microsoft / microsoft/onnxruntime-inference-examples

On SNPE example on ARM64 Windows device, snpe-onnx-to-dlc is for x64 only

Open
#197 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
1.7k
Forks
414
Avg merge
1d 6h
Merged PRs (30d)
14

Description

I'm using ARM64 Windows (Dev Kit 2023).

According to https://github.com/microsoft/onnxruntime-inference-examples/tree/main/c_sharp/Snpe_EP/vgg16_image_classification,
the instruction is to install 'SNPE SDK for Linux' on WSL2.
But, snpe-onnx-to-dlc is for x64 only and thus not executable on WSL2, thus it fails at the step below.

Follow steps 3 through 5 in [Qualcomm's tutorial](https://developer.qualcomm.com/sites/default/files/docs/snpe/tutorial_onnx.html)
These will generate a vgg16.dlc file in $SNPE_ROOT/models/VGG/dlc/

It worked on Linux x64 system. Is there a way to make WSL run the snpe-onnx-to-dlc like x64 emulation?

Thank you.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with c_sharp/Snpe_EP/vgg16_image_classification and the linked Qualcomm SNPE tutorial, focusing on the steps that invoke snpe-onnx-to-dlc. Reproduce the failure on ARM64 Windows under WSL2 and compare it with the reported working Linux x64 setup; done means documenting whether supported emulation or another documented path exists.

Written by the indexing model from the issue text.

Assessment

Tech stack
csharp, linux
Domain
machine-learning, operating-systems
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.