Skip to content

fix a bug of random flip in MixUp #9336

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.

Sign up for GitHub

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

Jump to bottom
Merged
ZwwWayne merged 1 commit into from
Nov 21, 2022
Merged

fix a bug of random flip in MixUp #9336

ZwwWayne merged 1 commit into from
Nov 21, 2022

Conversation

@motokimura
Copy link

@motokimura motokimura commented Nov 16, 2022 •
edited
Loading

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.

Motivation

Please describe the motivation of this PR and the goal you want to achieve through this PR.

Random flip in MixUp augmentation seems to have a bug.

In current implementation, when flip_ratio is set to 0, mixup image is always flipped.

Modification

Please briefly describe what modification is made in this PR.

Fixed the above behavior.

BC-breaking (Optional)

Does the modification introduce changes that break the backward-compatibility of the downstream repos?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.

Use cases (Optional)

If this PR introduces a new feature, it is better to list some use cases here, and update the documentation.

Checklist

  1. Pre-commit or other linting tools are used to fix the potential lint issues.
  2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness.
  3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMCls.
  4. The documentation has been modified accordingly, like docstring or example tutorials.

@CLAassistant
Copy link

CLAassistant commented Nov 16, 2022 •
edited
Loading

CLA assistant check
All committers have signed the CLA.

@ZwwWayne ZwwWayne added this to the 2.27.0 milestone Nov 21, 2022
@ZwwWayne ZwwWayne changed the base branch from master to dev November 21, 2022 02:48
@ZwwWayne ZwwWayne requested a review from RangiLyu November 21, 2022 02:48
@ZwwWayne ZwwWayne assigned RangiLyu and unassigned wanghonglie Nov 21, 2022
@codecov
Copy link

codecov bot commented Nov 21, 2022 •
edited
Loading

Codecov Report

Base: 64.19% // Head: 64.17% // Decreases project coverage by -0.02% ⚠️

Coverage data is based on head (c0e9462) compared to base (e71b499).
Patch coverage: 100.00% of modified lines in pull request are covered.

Additional details and impacted files 
@@            Coverage Diff             @@
##              dev    #9336      +/-   ##
==========================================
- Coverage   64.19%   64.17%   -0.03%     
==========================================
  Files         361      361              
  Lines       29544    29544              
  Branches     5023     5023              
==========================================
- Hits        18966    18960       -6     
- Misses       9570     9579       +9     
+ Partials     1008     1005       -3
Flag Coverage Δ
unittests 64.14% <100.00%> (-0.03%) ⬇️

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

Impacted Files Coverage Δ
mmdet/datasets/pipelines/transforms.py 76.00% <100.00%> (ø)
mmdet/models/detectors/cornernet.py 94.87% <0.00%> (-5.13%) ⬇️
mmdet/models/dense_heads/corner_head.py 68.33% <0.00%> (-1.39%) ⬇️
mmdet/core/bbox/assigners/max_iou_assigner.py 72.36% <0.00%> (-1.32%) ⬇️
mmdet/models/roi_heads/mask_heads/maskiou_head.py 89.65% <0.00%> (+2.29%) ⬆️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.

@ZwwWayne ZwwWayne merged commit 2c82b7e into open-mmlab:dev Nov 21, 2022
@motokimura motokimura deleted the fix_mixup_flip branch November 21, 2022 10:19
SakiRinn pushed a commit to SakiRinn/mmdetection-locount that referenced this pull request Mar 17, 2023
@motokimura @SakiRinn
[Fix]: fix random flipping ratio compare of mixup image (open-mmlab#9336
b351736 
)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@RangiLyu RangiLyu RangiLyu approved these changes

Assignees

@RangiLyu RangiLyu

Labels

None yet

Projects

None yet

Milestone

2.27.0

Development

Successfully merging this pull request may close these issues.

5 participants

@motokimura @CLAassistant @RangiLyu @wanghonglie @ZwwWayne