-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
[Refactor] Change the meaning of momentum
in EMA
#1581
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
please also add the warning in the initialize function of average_model.py
Co-authored-by: Yanhong Zeng <zengyh1900@gmail.com>
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@plyfager please fix ut.
…to plyfager/ema-check
Codecov ReportBase: 87.92% // Head: 87.93% // Increases project coverage by
Additional details and impacted files@@ Coverage Diff @@
## dev-1.x #1581 +/- ##
========================================
Coverage 87.92% 87.93%
========================================
Files 399 399
Lines 26051 26059 +8
Branches 4048 4051 +3
========================================
+ Hits 22906 22914 +8
Misses 2240 2240
Partials 905 905
Flags with carried forward coverage won't be shown. Click here to find out more.
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. |
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
For aligning with MMEngine, we change the meaning of momentum in EMA. In past, we set momentum a number close to 1. and use it to multiply with ema_weights/ average_params.
Now we set momentum to a number close to 0., and use it to multiply with source_weights/ source_params.
This will cause the following changes:
momentum
will be changed.Notion:
Since RamupEMA's momentum won't be set in configs, so we only need to change the codes.
Modification
Please briefly describe what modification is made in this PR.
Who can help? @ them here!
BC-breaking (Optional)
Does the modification introduce changes that break the backward-compatibility of the downstream repositories?
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
Before PR:
After PR: