Implementation of the Atrous Convolution class. More...

#include <atrous_convolution.hpp>

Public Member Functions
	AtrousConvolution ()
	Create the AtrousConvolution object.

	AtrousConvolution (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 size_t dilationWidth=1, const size_t dilationHeight=1, const std::string &paddingType="None")
	Create the AtrousConvolution object using the specified number of input maps, output maps, filter size, stride, dilation and padding parameter. More...

	AtrousConvolution (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 size_t dilationWidth=1, const size_t dilationHeight=1, const std::string &paddingType="None")
	Create the AtrousConvolution object using the specified number of input maps, output maps, filter size, stride, dilation 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.

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 input size.

size_t	OutputSize () const
	Get the output size.

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	DilationWidth () const
	Get the dilation rate on the X axis.

size_t &	DilationWidth ()
	Modify the dilation rate on the X axis.

size_t	DilationHeight () const
	Get the dilation rate on the Y axis.

size_t &	DilationHeight ()
	Modify the dilation rate on the Y axis.

ann::Padding const &	Padding () const
	Get the internal Padding layer.

ann::Padding &	Padding ()
	Modify the internal Padding layer.

size_t	WeightSize () const
	Get size of the weight matrix.

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::AtrousConvolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >

Implementation of the Atrous Convolution class.

The Atrous Convolution class represents a single layer of a neural network. Atrous (or Dilated) Convolutions are just simple convolutions applied to input with the defined, spaces included between the kernel cells, in order to capture a larger field of reception, without having to increase dicrete kernel sizes.

Template Parameters

ForwardConvolutionRule	Atrous Convolution to perform forward process.
BackwardConvolutionRule	Atrous Convolution to perform backward process.
GradientConvolutionRule	Atrous 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

◆ AtrousConvolution() [1/2]

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

mlpack::ann::AtrousConvolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::AtrousConvolution	(	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 size_t	dilationWidth = `1`,
		const size_t	dilationHeight = `1`,
		const std::string &	paddingType = `"None"`
	)

Create the AtrousConvolution object using the specified number of input maps, output maps, filter size, stride, dilation 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 widht of the input data.
inputHeight	The height of the input data.
dilationWidth	The space between the cells of filters in x direction.
dilationHeight	The space between the cells of filters in y direction.
paddingType	The type of padding (Valid or Same). Defaults to None.

◆ AtrousConvolution() [2/2]

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

mlpack::ann::AtrousConvolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::AtrousConvolution	(	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 size_t	dilationWidth = `1`,
		const size_t	dilationHeight = `1`,
		const std::string &	paddingType = `"None"`
	)

Create the AtrousConvolution object using the specified number of input maps, output maps, filter size, stride, dilation 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 widht of the input data.
inputHeight	The height of the input data.
dilationWidth	The space between the cells of filters in x direction.
dilationHeight	The space between the cells of filters in y direction.
paddingType	The type of padding (Valid/Same/None). Defaults to None.

Member Function Documentation

◆ Backward()

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

template<typename eT >

void mlpack::ann::AtrousConvolution< 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::AtrousConvolution< 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/atrous_convolution.hpp
src/mlpack/methods/ann/layer/atrous_convolution_impl.hpp

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ AtrousConvolution() [1/2]

◆ AtrousConvolution() [2/2]

Member Function Documentation

◆ Backward()

◆ Forward()