Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Feature] add onnxruntime test tool #277

Closed
wants to merge 4 commits into from

Conversation

grimoire
Copy link
Member

Hi
This PR adds an ONNXRuntime test tool to align results between PyTorch and ONNXRuntime.
Tested on mattor and restorer models.

@innerlee
Copy link
Contributor

Hi do you want to write a doc on how to use this tool? Add contents to here https://mmediting.readthedocs.io/en/latest/tools_scripts.html?highlight=onnx#convert-to-onnx-experimental .
Particularly, if you give the list of models that have been verified, and post the related command, that would be very great!

@codecov
Copy link

codecov bot commented Apr 26, 2021

Codecov Report

Merging #277 (459862e) into master (ce4ad1f) will increase coverage by 0.05%.
The diff coverage is n/a.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #277      +/-   ##
==========================================
+ Coverage   79.94%   79.99%   +0.05%     
==========================================
  Files         159      160       +1     
  Lines        7942     8003      +61     
  Branches     1177     1185       +8     
==========================================
+ Hits         6349     6402      +53     
- Misses       1449     1456       +7     
- Partials      144      145       +1     
Flag Coverage Δ
unittests 79.99% <ø> (+0.05%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
mmedit/models/backbones/sr_backbones/__init__.py 100.00% <0.00%> (ø)
mmedit/models/backbones/sr_backbones/rdn.py 86.66% <0.00%> (ø)

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update ce4ad1f...459862e. Read the comment docs.


### Evaluate ONNX model with ONNXRuntime

We provide `tools/ort_test.py` to evaluate ONNX model with ONNXRuntime backend.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ort is cryptic. How about renaming the file to onnx_runtime_test.py?

@grimoire
Copy link
Member Author

Close this PR.
I will update the code at #279.

@grimoire grimoire closed this Apr 26, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants