[TO_REVIEW] Add epsilon in MCC to prevent log(0) #270
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
tgnassou
reviewed
Oct 30, 2024
skada/deep/losses.py
Outdated
| @@ -395,7 +395,8 @@ def mcc_loss(y, T=1): | |||
| y_scaled = probability_scaling(y, temperature=T) | |||
|
|
|||
| # Uncertainty Reweighting & class correlation matrix | |||
| H = -torch.sum(y_scaled * torch.log(y_scaled), axis=1) | |||
| eps = 1e-7 # To avoid log(0) | |||
There was a problem hiding this comment.
eps should be a parameter
tgnassou
approved these changes
Oct 31, 2024
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Outdated suggestions cannot be applied.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 includes changes to the
mcc_lossfunction to handle zero probabilities correctly, updates to the corresponding tests, and necessary imports.Improvements to
mcc_lossfunction:skada/deep/losses.py: Added a small epsilon value to avoid taking the logarithm of zero, which can lead to numerical issues. ([skada/deep/losses.pyL398-R399](https://github.com/scikit-adaptation/skada/pull/270/files#diff-0774706cdd6571bdf61f65dbc2fe0fd5c9e6ae928b28459a523339e962180212L398-R399))Updates to tests:
skada/deep/tests/test_deep_class_confusion.py: Added a new testtest_mcc_with_zerosto ensure that themcc_lossfunction handles zero probabilities correctly. ([skada/deep/tests/test_deep_class_confusion.pyR59-R81](https://github.com/scikit-adaptation/skada/pull/270/files#diff-71736bf2bcae56dd6073bdfd1c728374aa1b4f9d9a72594e27a02b269b14a169R59-R81))