webnn/segment-anything-model-webnn
By webnn · ↓ 0 · ♥ 0 · Updated 2025-09-17
What's in this repo
This page lists the files in webnn/segment-anything-model-webnn, including sam_vit_b-decoder-int8.onnx, sam_vit_b-decoder-orig-img-size-dynamic-int8.onnx, sam_vit_b-encoder-int8.onnx and more.
- 7 ONNX models (.onnx files)
- 10 files, including 7 .onnx, 1 .md, 1 .py
- Last updated 2025-09-17
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/sam_vit_b-decoder-int8.onnx | — | Download |
| onnx/sam_vit_b-decoder-orig-img-size-dynamic-int8.onnx | — | Download |
| onnx/sam_vit_b-encoder-int8.onnx | — | Download |
| onnx/sam_vit_b_01ec64.decoder-fp16.onnx | — | Download |
| onnx/sam_vit_b_01ec64.decoder-orig-img-size-dynamic-fp16.onnx | — | Download |
| onnx/sam_vit_b_01ec64.decoder.onnx | — | Download |
| onnx/sam_vit_b_01ec64.encoder-fp16.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Model summary
This Segment Anything Model has been optimized to work with WebNN. This model is licensed under the Apache-2.0 License. For terms of use, please visit the Code of Conduct. If you comply with the license and terms of use, you have the rights described therin. By using this Model, you accept the terms.
Segment-Anything-WebNN is meant to be used with the corresponding sample here.
Model changes
Segment-Anything-Model-WebNN is an ONNX version of the Segment Anything Model, and is optimized for WebNN by using static input shapes and eliminates operators that are not in use.
Please find the original Segment Anything Model here.
Model info
Created: 2025-09-17
Updated: 2025-09-17
View on Hugging Face