Download README.md from fastforks/efficientformer: direct link, hf CLI and curl.
- Browser
- Download file 7.24 kB
-
https://huggingface.co/fastforks/efficientformer/resolve/main/README.md
- Command line
-
hf download hf://fastforks/efficientformer/README.md
-
curl -L -o README.md https://huggingface.co/fastforks/efficientformer/resolve/main/README.md
library_name: fastforks
pipeline_tag: image-classification
license: apache-2.0
tags:
- classification
- image-classification
- cuda
- pytorch
- fastforks
- fastforks-card
EfficientFormer (fastforks)
EfficientFormer (Li et al. 2022, Snap Research): a hybrid classifier, pooling blocks on feature maps followed by transformer blocks on tokens.
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/efficientformer_l1.snap_dist_in1k, https://huggingface.co/timm/efficientformer_l3.snap_dist_in1k, https://huggingface.co/timm/efficientformer_l7.snap_dist_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 |
|---|---|---|---|---|
efficientformer_l1.snap_dist_in1k@1 |
efficientformer_l1.snap_dist_in1k.safetensors | dab9ad0e328f |
Apache-2.0 | yes |
efficientformer_l3.snap_dist_in1k@1 |
efficientformer_l3.snap_dist_in1k.safetensors | ab0c5bfd7c18 |
Apache-2.0 | yes |
efficientformer_l7.snap_dist_in1k@1 |
efficientformer_l7.snap_dist_in1k.safetensors | c497103536ff |
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/efficientformer_l1.snap_dist_in1k/blob/8738a58190800aaf5995f453b05f643df453a565/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): efficientformer_l1.snap_dist_in1k 224x224 (0.1 GiB peak allocated, 0.1 reserved); efficientformer_l3.snap_dist_in1k 224x224 (0.2 GiB peak allocated, 0.2 reserved); efficientformer_l7.snap_dist_in1k 224x224 (0.3 GiB peak allocated, 0.3 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 |
|---|---|---|---|---|---|---|---|---|---|---|
efficientformer_l1.snap_dist_in1k |
224x224 | 4.87 | 6.40 | 3.72 | β | β | β | 104 / 124 | 93 / 104 | β |
efficientformer_l3.snap_dist_in1k |
224x224 | 8.39 | 11.0 | 6.37 | β | β | β | 214 / 236 | 161 / 216 | β |
efficientformer_l7.snap_dist_in1k |
224x224 | 12.3 | 15.9 | 9.65 | β | β | β | 505 / 522 | 300 / 324 | β |
Startup and first call
| model | load (s): original | portable | kernels | first call (s): original | portable | kernels |
|---|---|---|---|---|---|---|
efficientformer_l1.snap_dist_in1k |
0.22 | 1.71 | β | 0.22 | 0.07 | β |
efficientformer_l3.snap_dist_in1k |
0.37 | 1.86 | β | 0.03 | 0.08 | β |
efficientformer_l7.snap_dist_in1k |
0.93 | 2.27 | β | 0.03 | 0.07 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|---|
efficientformer_l1.snap_dist_in1k |
224x224 | 3.72 ms | 1.69 ms | 0.335 ms | β | 9.10 s | 35.4 s | 93 / 104 | 125 / 144 | β | 128 / 142 |
efficientformer_l3.snap_dist_in1k |
224x224 | 6.37 ms | 2.57 ms | 0.750 ms | β | 11.8 s | 39.4 s | 161 / 216 | 193 / 216 | β | 227 / 286 |
efficientformer_l7.snap_dist_in1k |
224x224 | 9.65 ms | 3.69 ms | 1.40 ms | β | 14.4 s | 40.0 s | 300 / 324 | 332 / 364 | β | 460 / 490 |
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 |
|---|---|---|---|---|---|
efficientformer_l1.snap_dist_in1k |
ImageNet-1k val, 5000 random images, top-1 / top-5 % | 81.14 / 95.22 | 81.16 / 95.24 | 81.14 / 95.12 | |
efficientformer_l3.snap_dist_in1k |
ImageNet-1k val, 5000 random images, top-1 / top-5 % | 83.12 / 96.32 | 83.14 / 96.32 | 83.16 / 96.32 | |
efficientformer_l7.snap_dist_in1k |
ImageNet-1k val, 5000 random images, top-1 / top-5 % | 84.44 / 96.68 | 84.44 / 96.66 | 84.38 / 96.68 |
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| <= 1.3e-05 vs the original. GPU, float16 (the default), portable and kernels: mean |diff| <= 0.0046 and p99 <= 0.019 (absolute error of the output logits).
Usage
from fastforks import classification
model = classification.load("efficientformer_l1.snap_dist_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: efficientformer_l1.snap_dist_in1k, efficientformer_l3.snap_dist_in1k, efficientformer_l7.snap_dist_in1k.
Kernels backend
No kernels backend: not built yet: pooling blocks with Conv-BN MLPs and LayerNorm transformer blocks with learned attention bias tables need a dedicated kernels runner.