Conversation
Contributor
EzicStar
commented
Jun 23, 2025
EzicStar
commented
- reduce memory usage when training, testing and predicting
- clean _step logic
- make alibi mask optional when there no attention mask is passed as parameter
- add description to LitVisionTransformer
- close CUDA OOM during validation with full bag size (large slides/tile sets exceed GPU memory) in train/crossval #78
- make validation and testing more efficient - improve lightning_model code - make alibi mask optional when there no attention mask is passed as parameter
Contributor
Author
|
Regarding the TODO left in the _step function, ignored it on purpose 😊 |
georg-wolflein
approved these changes
Jun 24, 2025
Contributor
georg-wolflein
left a comment
georg-wolflein
left a comment
There was a problem hiding this comment.
Nice, thank you so much for diagnosing this significant issue! Could you perform some testing before merging please?
Specifically, could you please do the following (if you haven't already):
- For a dataset that caused CUDA OOM before this PR, can you check that it works now with this PR?
- For a dataset that did not cause CUDA OOM before this PR, can you compare the prediction results to ensure that the numbers didn't change?
Thank you @EzicStar, this is a really important contribution. I approved this PR, so feel free to merge once you addressed the comments (very minor) and performed the experiments outlined above:)
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.