deezer / deezer/spleeter

[Discussion] moving_mean=0, moving_variance=1 in all BatchNormalization layers

Open
#151 0 comments 0 reactions 0 assignees View on GitHub
question
Dominant language
Python
Stars
28.4k
Forks
3.1k
PR merge metrics
No merged PRs in 30d

Description

I loaded the weights in all BatchNormalization layers, and find that all moving_mean == 0 and moving_variance==1. Why does this happen? Because it seems to me that these two values should be calculated during training. It's confusing to me

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.