Skip to content

bug: bceloss not decrease #23

@oreo34567

Description

@oreo34567

i found a bug: if using bceloss in train.py, then unet3plus.py should not apply a sigmoid activation

❌ before

return F.sigmoid(d1)

✅ after

return d1

Otherwise you're applying sigmoid twice and the loss may not decrease

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions