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] Exponential Moving Average Hook #542

Merged
merged 2 commits into from
Sep 23, 2021

Conversation

ckkelvinchan
Copy link
Member

@ckkelvinchan ckkelvinchan commented Sep 18, 2021

Motivation

Many existing methods, such as Real-ESRGAN, use exponential moving average hook during training.

Modification

This PR supports exponential moving average hook. Users can define this hook in the configuration file.

Remark

Codes adopted from MMGeneration.

@ckkelvinchan ckkelvinchan added need test status/WIP work in progress normally labels Sep 18, 2021
@codecov
Copy link

codecov bot commented Sep 18, 2021

Codecov Report

Merging #542 (df46f0a) into master (7037144) will increase coverage by 0.05%.
The diff coverage is 96.22%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master     #542      +/-   ##
==========================================
+ Coverage   80.28%   80.34%   +0.05%     
==========================================
  Files         194      195       +1     
  Lines       10805    10857      +52     
  Branches     1640     1650      +10     
==========================================
+ Hits         8675     8723      +48     
- Misses       1872     1874       +2     
- Partials      258      260       +2     
Flag Coverage Δ
unittests 80.34% <96.22%> (+0.05%) ⬆️

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

Impacted Files Coverage Δ
mmedit/core/hooks/ema.py 96.07% <96.07%> (ø)
mmedit/core/hooks/__init__.py 100.00% <100.00%> (ø)
...ls/components/stylegan2/generator_discriminator.py 83.73% <0.00%> (-1.21%) ⬇️

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 7037144...df46f0a. Read the comment docs.

@ckkelvinchan ckkelvinchan removed need test status/WIP work in progress normally labels Sep 20, 2021
@innerlee innerlee merged commit b688219 into open-mmlab:master Sep 23, 2021
Yshuo-Li pushed a commit to Yshuo-Li/mmediting that referenced this pull request Jul 15, 2022
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