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

Jump to bottom

Why dice smoothing only applied in denominator? #610

Open

fiskrt opened this issue Apr 14, 2023 · 0 comments

fiskrt commented Apr 14, 2023

Hi, is there a reason why the dice smoothing is only applied in the denominator:

AdelaiDet/adet/modeling/condinst/dynamic_mask_head.py

Lines 57 to 58 in f60e856

    
           union = (x ** 2.0).sum(dim=1) + (target ** 2.0).sum(dim=1) + eps 
        
           loss = 1. - (2 * intersection / union)

and not like
loss = 1. - ((2 * intersection + eps) / (union + eps))

This causes all zero-input predictions to always maximize the loss even if it's completely correct.

The text was updated successfully, but these errors were encountered:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment