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

add temporal head and MPJPELoss #522

Merged
merged 7 commits into from
Mar 25, 2021
Merged

Conversation

cherryjm
Copy link
Contributor

@cherryjm cherryjm commented Mar 16, 2021

  • add temporal head
  • add MPJPELoss for 3D pose estimation

@cherryjm cherryjm closed this Mar 16, 2021
@cherryjm cherryjm reopened this Mar 16, 2021
@codecov
Copy link

codecov bot commented Mar 16, 2021

Codecov Report

Merging #522 (7a4bbec) into master (0bd81c8) will increase coverage by 0.07%.
The diff coverage is 90.78%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #522      +/-   ##
==========================================
+ Coverage   81.16%   81.23%   +0.07%     
==========================================
  Files         139      140       +1     
  Lines        9572     9647      +75     
  Branches     1530     1537       +7     
==========================================
+ Hits         7769     7837      +68     
- Misses       1458     1464       +6     
- Partials      345      346       +1     
Flag Coverage Δ
unittests 81.13% <90.78%> (+0.07%) ⬆️

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

Impacted Files Coverage Δ
mmpose/core/post_processing/__init__.py 100.00% <ø> (ø)
mmpose/models/losses/regression_loss.py 95.65% <81.81%> (-4.35%) ⬇️
.../models/keypoint_heads/temporal_regression_head.py 91.07% <91.07%> (ø)
mmpose/core/post_processing/post_transforms.py 87.50% <100.00%> (+0.90%) ⬆️
mmpose/models/keypoint_heads/__init__.py 100.00% <100.00%> (ø)
mmpose/models/losses/__init__.py 100.00% <100.00%> (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 0bd81c8...7a4bbec. Read the comment docs.

@innerlee innerlee requested a review from jin-s13 March 16, 2021 08:45
Copy link
Collaborator

@jin-s13 jin-s13 left a comment

Choose a reason for hiding this comment

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

It looks good to me.

@innerlee
Copy link
Contributor

The code is clean. An important thing is to make sure that the flip op correctly changes all affected coordinates.

- "target_image_path": path to the image file
output (np.ndarray[N, K, 3]): predicted regression vector.
"""
target_image_paths = []
Copy link
Contributor

Choose a reason for hiding this comment

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

Save a few lines by

target_image_paths = [m['target_image_path'] for m in metas]

@innerlee innerlee merged commit 5c213af into open-mmlab:master Mar 25, 2021
@jin-s13 jin-s13 mentioned this pull request Mar 28, 2021
5 tasks
rollingman1 pushed a commit to rollingman1/mmpose that referenced this pull request Nov 5, 2021
* resolve comments

* update changelog

* patch for Issue open-mmlab#522

* fix bug

* fix bug
shuheilocale pushed a commit to shuheilocale/mmpose that referenced this pull request May 6, 2023
ajgrafton pushed a commit to ajgrafton/mmpose that referenced this pull request Mar 6, 2024
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.

None yet

4 participants