Skip to content

compare some face loss with mnist, and visual the features.

Notifications You must be signed in to change notification settings

yangJirui/compareFaceLoss

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Some Face Losses with tensorflow.

Abstract

This is a tensorflow re-implemetation of some Face Losses, Such as Cos Loss... I only do some "toy experiments" with mnist and compare the performance by visual the features.

Compare

1、softmax Loss 1 2

2、cosLoss s = 24. m = 0.2. The visualization is amazing ! 3 4

3、More Face Losses ...

About

compare some face loss with mnist, and visual the features.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages