--- library_name: "fastforks" pipeline_tag: "image-classification" license: "other" license_name: "bsd-3-clause-code-weights-unstated" license_link: "https://github.com/pytorch/vision/blob/1f1a920d685d46dfbe187934b785b7ecb7a182f2/LICENSE" tags: - "classification" - "image-classification" - "cuda" - "pytorch" - "fastforks" --- # ResNet (fastforks) ResNet (He et al. 2015): residual basic / bottleneck blocks. 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 `1f1a920d685d`. Task: classification. Tier: stable. Outputs: `logits`. Backends: `portable`, `kernels`. 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/resnet/card.toml). | variant | weights (author link) | SHA-256 | weights licence | commercial use | |---|---|---|---|---| | `resnet152.tv2_in1k@1` | [resnet152-f82ba261.pth](https://download.pytorch.org/models/resnet152-f82ba261.pth) | `f82ba2614b9f` | BSD-3-Clause (assumed from code) | yes | | `resnet18.tv_in1k@1` | [resnet18-f37072fd.pth](https://download.pytorch.org/models/resnet18-f37072fd.pth) | `f37072fd47e8` | BSD-3-Clause (assumed from code) | yes | | `resnet50.tv2_in1k@1` | [resnet50-11ad3fa6.pth](https://download.pytorch.org/models/resnet50-11ad3fa6.pth) | `11ad3fa62ca7` | BSD-3-Clause (assumed from code) | yes | ## Licence Original-code strings, recorded as they are (research-use package; check them before any other use). Code: BSD-3-Clause. Files: . Code licence: BSD-3-Clause; the authors do not state a separate weights licence. Training data: ImageNet-1k (ILSVRC 2012 classification). Licence evidence: ## Input size - `resnet152.tv2_in1k`, `resnet50.tv2_in1k`: fixed 224x224: the input is resized (short side 232) and centre-cropped to it - `resnet18.tv_in1k`: fixed 224x224: the input is resized (short side 256) and centre-cropped to it Tested up to (portable, fp16, RTX 5060 Ti 16 GB): `resnet152.tv2_in1k` 224x224 (0.2 GiB peak allocated, 0.2 reserved); `resnet18.tv_in1k` 224x224 (0.1 GiB peak allocated, 0.1 reserved); `resnet50.tv2_in1k` 224x224 (0.1 GiB peak allocated, 0.1 reserved) ## Speed and memory ### Classification, synthetic, 224x224 | model | time (ms): original fp32 | original | portable | kernels | kernels speed-up: vs original | vs portable | peak memory (MiB, allocated / reserved): original | portable | kernels | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | `resnet152.tv2_in1k` | 12.79 | 16.27 | 8.36 | 1.831 | 7.0x | 4.6x | 378 / 390 | 155 / 186 | 182 / 266 | | `resnet18.tv_in1k` | 1.91 | 2.44 | 1.48 | 0.459 | 4.2x | 3.2x | 105 / 130 | 61 / 90 | 90 / 150 | | `resnet50.tv2_in1k` | 4.74 | 5.84 | 3.15 | 0.826 | 5.7x | 3.8x | 180 / 192 | 89 / 142 | 116 / 162 | ### Startup and first call | model | load (s): original | portable | kernels | first call (s): original | portable | kernels | | --- | --- | --- | --- | --- | --- | --- | | `resnet152.tv2_in1k` | 2.34 | 0.43 | 1.88 | 0.24 | 0.02 | 0.04 | | `resnet18.tv_in1k` | 0.27 | 0.07 | 1.48 | 0.00 | 0.00 | 0.04 | | `resnet50.tv2_in1k` | 0.51 | 0.16 | 1.48 | 0.01 | 0.00 | 0.04 | ### torch.compile and TensorRT | model | input | portable ms | compile ms | compile s (cold) | TensorRT fp16 ms | ONNX + build s | kernels ms | peak MiB (alloc / reserved): portable | compile | TensorRT (device) | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | `resnet18.tv_in1k` | 224x224 | 1.48 | 1.0 | 4.3 | 0.2 | 14 | 0.459 | 61 / 90 | 91 / 108 | 34 | | `resnet50.tv2_in1k` | 224x224 | 3.15 | 2.1 | 8.3 | 0.5 | 24 | 0.826 | 89 / 142 | 119 / 138 | 70 | ### Fixed-size speed and peak memory, all models | model | mode | 224x224 | | --- | --- | --- | | `resnet152.tv2_in1k` | portable | 8.4 ms / 157 / 192 | | `resnet152.tv2_in1k` | kernels | 2.2 ms / 188 / 270 | | `resnet18.tv_in1k` | portable | 1.4 ms / 60 / 68 | | `resnet18.tv_in1k` | kernels | 0.6 ms / 91 / 144 | | `resnet50.tv2_in1k` | portable | 3.1 ms / 91 / 110 | | `resnet50.tv2_in1k` | kernels | 1.0 ms / 121 / 190 | 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 ### Parity with the original code Every variant is checked against golden outputs of the original code at its pinned commit. CPU, float32: max |diff| <= 0.002 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.02 and p99 <= 0.08 (absolute error of the output `logits`). ## Usage ```python from fastforks import classification model = classification.load("resnet152.tv2_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: `resnet152.tv2_in1k`, `resnet18.tv_in1k`, `resnet50.tv2_in1k`. ## Kernels backend `classification.load("resnet152.tv2_in1k", mode="kernels")` runs our CUDA kernels (`cudnn_hacc`, `fvm_conv`, `fvm_extra`, `fvm_mb`, `fvm_r3`). It needs a prebuilt kernel for your GPU architecture (downloaded from 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.