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

[Fix]: parse scales of list in PyTorch==1.7.0 (#451 in MMPose) #815

Merged
merged 2 commits into from
Feb 4, 2021

Conversation

RunningLeon
Copy link
Collaborator

Fix Issue #451 in MMPose: pytorch2onnx failed with PyTorch>=1.7.0 for hrnet_w32_coco_256x192.py. This problem was once metioned in #4221 as well.

This PR includes:

  1. update _interpolate_get_scales_if_available to support pytorch2onnx with PyTorch<=1.7.0

@codecov
Copy link

codecov bot commented Feb 3, 2021

Codecov Report

Merging #815 (4a92580) into master (6c57b88) will increase coverage by 0.01%.
The diff coverage is 0.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #815      +/-   ##
==========================================
+ Coverage   62.23%   62.25%   +0.01%     
==========================================
  Files         144      144              
  Lines        8506     8504       -2     
  Branches     1522     1523       +1     
==========================================
  Hits         5294     5294              
+ Misses       2945     2943       -2     
  Partials      267      267              
Flag Coverage Δ
unittests 62.25% <0.00%> (+0.01%) ⬆️

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

Impacted Files Coverage Δ
mmcv/onnx/onnx_utils/symbolic_helper.py 0.00% <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 6c57b88...4da41ed. Read the comment docs.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Convert HRNet mmpose model to ONNX
3 participants