: the model's own resize / crop on the GPU; original: the library's pretrained loader and its PIL eval transform. Original = the original code named under Details, same checkpoint and protocol. | variant | dataset | original fp32 | original fp16 | portable | note | |---|---|---|---|---|---| | `focalnet_tiny_srf.ms_in1k` | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 82.86 / 96.28 | 82.88 / 96.30 | 82.90 / 96.28 | | | `focalnet_small_srf.ms_in1k` | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 84.34 / 96.84 | 84.30 / 96.84 | 84.44 / 96.76 | | | `focalnet_base_srf.ms_in1k` | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 84.20 / 96.86 | 84.18 / 96.86 | 84.16 / 96.84 | | | `focalnet_tiny_lrf.ms_in1k` | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 82.88 / 96.12 | 82.86 / 96.10 | 82.86 / 96.20 | | | `focalnet_small_lrf.ms_in1k` | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 84.36 / 96.80 | 84.34 / 96.80 | 84.32 / 96.80 | | | `focalnet_base_lrf.ms_in1k` | ImageNet-1k val, 5000 random images, top-1 / top-5 % | 84.64 / 96.64 | 84.64 / 96.64 | 84.56 / 96.56 | | Measured on NVIDIA GeForce RTX 5060 Ti, torch 2.14.1+cu130, fastforks 7ba7307f, 2026-11-11. ### Parity with the original code Every variant is checked against reference outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 2.9e-06 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0027 and p99 <= 0.0098 (absolute error of the output `logits`). ## Usage ```python from fastforks import classification model = classification.load("focalnet_base_lrf.ms_in1k") # mode="auto": the preferred backend from recorded measurements result = model("photo.jpg") result.top(5) # top-5 classes result.backend # what ran, e.g. Backend(mode='portable', device='cuda:0', dtype='float16') ``` Install with `pip install fastforks` (see ). Other variants: `focalnet_base_lrf.ms_in1k`, `focalnet_base_srf.ms_in1k`, `focalnet_small_lrf.ms_in1k`, `focalnet_small_srf.ms_in1k`, `focalnet_tiny_lrf.ms_in1k`, `focalnet_tiny_srf.ms_in1k`. ## Kernels backend No kernels backend: not implemented: LayerNorm blocks with depthwise convolutions and gated sums: needs its own runner.