search

microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
https://onnxruntime.ai
MIT License
14.13k stars 2.85k forks source link

[Web] Demucs model won't run in both WASM and WGPU #22031

Open gianlourbano opened 1 week ago

gianlourbano commented 1 week ago

Describe the issue

I converted the model from pytorch to onnx as described here, with some issues. The model works in onnx python, but in wasm /webgpu the runtime dies without error. The optimized version of the model runs in wasm, but not webgpu. I don't know if this problem is related to the model conversion or the runtime. I have tested with both @latest and @dev.

To reproduce

Here's a link to a sample repo, instructions in README.

Urgency

Urgent, as this project is related to my thesis

ONNX Runtime Installation

Released Package

ONNX Runtime Version or Commit ID

1.19.2, 1.20.0-dev.20240907-ad9afbb042

Execution Provider

'wasm'/'cpu' (WebAssembly CPU), 'webgpu' (WebGPU)

gyagp commented 1 week ago

For WebGPU EP, the problem is related to op unsqueeze. According the ONNX spec (https://onnx.ai/onnx/operators/onnx__Unsqueeze.html), axes of unsqueeze is a list of integers, but in your model, it's just a scalar "1".

gianlourbano commented 1 week ago

So the problem is related to the dynamo export of torch?

fs-eire commented 1 week ago

Technically the axes should always be a 1D tensor. However, in reality, the CPU code has loosen the limit:

https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/core/providers/cpu/tensor/unsqueeze.cc#L60-L62

perhaps webgpu should have same behavior to CPU.

22054