mlboydaisuke / ormbg-ExecuTorch

huggingface.co
Total runs: 96
24-hour runs: 0
7-day runs: -10
30-day runs: -3
Model's Last Updated: September 04 2026
image-segmentation

Introduction of ormbg-ExecuTorch

Model Details of ormbg-ExecuTorch

ormbg_isnet — ExecuTorch XNNPACK

  • Source : schirrmacher/ormbg
  • License : Apache-2.0
  • Input : [[1, 3, 1024, 1024]] — RGB 0-1, 1024x1024
  • Output : alpha mask [1,1,1024,1024] 0-1 (sigmoid)
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 ormbg_isnet_xnnpack_fp32.pte 176.1 1.000000 121.7
int8 ormbg_isnet_xnnpack_int8.pte 44.3 0.999988 87.2

*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: 375.5 ms).

Checked in the task's own units

Correlation is a first filter. These are the numbers that decide:

  • int8 — measured in the units that matter for this model: mask IoU at 0.5, median 0.9994 over five real images (worst 0.9916) against the fp32 build.
Precisions that did not earn a slot
  • fp16 is not shipped : it comes out at 100% of the fp32 file (176.1 MB vs 176.1 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.
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, 1024, 1024] 2.205e-06 1.000000

XNNPACK delegate coverage (fp32): 100.0% (467/467 ops)

Conversion

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

Runs of mlboydaisuke ormbg-ExecuTorch on huggingface.co

96
Total runs
0
24-hour runs
7
3-day runs
-10
7-day runs
-3
30-day runs

More Information About ormbg-ExecuTorch huggingface.co Model

More ormbg-ExecuTorch license Visit here:

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

ormbg-ExecuTorch huggingface.co

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

mlboydaisuke ormbg-ExecuTorch online free

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

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

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

ormbg-ExecuTorch install

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

ormbg-ExecuTorch install url in huggingface.co:

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

Url of ormbg-ExecuTorch

ormbg-ExecuTorch huggingface.co Url

Provider of ormbg-ExecuTorch huggingface.co

mlboydaisuke
ORGANIZATIONS

Other API from mlboydaisuke