Skip to content

[Fix] Fix indentation bug in hd_loss that mishandles ignore_index #3869

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

Open
Mr-Neutr0n wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[Fix] Fix indentation bug in hd_loss that mishandles ignore_index #3869

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2e5fcb7
[Fix] Fix indentation bug in hd_loss that mishandles ignore_index
Mr-Neutr0n Feb 11, 2026
097f1d4
ci: retrigger pr_stage_test
Mr-Neutr0n Jun 4, 2026
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
6 changes: 3 additions & 3 deletions mmseg/models/losses/huasdorff_distance_loss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,9 +67,9 @@ def hd_loss(seg_soft: Tensor,
dtm = s_dtm + g_dtm
multiplied = torch.einsum('bxy, bxy->bxy', delta_s, dtm)
hd_loss = multiplied.mean()
if class_weight is not None:
hd_loss *= class_weight[i]
total_loss += hd_loss
if class_weight is not None:
hd_loss *= class_weight[i]
total_loss += hd_loss

return total_loss / num_class

Expand Down