Fix pixel weighting in segmentation cross entropy - #3
Open
sylvesterkaczmarek wants to merge 1 commit into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Weighted cross entropy broadcasts
[B,H,W]losses against[B,1,H,W]weights, coupling different images and scaling the loss with batch size. Entirely masked images can still receive gradients.Flatten leading batch dimensions into the loss layout and align pixel weights with the unreduced loss. Cover single images, multiple batch axes, soft targets, zero weights and gradients. Correct the metrics tracker test that expected the doubled loss.
Validation: all 31 loss and metrics tests pass; 13 new regression cases fail on unchanged upstream. Syntax and
git diff --checkpass.