mattpoggi / mono-uncertainty

CVPR 2020 - On the uncertainty of self-supervised monocular depth estimation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Modifying Eq 12/13 to deal with negative loss

MohitLamba94 opened this issue · comments

Hi,
Thanks for this great work. In Eq. 12/13 you have a log(variance) that might go negative for variance<1. Assuming, variance to be always +ve can we modify the Eq. 12/13 to log(1+variance) to prevent negative loss and allowing better optimization?
Will this modification hamper training or net output during inference?

Hi,
I never tried, because the negative loss never gave issues in my experiments.
You can use sigmoids over the outputs, but I think your solution should work as well.