mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-17 21:10:43 +00:00
451c02543a
### Description
Allow WebGPU backend to specify `preferredLayout`. Default is NHWC.
```js
const options = {executionProviders: [{name:'webgpu', preferredLayout: 'NCHW'}]};
sess1 = await ort.InferenceSession.create('./mobilenetv2-12.onnx', options);
```
### Motivation and Context
- implement @qjia7's requirement for an easier way to do performance
comparison between NCHW vs NHWC.
- It's possible that NCHW does better on some models and NHWC on others.
So offer user the capability to switch.
|
||
|---|---|---|
| .. | ||
| backend-impl.ts | ||
| backend.ts | ||
| env-impl.ts | ||
| env.ts | ||
| index.ts | ||
| inference-session-impl.ts | ||
| inference-session.ts | ||
| onnx-value.ts | ||
| tensor-conversion-impl.ts | ||
| tensor-conversion.ts | ||
| tensor-factory-impl.ts | ||
| tensor-factory.ts | ||
| tensor-impl-type-mapping.ts | ||
| tensor-impl.ts | ||
| tensor-utils-impl.ts | ||
| tensor-utils.ts | ||
| tensor.ts | ||
| training-session-impl.ts | ||
| training-session.ts | ||
| version.ts | ||