mlboydaisuke / U2Net-ExecuTorch

huggingface.co
Total runs: 34
24-hour runs: 0
7-day runs: -20
30-day runs: -41
Model's Last Updated: August 15 2026
image-segmentation

Introduction of U2Net-ExecuTorch

Model Details of U2Net-ExecuTorch

u2net — ExecuTorch XNNPACK

  • Source : xuebinqin/U-2-Net + Carve/u2net-universal weights
  • License : Apache-2.0
  • Input : [[1, 3, 320, 320]] — RGB, ImageNet norm, 320x320
  • Output : saliency mask [1,1,320,320] 0-1 (sigmoid); min-max normalize then resize to the source image
Variants

All variants take and return fp32 tensors — swap the .pte file, keep your app code.

precision file size (MB) parity vs fp32 eager (worst corr) Mac median (ms)*
fp32 u2net_xnnpack_fp32.pte 176.0 1.000000 56.5

*Mac arm64, single process, median of 10 — a reference point for relative cost only, not a device number (torch eager fp32 on the same machine: 138.5 ms).

Precisions that did not earn a slot
  • fp16 is not shipped : it comes out at 100% of the fp32 file (176.0 MB vs 176.0 MB), so it buys nothing. XNNPACK serializes convolution weights as fp32 no matter what dtype the graph carries, so on a conv-heavy model fp16 saves no disk and only adds cast operations. Reach for int8 here, not fp16.
  • int8 is not shipped : mask IoU 0.814 median and 0.212 at worst against fp32. The int8 build systematically shrinks weak saliency: on a photo where fp32 marks 2.2% of pixels foreground it marks 0.5%. On images with an unambiguous subject it agrees closely (0.99), but that is not a promise this model can make.
Verification (executorch 1.4.0, torch 2.13.0)

Parity is measured against the fp32 eager model on real image input; corr is the correlation over all elements of each output tensor.

output shape max_abs_diff corr
0 [1, 1, 320, 320] 5.239e-05 1.000000

XNNPACK delegate coverage (fp32): 100.0% (477/477 ops)

Conversion

torch.export -> to_edge_transform_and_lower(XnnpackPartitioner) -> .pte (conversion scripts: executorch-models )

Runs of mlboydaisuke U2Net-ExecuTorch on huggingface.co

34
Total runs
0
24-hour runs
-10
3-day runs
-20
7-day runs
-41
30-day runs

More Information About U2Net-ExecuTorch huggingface.co Model

More U2Net-ExecuTorch license Visit here:

https://choosealicense.com/licenses/apache-2.0

U2Net-ExecuTorch huggingface.co

U2Net-ExecuTorch huggingface.co is an AI model on huggingface.co that provides U2Net-ExecuTorch's model effect (), which can be used instantly with this mlboydaisuke U2Net-ExecuTorch model. huggingface.co supports a free trial of the U2Net-ExecuTorch model, and also provides paid use of the U2Net-ExecuTorch. Support call U2Net-ExecuTorch model through api, including Node.js, Python, http.

mlboydaisuke U2Net-ExecuTorch online free

U2Net-ExecuTorch huggingface.co is an online trial and call api platform, which integrates U2Net-ExecuTorch's modeling effects, including api services, and provides a free online trial of U2Net-ExecuTorch, you can try U2Net-ExecuTorch online for free by clicking the link below.

mlboydaisuke U2Net-ExecuTorch online free url in huggingface.co:

https://huggingface.co/mlboydaisuke/U2Net-ExecuTorch

U2Net-ExecuTorch install

U2Net-ExecuTorch is an open source model from GitHub that offers a free installation service, and any user can find U2Net-ExecuTorch on GitHub to install. At the same time, huggingface.co provides the effect of U2Net-ExecuTorch install, users can directly use U2Net-ExecuTorch installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

U2Net-ExecuTorch install url in huggingface.co:

https://huggingface.co/mlboydaisuke/U2Net-ExecuTorch

Url of U2Net-ExecuTorch

U2Net-ExecuTorch huggingface.co Url

Provider of U2Net-ExecuTorch huggingface.co

mlboydaisuke
ORGANIZATIONS

Other API from mlboydaisuke