Skip to content

StevenBanama/Embbeding-Layer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

A common layers for Embedding

In this repos, we relize commom version of embedding layer for face recognize, meanwhile we add parameters m4 to improve the performace. In the cloth recognition, formula 1.2 improve the top 1 acc from 62.1% to 63.7% for resetnet50.

The embedding space for iras dataset show as follow. Our plan got a more compat embedding, which not only reduce the distance of inner cluster, but also gain the inter distance in "arc-face expand".

Reference: