Improve dataloader robustness with safe normalization and consistent tensor conversion#147
Open
SarthakJagota wants to merge 2 commits intoML4SCI:mainfrom
Open
Improve dataloader robustness with safe normalization and consistent tensor conversion#147SarthakJagota wants to merge 2 commits intoML4SCI:mainfrom
SarthakJagota wants to merge 2 commits intoML4SCI:mainfrom
Conversation
Address review: add epsilon normalization, enforce float32, include sanity check for constant images
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 PR improves the reliability of the dataloader used in the DeepLense pipeline.
Changes
Added a safety check in the normalization step to prevent division-by-zero errors for constant images
Ensured the dataset consistently returns torch.Tensor objects even when transforms are not applied
Verified that the dataloader runs successfully after these changes
These updates improve reproducibility and make the pipeline more robust across different datasets and environments.
Fixes #145