About loss - Githubissues

WeitaoVan / L-GM-loss

Implementation of our accepted CVPR 2018 paper "Rethinking Feature Distribution for Loss Functions in Image Classification"

MIT License

172 stars 34 forks source link

Closed yuancoder222 closed 5 years ago

yuancoder222 commented 5 years ago

I have a question that why after classdistance layer, there is still a softmaxloss layer, so you change your distribution again.