Add model EMA (Exponential Moving Average) #114
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
sokovninn
requested review from
kozlov721,
klemen1999,
tersekmatija and
conorsim
and removed request for
a team
github-actions
bot
added
enhancement
sokovninn
changed the title
klemen1999
reviewed
Oct 14, 2024
Codecov ReportAttention: Patch coverage is
✅ All tests successful. No failed tests found.
Additional details and impacted files@@ Coverage Diff @@
## main #114 +/- ##
=======================================
Coverage ? 97.06%
=======================================
Files ? 141
Lines ? 6133
Branches ? 0
=======================================
Hits ? 5953
Misses ? 180
Partials ? 0 ☔ View full report in Codecov by Sentry. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces a new Exponential Moving Average (EMA) callback for model training, along with its integration and corresponding unit tests. The main changes include the addition of the
EMACallbackclass, its registration, and tests to ensure its functionality.New EMA Callback
luxonis_train/callbacks/ema.py: Added theEMACallbackclass, which includes methods for initializing the EMA, updating EMA weights, and handling checkpoint saving/loading. This class helps in maintaining a moving average of model parameters to potentially improve model performance.Integration
luxonis_train/callbacks/__init__.py: Registered theEMACallbackin theCALLBACKSregistry and added it to the__all__list for proper module export. [1] [2] [3]Unit Tests
tests/unittests/test_callbacks/test_ema.py: Added unit tests for theEMACallbackto verify its initialization, batch update, checkpoint saving/loading, and validation epoch handling.