Skip to content

Fix minor typo in dice.py #1181

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 16, 2025
Merged

Fix minor typo in dice.py #1181

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions segmentation_models_pytorch/losses/dice.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,8 +115,8 @@ def forward(self, y_pred: torch.Tensor, y_true: torch.Tensor) -> torch.Tensor:
else:
loss = 1.0 - scores

# Dice loss is undefined for non-empty classes
# So we zero contribution of channel that does not have true pixels
# Dice loss is undefined for empty images with no classes
# So we set the contribution of any channel without true pixels to zero
# NOTE: A better workaround would be to use loss term `mean(y_pred)`
# for this case, however it will be a modified jaccard loss

Expand Down