google / google/torchax

Would nn.BatchNorm2d work as expected?

Open
#22 13 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
243
Forks
38
Avg merge
15h 32m
Merged PRs (30d)
2

Description

Dear authors,

Thanks for your wonderful work! I wonder if nn.BatchNorm2d works. During training, the running mean and running variance are updated according to their own rule instead of being updated with the optimizer.

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.