chrischute/real-nvp

Why k is used in loss?

Closed this issue · 1 comments

Hi, I wonder why k is used to compute the gauss probability in the loss function

Hi, I wonder why k is used to compute the gauss probability in the loss function

Hi, @ZRJMoon , I'm confused about this, could you give an explanation?
And I think this constant term is useless for optimization?