Deep-Mutual-Learning
Deep-Mutual-Learning copied to clipboard
the kl loss become stable but getting larger
hi,
i have a problem when training recognition task, the kl loss become stable but getting larger , and other loss is getting lower, did you have this problem when training other tasks, and and how did this or what's the reason ?
thanks
@niliusha123 I didn't try this method on other tasks. Maybe you should adjust the coefficients of the different losses.