Giters

happynear / AMSoftmax

A simple yet effective loss function for face verification.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how does the loss converge

jyshee opened this issue · comments

commented

Does the AMS loss have the similar converge curve with softmax loss? In my exps, the AMS loss (set m=1) changes little during training, even after lots of iters.

commented

Loss is meaningless in AMS. Maybe you can output the accuracy, target logit etc to observe the convergence of the network.