Fills a Blob with values $x \sim U(-a, +a)$ where $ a $ is set inversely proportional to number of incoming nodes, outgoing nodes, or their average. More...

#include <filler.hpp>

Inheritance diagram for caffe::XavierFiller< Dtype >:

Public Member Functions
	XavierFiller (const FillerParameter &param)

virtual void	Fill (Blob< Dtype > *blob)

Public Member Functions inherited from caffe::Filler< Dtype >
	Filler (const FillerParameter &param)

Additional Inherited Members
Protected Attributes inherited from caffe::Filler< Dtype >
FillerParameter	filler_param_

Detailed Description

template<typename Dtype>
class caffe::XavierFiller< Dtype >

Fills a Blob with values $x \sim U(-a, +a)$ where $ a $ is set inversely proportional to number of incoming nodes, outgoing nodes, or their average.

A Filler based on the paper [Bengio and Glorot 2010]: Understanding the difficulty of training deep feedforward neuralnetworks.

It fills the incoming matrix by randomly sampling uniform data from [-scale, scale] where scale = sqrt(3 / n) where n is the fan_in, fan_out, or their average, depending on the variance_norm option. You should make sure the input blob has shape (num, a, b, c) where a * b * c = fan_in and num * b * c = fan_out. Note that this is currently not the case for inner product layers.

TODO(dox): make notation in above comment consistent with rest & use LaTeX.

The documentation for this class was generated from the following file:

include/caffe/filler.hpp

Public Member Functions

Additional Inherited Members

Detailed Description

template<typename Dtype> class caffe::XavierFiller< Dtype >

template<typename Dtype>
class caffe::XavierFiller< Dtype >