Skip to content

mf1024/Batch-Renormalization-PyTorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 

Repository files navigation

Batch-Renormalization-PyTorch

Batch Renormalization module for PyTorch

Batch Renormalization implementation based on paper https://arxiv.org/abs/1702.03275 . Currently there is only 2D implementation for conv nets.

Usage is the same as for PyTorch BatchNorm2D class: You intialize an instance by providing number of features (number of channels in conv layer). Input is expected to be in shape (N, C, H, W), where: (N - number of samples per batch, C - number of channels, H - height, W - width)

About

Batch Renormalization module for PyTorch based on paper https://arxiv.org/abs/1702.03275 .

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages