added setting to skip x epochs when using train_and_test_on_datasets #258
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
Dref360
requested changes
Apr 27, 2023
baal/modelwrapper.py
Outdated
| if patience is not None and (e - best_epoch) > patience and (e > min_epoch_for_es): | ||
| # Early stopping | ||
| break | ||
| hist.append(self.get_metrics()) |
There was a problem hiding this comment.
This is appending the metric twice I think. L184 already does it.
There was a problem hiding this comment.
Yes I made an mistake in the PR, sorry for that
There was a problem hiding this comment.
Hi @studentWUR,
Thank you so much for your Pull Request. Would you mind pushing the requested change so that we can merge this branch?
There was a problem hiding this comment.
Sorry for my late reply; pushing a pull request is new for me; so I am slightly confused. In my forked repo I fixed the abovementioned typo, but how to push this to your git? Can you merge it from mine repo
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Outdated suggestions cannot be applied.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.
Summary:
For training it is not desirable to test at every epoch. This simple update solves this issue. By using a skip_epochs option in train_and_test_on_datasets
Checklist:
tests/documentation_test.py).