Base layer for RBM models. More...

#include <neuron_layer.h>

Inheritance diagram for singa::RBMLayer:

Public Member Functions
void	Setup (const LayerProto &proto, int npartitions) override
	Setup layer properties. More...

const Blob< float > &	neg_data (const Layer *layer)

Blob< float > *	mutable_neg_data (const Layer *layer)

const std::vector< Param * >	GetParams () const override
	Layers that have paramters must override this function. More...

virtual Blob< float > *	Sample (int flat)

Public Member Functions inherited from singa::Layer
virtual void	ComputeFeature (int flag, Metric *perf)=0
	Compute features of this layer based on connected layers. More...

virtual void	ComputeGradient (int flag, Metric *perf)=0
	Compute gradients for parameters and connected layers. More...

virtual ConnectionType	src_neuron_connection (int k) const
	Return the connection type between one neuron of this layer and its source layer. More...

virtual ConnectionType	dst_layer_connection () const
	Return the connection type of this layer and all dst layers. More...

virtual const std::string	DebugString (int step, int flag)
	For print debug info about each layer, e.g., norm of feature vector, norm of parameters. More...

int	partition_dim () const

int	partition_id () const

int	type () const

const std::string &	name () const
	Return name of this layer.

virtual const Blob< float > &	data (const Layer *from) const

virtual Blob< float > *	mutable_data (const Layer *from)

virtual const Blob< float > &	grad (const Layer *from) const

virtual Blob< float > *	mutable_grad (const Layer *from)

const std::vector< Layer * >	srclayers () const
	return LayerS that connected to this layer

const std::vector< Layer * >	dstlayers () const
	return LayerS that this layer connected to

int	srclayers_size () const

int	dstlayers_size () const

void	clear_dstlayers ()

void	clear_srclayers ()

void	add_srclayer (Layer *src)

void	add_dstlayer (Layer *dst)

Protected Attributes
bool	gaussian_
	if ture, sampling according to guassian distribution

int	hdim_
	dimension of the hidden layer

int	vdim_
	dimension of the visible layer

int	batchsize_

bool	first_gibbs_

Param *	weight_

Param *	bias_

Blob< float >	neg_data_

Blob< float >	neg_sample_

Blob< float >	sample_

Protected Attributes inherited from singa::Layer
LayerProto	layer_proto_

Blob< float >	data_

Blob< float >	grad_

std::vector< Layer * >	srclayers_

std::vector< Layer * >	dstlayers_

Additional Inherited Members
Static Public Member Functions inherited from singa::Layer
static Layer *	Create (const LayerProto &proto)

Detailed Description

Base layer for RBM models.

Member Function Documentation

const std::vector<Param*> singa::RBMLayer::GetParams ( ) const

inlineoverridevirtual

Layers that have paramters must override this function.

Parameters

flag	used to get the calling phase, e.g., forward of training (kForward \| kTrain)

Returns: parameters associated with this layer

Reimplemented from singa::Layer.

void singa::RBMLayer::Setup	(	const LayerProto &	proto,
		int	npartitions
	)

overridevirtual

Setup layer properties.

Setup the shapes for data and parameters, also setup some properties based on the layer configuration and connected layers.

Parameters

proto	layer configuration.
npartitions	num of total partitions of the original layer. This layer should be setup as one partition.

Reimplemented from singa::Layer.

Reimplemented in singa::RBMHidLayer, and singa::RBMVisLayer.

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

/home/wangwei/program/asf/release-0.1/apache-singa-incubating-0.1.0-RC1/include/neuralnet/neuron_layer.h

Public Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Member Function Documentation