Implementation of the Convolution class. More...

#include <convolution.hpp>

Public Member Functions
	Convolution ()
	Create the Convolution object.

	Convolution (const size_t inSize, const size_t outSize, const size_t kernelWidth, const size_t kernelHeight, const size_t strideWidth=1, const size_t strideHeight=1, const size_t padW=0, const size_t padH=0, const size_t inputWidth=0, const size_t inputHeight=0, const std::string &paddingType="None")
	Create the Convolution object using the specified number of input maps, output maps, filter size, stride and padding parameter. More...

	Convolution (const size_t inSize, const size_t outSize, const size_t kernelWidth, const size_t kernelHeight, const size_t strideWidth, const size_t strideHeight, const std::tuple< size_t, size_t > &padW, const std::tuple< size_t, size_t > &padH, const size_t inputWidth=0, const size_t inputHeight=0, const std::string &paddingType="None")
	Create the Convolution object using the specified number of input maps, output maps, filter size, stride and padding parameter. More...

void	Reset ()

template<typename eT >
void	Forward (const arma::Mat< eT > &input, arma::Mat< eT > &output)
	Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...

template<typename eT >
void	Backward (const arma::Mat< eT > &, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. More...

template<typename eT >
void	Gradient (const arma::Mat< eT > &, const arma::Mat< eT > &error, arma::Mat< eT > &gradient)

OutputDataType const &	Parameters () const
	Get the parameters.

OutputDataType &	Parameters ()
	Modify the parameters.

arma::cube const &	Weight () const
	Get the weight of the layer.

arma::cube &	Weight ()
	Modify the weight of the layer.

arma::mat const &	Bias () const
	Get the bias of the layer.

arma::mat &	Bias ()
	Modify the bias of the layer.

InputDataType const &	InputParameter () const
	Get the input parameter.

InputDataType &	InputParameter ()
	Modify the input parameter.

OutputDataType const &	OutputParameter () const
	Get the output parameter.

OutputDataType &	OutputParameter ()
	Modify the output parameter.

OutputDataType const &	Delta () const
	Get the delta.

OutputDataType &	Delta ()
	Modify the delta.

OutputDataType const &	Gradient () const
	Get the gradient.

OutputDataType &	Gradient ()
	Modify the gradient.

size_t	InputWidth () const
	Get the input width.

size_t &	InputWidth ()
	Modify input the width.

size_t	InputHeight () const
	Get the input height.

size_t &	InputHeight ()
	Modify the input height.

size_t	OutputWidth () const
	Get the output width.

size_t &	OutputWidth ()
	Modify the output width.

size_t	OutputHeight () const
	Get the output height.

size_t &	OutputHeight ()
	Modify the output height.

size_t	InputSize () const
	Get the number of input maps.

size_t	OutputSize () const
	Get the number of output maps.

size_t	KernelWidth () const
	Get the kernel width.

size_t &	KernelWidth ()
	Modify the kernel width.

size_t	KernelHeight () const
	Get the kernel height.

size_t &	KernelHeight ()
	Modify the kernel height.

size_t	StrideWidth () const
	Get the stride width.

size_t &	StrideWidth ()
	Modify the stride width.

size_t	StrideHeight () const
	Get the stride height.

size_t &	StrideHeight ()
	Modify the stride height.

size_t	PadHTop () const
	Get the top padding height.

size_t &	PadHTop ()
	Modify the top padding height.

size_t	PadHBottom () const
	Get the bottom padding height.

size_t &	PadHBottom ()
	Modify the bottom padding height.

size_t	PadWLeft () const
	Get the left padding width.

size_t &	PadWLeft ()
	Modify the left padding width.

size_t	PadWRight () const
	Get the right padding width.

size_t &	PadWRight ()
	Modify the right padding width.

size_t	WeightSize () const
	Get size of weights for the layer.

size_t	InputShape () const
	Get the shape of the input.

template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename ForwardConvolutionRule = NaiveConvolution<ValidConvolution>, typename BackwardConvolutionRule = NaiveConvolution<FullConvolution>, typename GradientConvolutionRule = NaiveConvolution<ValidConvolution>, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >

Implementation of the Convolution class.

The Convolution class represents a single layer of a neural network. Example usage:

Suppose we want to pass a matrix M (2744x100) to a Convolution layer; in this example, M was obtained from "flattening" 100 images (or Mel cepstral coefficients, if we talk about speech, or whatever you like) of dimension 196x14. In other words, the first 196 columns of each row of M will be made of the 196 columns of the first row of each of the 100 images (or Mel cepstral coefficients). Then the next 295 columns of M (196 - 393) will be made of the 196 columns of the second row of the 100 images (or Mel cepstral coefficients), etc. Given that the size of our 2-D input images is 196x14, the parameters for our Convolution layer will be something like this:

Convolution<> c(1, // Number of input activation maps.
                14, // Number of output activation maps.
                3, // Filter width.
                3, // Filter height.
                1, // Stride along width.
                1, // Stride along height.
                0, // Padding width.
                0, // Padding height.
                196, // Input width.
                14); // Input height.

This Convolution<> layer will treat each column of the input matrix M as a 2-D image (or object) of the original 196x14 size, using this as the input for the 14 filters of this example.

Template Parameters

ForwardConvolutionRule	Convolution to perform forward process.
BackwardConvolutionRule	Convolution to perform backward process.
GradientConvolutionRule	Convolution to calculate gradient.
InputDataType	Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataType	Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).

Constructor & Destructor Documentation

◆ Convolution() [1/2]

template<typename ForwardConvolutionRule , typename BackwardConvolutionRule , typename GradientConvolutionRule , typename InputDataType , typename OutputDataType >

mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Convolution	(	const size_t	inSize,
		const size_t	outSize,
		const size_t	kernelWidth,
		const size_t	kernelHeight,
		const size_t	strideWidth = `1`,
		const size_t	strideHeight = `1`,
		const size_t	padW = `0`,
		const size_t	padH = `0`,
		const size_t	inputWidth = `0`,
		const size_t	inputHeight = `0`,
		const std::string &	paddingType = `"None"`
	)

Create the Convolution object using the specified number of input maps, output maps, filter size, stride and padding parameter.

Parameters

inSize	The number of input maps.
outSize	The number of output maps.
kernelWidth	Width of the filter/kernel.
kernelHeight	Height of the filter/kernel.
strideWidth	Stride of filter application in the x direction.
strideHeight	Stride of filter application in the y direction.
padW	Padding width of the input.
padH	Padding height of the input.
inputWidth	The width of the input data.
inputHeight	The height of the input data.
paddingType	The type of padding (Valid or Same). Defaults to None.

◆ Convolution() [2/2]

template<typename ForwardConvolutionRule , typename BackwardConvolutionRule , typename GradientConvolutionRule , typename InputDataType , typename OutputDataType >

mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Convolution	(	const size_t	inSize,
		const size_t	outSize,
		const size_t	kernelWidth,
		const size_t	kernelHeight,
		const size_t	strideWidth,
		const size_t	strideHeight,
		const std::tuple< size_t, size_t > &	padW,
		const std::tuple< size_t, size_t > &	padH,
		const size_t	inputWidth = `0`,
		const size_t	inputHeight = `0`,
		const std::string &	paddingType = `"None"`
	)

Create the Convolution object using the specified number of input maps, output maps, filter size, stride and padding parameter.

Parameters

inSize	The number of input maps.
outSize	The number of output maps.
kernelWidth	Width of the filter/kernel.
kernelHeight	Height of the filter/kernel.
strideWidth	Stride of filter application in the x direction.
strideHeight	Stride of filter application in the y direction.
padW	A two-value tuple indicating padding widths of the input. First value is padding at left side. Second value is padding on right side.
padH	A two-value tuple indicating padding heights of the input. First value is padding at top. Second value is padding on bottom.
inputWidth	The width of the input data.
inputHeight	The height of the input data.
paddingType	The type of padding (Valid or Same). Defaults to None.

Member Function Documentation

◆ Backward()

template<typename ForwardConvolutionRule , typename BackwardConvolutionRule , typename GradientConvolutionRule , typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Backward	(	const arma::Mat< eT > &	,
		const arma::Mat< eT > &	gy,
		arma::Mat< eT > &	g
	)

Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f.

Using the results from the feed forward pass.

Parameters

*	(input) The propagated input activation.
gy	The backpropagated error.
g	The calculated gradient.

◆ Forward()

template<typename ForwardConvolutionRule , typename BackwardConvolutionRule , typename GradientConvolutionRule , typename InputDataType , typename OutputDataType >

template<typename eT >

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Forward	(	const arma::Mat< eT > &	input,
		arma::Mat< eT > &	output
	)

Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f.

Parameters

input	Input data used for evaluating the specified function.
output	Resulting output activation.

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

src/mlpack/methods/ann/layer/convolution.hpp
src/mlpack/methods/ann/layer/convolution_impl.hpp

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ Convolution() [1/2]

◆ Convolution() [2/2]

Member Function Documentation

◆ Backward()

◆ Forward()