#include <GNeuralNet.h>

Inheritance diagram for GClasses::GLayerConvolutional2D:

Public Member Functions
	GLayerConvolutional2D (size_t inputCols, size_t inputRows, size_t inputChannels, size_t kernelSize, size_t kernelsPerChannel, GActivationFunction *pActivationFunction=NULL)
	General-purpose constructor. For example, if your input is a 64x48 color (RGB) image, then inputCols will be 64, inputRows will be 48, and inputChannels will be 3. The total input size will be 9216 (64483=9216). If kernelSize is 5, then the output will consist of 60 columns (64-5+1=60) and 44 rows (48-5+1=44). If kernelsPerChannel is 2, then there will be 6 (32=6) channels in the output, for a total of 15840 (6044*6=15840) output values. (kernelSize must be <= inputSamples.) More...

	GLayerConvolutional2D (GDomNode *pNode)
	Deserializing constructor. More...

virtual	~GLayerConvolutional2D ()

virtual void	activate ()
	Applies the activation function to the net vector to compute the activation vector. More...

virtual double *	activation ()
	Returns the activation values from the most recent call to feedForward(). More...

virtual void	backPropError (GNeuralNetLayer *pUpStreamLayer, size_t inputStart=0)
	Backpropagates the error from this layer into the upstream layer's error vector. (Assumes that the error in this layer has already been computed and deactivated. The error this computes is with respect to the output of the upstream layer.) More...

double *	bias ()

double *	biasDelta ()

virtual void	computeError (const double *pTarget)
	Computes the error terms associated with the output of this layer, given a target vector. (Note that this is the error of the output, not the error of the weights. To obtain the error term for the weights, deactivateError must be called.) More...

virtual void	copyBiasToNet ()
	Copies the bias vector into the net vector. More...

virtual void	copyWeights (GNeuralNetLayer *pSource)
	Copy the weights from pSource to this layer. (Assumes pSource is the same type of layer.) More...

virtual size_t	countWeights ()
	Returns the number of double-precision elements necessary to serialize the weights of this layer into a vector. More...

virtual void	deactivateError ()
	Multiplies each element in the error vector by the derivative of the activation function. This results in the error having meaning with respect to the weights, instead of the output. (Assumes the error for this layer has already been computed.) More...

virtual void	diminishWeights (double amount, bool regularizeBiases)
	Diminishes all the weights (that is, moves them in the direction toward 0) by the specified amount. More...

virtual void	dropConnect (GRand &rand, double probOfDrop)
	Throws an exception, because convolutional layers do not support dropConnect. More...

virtual void	dropOut (GRand &rand, double probOfDrop)
	Randomly sets the activation of some units to 0. More...

virtual double *	error ()
	Returns a buffer used to store error terms for each unit in this layer. More...

virtual void	feedIn (const double *pIn, size_t inputStart, size_t inputCount)
	Feeds a portion of the inputs through the weights and updates the net. More...

virtual size_t	inputs ()
	Returns the number of values expected to be fed as input into this layer. More...

GMatrix &	kernels ()

virtual void	maxNorm (double max)
	Clips each kernel weight (not including the bias) to fall between -max and max. More...

double *	net ()
	Returns the net vector (that is, the values computed before the activation function was applied) from the most recent call to feedForward(). More...

virtual size_t	outputs ()
	Returns the number of nodes or units in this layer. More...

virtual void	perturbWeights (GRand &rand, double deviation, size_t start, size_t count)
	Perturbs the weights that feed into the specifed units with Gaussian noise. start specifies the first unit whose incoming weights are perturbed. count specifies the maximum number of units whose incoming weights are perturbed. More...

virtual void	renormalizeInput (size_t input, double oldMin, double oldMax, double newMin=0.0, double newMax=1.0)
	Throws an exception. More...

virtual void	resetWeights (GRand &rand)
	Initialize the weights with small random values. More...

virtual void	resize (size_t inputs, size_t outputs, GRand *pRand=NULL, double deviation=0.03)
	Resizes this layer. If pRand is non-NULL, an exception is thrown. More...

virtual void	scaleUnitIncomingWeights (size_t unit, double scalar)
	Throws an exception. More...

virtual void	scaleUnitOutgoingWeights (size_t input, double scalar)
	Throws an exception. More...

virtual void	scaleWeights (double factor, bool scaleBiases)
	Multiplies all the weights in this layer by the specified factor. More...

virtual GDomNode *	serialize (GDom *pDoc)
	Marshall this layer into a DOM. More...

virtual const char *	type ()
	Returns the type of this layer. More...

virtual double	unitIncomingWeightsL1Norm (size_t unit)
	Throws an exception. More...

virtual double	unitIncomingWeightsL2Norm (size_t unit)
	Throws an exception. More...

virtual double	unitOutgoingWeightsL1Norm (size_t input)
	Throws an exception. More...

virtual double	unitOutgoingWeightsL2Norm (size_t input)
	Throws an exception. More...

virtual void	updateBias (double learningRate, double momentum)
	Updates the bias of this layer by gradient descent. (Assumes the error has already been computed and deactivated.) More...

virtual void	updateWeights (const double *pUpStreamActivation, size_t inputStart, size_t inputCount, double learningRate, double momentum)
	Updates the weights that feed into this layer (not including the bias) by gradient descent. (Assumes the error has already been computed and deactivated.) More...

virtual void	updateWeightsAndRestoreDroppedOnes (const double *pUpStreamActivation, size_t inputStart, size_t inputCount, double learningRate, double momentum)
	This is a special weight update method for use with drop-connect. It updates the weights, and restores the weights that were previously dropped by a call to dropConnect. More...

virtual size_t	vectorToWeights (const double *pVector)
	Deserialize from a vector to the weights in this layer. Return the number of elements consumed. More...

virtual size_t	weightsToVector (double *pOutVector)
	Serialize the weights in this layer into a vector. Return the number of elements written. More...

Public Member Functions inherited from GClasses::GNeuralNetLayer
	GNeuralNetLayer ()

virtual	~GNeuralNetLayer ()

virtual void	copySingleNeuronWeights (size_t source, size_t dest)

void	feedForward (const double *pIn)
	Feeds in the bias and pIn, then computes the activation of this layer. More...

virtual void	feedIn (GNeuralNetLayer *pUpStreamLayer, size_t inputStart)
	Feeds the previous layer's activation into this layer. (Implementations for specialized hardware may override this method to avoid shuttling the previous layer's activation back to host memory.) More...

GMatrix *	feedThrough (const GMatrix &data)
	Feeds a matrix through this layer, one row at-a-time, and returns the resulting transformed matrix. More...

virtual void	getWeightsSingleNeuron (size_t outputNode, double *&weights)
	Gets the weights and bias of a single neuron. More...

virtual void	setWeightsSingleNeuron (size_t outputNode, const double *weights)
	Gets the weights and bias of a single neuron. More...

virtual void	updateWeights (GNeuralNetLayer *pUpStreamLayer, size_t inputStart, double learningRate, double momentum)
	Refines the weights by gradient descent. More...

virtual void	updateWeightsAndRestoreDroppedOnes (GNeuralNetLayer *pUpStreamLayer, size_t inputStart, double learningRate, double momentum)
	Refines the weights by gradient descent. More...

virtual bool	usesGPU ()
	Returns true iff this layer does its computations in parallel on a GPU. More...

Protected Attributes
GMatrix	m_activation

GMatrix	m_bias

GMatrix	m_delta

size_t	m_inputChannels

size_t	m_inputCols

size_t	m_inputRows

size_t	m_kernelCount

GMatrix	m_kernels

size_t	m_kernelsPerChannel

size_t	m_outputCols

size_t	m_outputRows

GActivationFunction *	m_pActivationFunction

Additional Inherited Members
Static Public Member Functions inherited from GClasses::GNeuralNetLayer
static GNeuralNetLayer *	deserialize (GDomNode *pNode)
	Unmarshalls the specified DOM node into a layer object. More...

Protected Member Functions inherited from GClasses::GNeuralNetLayer
GDomNode *	baseDomNode (GDom *pDoc)

Constructor & Destructor Documentation

GClasses::GLayerConvolutional2D::GLayerConvolutional2D	(	size_t	inputCols,
		size_t	inputRows,
		size_t	inputChannels,
		size_t	kernelSize,
		size_t	kernelsPerChannel,
		GActivationFunction *	pActivationFunction = `NULL`
	)

General-purpose constructor. For example, if your input is a 64x48 color (RGB) image, then inputCols will be 64, inputRows will be 48, and inputChannels will be 3. The total input size will be 9216 (64*48*3=9216). If kernelSize is 5, then the output will consist of 60 columns (64-5+1=60) and 44 rows (48-5+1=44). If kernelsPerChannel is 2, then there will be 6 (3*2=6) channels in the output, for a total of 15840 (60*44*6=15840) output values. (kernelSize must be <= inputSamples.)

GClasses::GLayerConvolutional2D::GLayerConvolutional2D ( GDomNode * pNode )

Deserializing constructor.

virtual GClasses::GLayerConvolutional2D::~GLayerConvolutional2D ( )

virtual

Member Function Documentation

virtual void GClasses::GLayerConvolutional2D::activate ( )

virtual

Applies the activation function to the net vector to compute the activation vector.

Public Member Functions

Protected Attributes

Additional Inherited Members

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation