deepinsight / deepinsight/insightface

Why you want backbone's gradient to multiply world_size (partial fc, pytorch version)

Open
#1,403 3 comments 2 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
29.7k
Forks
6.1k
PR merge metrics
No merged PRs in 30d

Description

I've noticed you enforce backbone's gradient to multiply a scaler world_size , can you explain the insight behind this motivation ?

https://github.com/deepinsight/insightface/blob/79aacd2bb3323fa50a125b828bb1656166604487/recognition/partial_fc/pytorch/partial_fc.py#L190

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.