happynear / AMSoftmax

A simple yet effective loss function for face verification.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

I put inner_product_layer and LabelSpecificAdd together,but it gets worse result.

recordcode opened this issue · comments

Hi,thanks for your work. Did you ever try to put it together? I think put it together shouldn't make it worse. But , when I use it to train lenet(dataset:mnist) , it actually get worse result.