All Projects → ChenglongChen → batch_normalization

ChenglongChen / batch_normalization

Licence: other
Batch Normalization Layer for Caffe

Programming Languages

C++
36643 projects - #6 most used programming language
Protocol Buffer
295 projects
Cuda
1817 projects

Batch Normalization Layer for Caffe

This implementation of Batch Normalization is based on MVNLayer in Caffe.

To add this layer, you have to modify common_layers.hpp, layer_factory.cpp and caffe.proto. See Caffe wiki

NOTE

This implementation is very basic which just performs batch normalization computation. Two pieces in the paper are still missing here:

  • fixed mean & variance for inference
  • per batch shuffling for thorough randomness

Update log

2016/01/18 An improved version is provided here with moving average statistics for inference.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].