Fix Division by Zero and Deprecated Function Bugs #120
Conversation
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
- Added epsilon (1e-8) to normalization in data.py and models.py to prevent crash on uniform images. - Replaced deprecated torch.nn.functional.sigmoid with torch.sigmoid.
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Outdated suggestions cannot be applied.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.
Fix Numerical Instability (NaNs) and Deprecated Functions in Physics Informed Super Resolution
Description
This PR addresses critical stability issues in the
DeepLense_Physics_Informed_Super_Resolution_Anirudh_Shankarproject. Specifically, it prevents potentialNaNvalues (division by zero) that occur during normalization when an input image or feature map is uniform (i.e.,max == min).It also modernizes the codebase by replacing deprecated PyTorch functions that may cause warnings or errors in newer versions.
Changes
1e-8) to the denominator during Min-Max normalization in fGAN/data.py and fGAN/models.py.torch.nn.functional.sigmoidwithtorch.sigmoidinfGAN/models.py.