BiFuse icon indicating copy to clipboard operation
BiFuse copied to clipboard

Published 20 hours ago • verified publisher icon yuhsuanyeh

What the detail about loss function in training process

Open Xpangz opened this issue 3 years ago • 0 comments

Hey! I find the paper doesn't show loss function in training stage completely, it just introduce reverse Huber loss for optimizing predictions from both Be and Bc, what about the next two stage?

Xpangz avatar Jun 27 '21 06:06 Xpangz