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

Support Onnx #305

Merged
merged 6 commits into from Nov 30, 2020
Merged

Support Onnx #305

merged 6 commits into from Nov 30, 2020

Conversation

jin-s13
Copy link
Collaborator

@jin-s13 jin-s13 commented Nov 25, 2020

fix #131
fix #289
fix #299

@innerlee
Copy link
Contributor

Is tools/__init__.py needed?

@jin-s13
Copy link
Collaborator Author

jin-s13 commented Nov 25, 2020

Is tools/__init__.py needed?

No. I just deleted it.

@codecov
Copy link

codecov bot commented Nov 25, 2020

Codecov Report

Merging #305 (64cb626) into master (a82dd48) will decrease coverage by 0.02%.
The diff coverage is 100.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #305      +/-   ##
==========================================
- Coverage   83.82%   83.79%   -0.03%     
==========================================
  Files         114      114              
  Lines        7085     7085              
  Branches     1122     1122              
==========================================
- Hits         5939     5937       -2     
  Misses        941      941              
- Partials      205      207       +2     
Flag Coverage Δ
unittests 83.79% <100.00%> (-0.03%) ⬇️

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

Impacted Files Coverage Δ
mmpose/__init__.py 100.00% <100.00%> (ø)
mmpose/datasets/pipelines/mesh_transform.py 94.31% <0.00%> (-1.14%) ⬇️

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 a82dd48...ffc8d98. Read the comment docs.

@innerlee
Copy link
Contributor

Hi @RunningLeon, could you help review this pr? A detail to check is that the precision is relaxed to 1e-5 here.

@RunningLeon
Copy link

@innerlee
Normally, relative tolerance of 1e-5 is precise enough. Check here for setting of torchvision.

@innerlee
Copy link
Contributor

@RunningLeon everything okay other than typos?

tools/pytorch2onnx.py Outdated Show resolved Hide resolved
@innerlee
Copy link
Contributor

@RunningLeon good to go?

@RunningLeon
Copy link

@innerlee I think it's ok from my side of view.

@innerlee
Copy link
Contributor

Thanks!

@innerlee innerlee merged commit a2d0598 into master Nov 30, 2020
@jin-s13 jin-s13 deleted the onnx branch November 30, 2020 05:04
shuheilocale pushed a commit to shuheilocale/mmpose that referenced this pull request May 6, 2023
* add onnx

* add pytorch2onnx

* rm unnecessary files

* fix typo

* fix typos

* rm unnecessary index
ajgrafton pushed a commit to ajgrafton/mmpose that referenced this pull request Mar 6, 2024
* add onnx

* add pytorch2onnx

* rm unnecessary files

* fix typo

* fix typos

* rm unnecessary index
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
3 participants