Download README.md from fastforks/davit: direct link, hf CLI and curl.
- Browser
- Download file 6.76 kB
-
https://huggingface.co/fastforks/davit/resolve/main/README.md
- Command line
-
hf download hf://fastforks/davit/README.md
-
curl -L -o README.md https://huggingface.co/fastforks/davit/resolve/main/README.md
library_name: fastforks
pipeline_tag: image-classification
license: apache-2.0
tags:
- classification
- image-classification
- cuda
- pytorch
- fastforks
- fastforks-card
DaViT (fastforks)
DaViT (Ding et al. 2022): a hierarchical vision transformer that alternates window (spatial) attention and channel-group attention.
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/huggingface/pytorch-image-models at 0df212b369a5.
Author weight repos: https://huggingface.co/timm/davit_base.msft_in1k, https://huggingface.co/timm/davit_small.msft_in1k, https://huggingface.co/timm/davit_tiny.msft_in1k.
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.
| variant | weights (author link) | SHA-256 | weights licence | commercial use |
|---|---|---|---|---|
davit_base.msft_in1k@1 |
davit_base.msft_in1k.safetensors | cd12f8bd194e |
Apache-2.0 | yes |
davit_small.msft_in1k@1 |
davit_small.msft_in1k.safetensors | cef0f04c7349 |
Apache-2.0 | yes |
davit_tiny.msft_in1k@1 |
davit_tiny.msft_in1k.safetensors | 085937207d2e |
Apache-2.0 | 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: https://huggingface.co/timm/davit_tiny.msft_in1k/blob/982f32c73d98f9966df4a7178b32b820bed3c1b1/README.md
Input size
fixed 224x224: the input is resized (short side 235) and centre-cropped to it
Tested up to (portable, fp16, RTX 5060 Ti 16 GB): davit_base.msft_in1k 224x224 (0.2 GiB peak allocated, 0.2 reserved); davit_small.msft_in1k 224x224 (0.1 GiB peak allocated, 0.1 reserved); davit_tiny.msft_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 |
|---|---|---|---|---|---|---|---|---|---|---|
davit_base.msft_in1k |
224x224 | 13.4 | 20.0 | 11.7 | β | β | β | 537 / 548 | 212 / 224 | β |
davit_small.msft_in1k |
224x224 | 13.0 | 18.8 | 12.8 | β | β | β | 319 / 324 | 136 / 150 | β |
davit_tiny.msft_in1k |
224x224 | 6.93 | 9.88 | 6.33 | β | β | β | 196 / 204 | 96 / 116 | β |
Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
|---|---|---|---|---|---|---|
davit_base.msft_in1k |
0.99 | 1.84 | β | 0.56 | 0.27 | β |
davit_small.msft_in1k |
0.53 | 1.60 | β | 0.02 | 0.23 | β |
davit_tiny.msft_in1k |
0.39 | 1.47 | β | 0.85 | 0.25 | β |
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) |
|---|---|---|---|---|---|---|---|---|---|---|---|
davit_base.msft_in1k |
224x224 | 11.7 ms | 5.48 ms | 2.28 ms | β | 21.8 s | 71.1 s | 212 / 224 | 242 / 262 | β | 403 / 422 |
davit_small.msft_in1k |
224x224 | 12.8 ms | 5.54 ms | 1.92 ms | β | 21.8 s | 66.4 s | 136 / 150 | 166 / 190 | β | 234 / 254 |
davit_tiny.msft_in1k |
224x224 | 6.33 ms | 3.10 ms | 1.03 ms | β | 15.5 s | 53.8 s | 96 / 116 | 125 / 136 | β | 159 / 166 |
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 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 |
|---|---|---|---|---|---|
davit_tiny.msft_in1k |
ImageNet-1k val, 5000 random images, top-1 / top-5 % | 83.94 / 96.50 | 83.92 / 96.50 | 83.94 / 96.56 | |
davit_small.msft_in1k |
ImageNet-1k val, 5000 random images, top-1 / top-5 % | 85.18 / 97.20 | 85.16 / 97.20 | 85.24 / 97.18 | |
davit_base.msft_in1k |
ImageNet-1k val, 5000 random images, top-1 / top-5 % | 85.58 / 97.10 | 85.58 / 97.10 | 85.66 / 97.12 |
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| <= 3.3e-06 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0026 and p99 <= 0.011 (absolute error of the output logits).
Usage
from fastforks import classification
model = classification.load("davit_base.msft_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: davit_base.msft_in1k, davit_small.msft_in1k, davit_tiny.msft_in1k.
Kernels backend
No kernels backend: not implemented: window attention and channel attention with depthwise position convolutions: needs its own runner.