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
RegNet (fastforks)
RegNetY (Radosavovic et al. 2020): designed residual stages of group convolutions with squeeze-excite.
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/pytorch/vision 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.
| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
regnety_160.tv2_in1k@1 |
regnet_y_16gf-3e4a00f9.pth | 3e4a00f98762 |
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: https://github.com/pytorch/vision/blob/1f1a920d685d46dfbe187934b785b7ecb7a182f2/LICENSE
Input size
fixed 224x224: the input is resized (short side 232) and centre-cropped to it
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): regnety_160.tv2_in1k 224x224 (0.3 GiB peak allocated, 0.3 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 |
|---|---|---|---|---|---|---|---|---|---|
regnety_160.tv2_in1k |
12.11 | 12.15 | 8.34 | 1.865 | 6.5x | 4.5x | 512 / 524 | 208 / 250 | 229 / 316 |
Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
|---|---|---|---|---|---|---|
regnety_160.tv2_in1k |
3.07 | 1.08 | 2.22 | 0.48 | 0.04 | 0.06 |
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) |
|---|---|---|---|---|---|---|---|---|---|---|
regnety_160.tv2_in1k |
224x224 | 8.34 | 5.4 | 8.0 | 1.8 | 28 | 1.865 | 208 / 250 | 236 / 290 | 172 |
Fixed-size speed and peak memory, all models
| model | mode | 224x224 |
|---|---|---|
regnety_160.tv2_in1k |
portable | 8.3 ms / 211 / 524 |
regnety_160.tv2_in1k |
kernels | 2.0 ms / 238 / 610 |
Fixed-size cells: time (ms) / peak allocated / peak reserved memory (MiB).
Hardware, protocol and caveats: benchmarks (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
from fastforks import classification
model = classification.load("regnety_160.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 https://github.com/kleinicke/fastforks). Other variants: regnety_160.tv2_in1k.
Kernels backend
classification.load("regnety_160.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 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.