Generalize dice_loss with alpha/beta weighting #1458
+130
−48
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
rdyro
reviewed
Nov 7, 2025
Collaborator
rdyro
left a comment
rdyro
left a comment
There was a problem hiding this comment.
Nice, thank you for this PR! I left 1 comment
optax/losses/_segmentation.py
Outdated
| ) | ||
|
|
||
|
|
||
| def dice_plus_ce_loss( |
Collaborator
There was a problem hiding this comment.
In the spirit of modularity, maybe this can be removed? Can the user add the dice and ce losses themselves? Do you see an advantage to exposing this as a single function?
Contributor
Author
There was a problem hiding this comment.
Yes, I agree. I will remove this and the related stuff and recommit.
Apologies for such a late reply.
aymuos15
changed the title
Contributor
Author
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Outdated suggestions cannot be applied.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.
This should now close: #1358
As per the discussion here: #1366 (comment) the weighing with dice should accommodate some more overlap losses automatically.