Implementation of the Atrous Convolution class. More...

Public Member Functions
	AtrousConvolution ()
	Create the AtrousConvolution object. More...

	AtrousConvolution (const size_t inSize, const size_t outSize, const size_t kW, const size_t kH, const size_t dW=1, const size_t dH=1, const size_t padW=0, const size_t padH=0, const size_t inputWidth=0, const size_t inputHeight=0, const size_t dilationW=1, const size_t dilationH=1)
	Create the AtrousConvolution object using the specified number of input maps, output maps, filter size, stride, dilation and padding parameter. More...

template < typename eT >
void	Backward (const arma::Mat< eT > &&, 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...

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

OutputDataType const &	Delta () const
	Get the delta. More...

OutputDataType &	Delta ()
	Modify the delta. More...

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

OutputDataType const &	Gradient () const
	Get the gradient. More...

OutputDataType &	Gradient ()
	Modify the gradient. More...

size_t const &	InputHeight () const
	Get the input height. More...

size_t &	InputHeight ()
	Modify the input height. More...

size_t const &	InputWidth () const
	Get the input width. More...

size_t &	InputWidth ()
	Modify input the width. More...

size_t const &	OutputHeight () const
	Get the output height. More...

size_t &	OutputHeight ()
	Modify the output height. More...

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

OutputDataType &	OutputParameter ()
	Modify the output parameter. More...

size_t const &	OutputWidth () const
	Get the output width. More...

size_t &	OutputWidth ()
	Modify the output width. More...

OutputDataType const &	Parameters () const
	Get the parameters. More...

OutputDataType &	Parameters ()
	Modify the parameters. More...

void	Reset ()

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

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).

Definition at line 51 of file atrous_convolution.hpp.

Constructor & Destructor Documentation

◆ AtrousConvolution() [1/2]

AtrousConvolution ( )

Create the AtrousConvolution object.

◆ AtrousConvolution() [2/2]

AtrousConvolution	(	const size_t	inSize,
		const size_t	outSize,
		const size_t	kW,
		const size_t	kH,
		const size_t	dW = `1`,
		const size_t	dH = `1`,
		const size_t	padW = `0`,
		const size_t	padH = `0`,
		const size_t	inputWidth = `0`,
		const size_t	inputHeight = `0`,
		const size_t	dilationW = `1`,
		const size_t	dilationH = `1`
	)

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.
kW	Width of the filter/kernel.
kH	Height of the filter/kernel.
dW	Stride of filter application in the x direction.
dH	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.
dilationW	The space between the cells of filters in x direction.
dilationH	The space between the cells of filters in y direction.

Member Function Documentation

◆ Backward()

void Backward	(	const arma::Mat< eT > &&	,
		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.

◆ Bias()

arma::mat& Bias ( )

inline

Modify the bias weights of the layer.

Definition at line 170 of file atrous_convolution.hpp.

References AtrousConvolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::serialize().

◆ Delta() [1/2]

OutputDataType const& Delta ( ) const

inline

Get the delta.

Definition at line 140 of file atrous_convolution.hpp.

◆ Delta() [2/2]

OutputDataType& Delta ( )

inline

Modify the delta.

Definition at line 142 of file atrous_convolution.hpp.

◆ Forward()

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.

Parameters

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

◆ Gradient() [1/3]

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

◆ Gradient() [2/3]

OutputDataType const& Gradient ( ) const

inline

Get the gradient.

Definition at line 145 of file atrous_convolution.hpp.

◆ Gradient() [3/3]

OutputDataType& Gradient ( )

inline

Modify the gradient.

Definition at line 147 of file atrous_convolution.hpp.

◆ InputHeight() [1/2]

size_t const& InputHeight ( ) const

inline

Get the input height.

Definition at line 155 of file atrous_convolution.hpp.

◆ InputHeight() [2/2]

size_t& InputHeight ( )

inline

Modify the input height.

Definition at line 157 of file atrous_convolution.hpp.

◆ InputWidth() [1/2]

size_t const& InputWidth ( ) const

inline

Get the input width.

Definition at line 150 of file atrous_convolution.hpp.

◆ InputWidth() [2/2]

size_t& InputWidth ( )

inline

Modify input the width.

Definition at line 152 of file atrous_convolution.hpp.

◆ OutputHeight() [1/2]

size_t const& OutputHeight ( ) const

inline

Get the output height.

Definition at line 165 of file atrous_convolution.hpp.

◆ OutputHeight() [2/2]

size_t& OutputHeight ( )

inline

Modify the output height.

Definition at line 167 of file atrous_convolution.hpp.

◆ OutputParameter() [1/2]

OutputDataType const& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 135 of file atrous_convolution.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 137 of file atrous_convolution.hpp.

◆ OutputWidth() [1/2]

size_t const& OutputWidth ( ) const

inline

Get the output width.

Definition at line 160 of file atrous_convolution.hpp.

◆ OutputWidth() [2/2]

size_t& OutputWidth ( )

inline

Modify the output width.

Definition at line 162 of file atrous_convolution.hpp.

◆ Parameters() [1/2]

OutputDataType const& Parameters ( ) const

inline

Get the parameters.

Definition at line 130 of file atrous_convolution.hpp.

◆ Parameters() [2/2]

OutputDataType& Parameters ( )

inline

Modify the parameters.

Definition at line 132 of file atrous_convolution.hpp.

◆ Reset()

void Reset ( )

◆ serialize()

void serialize	(	Archive &	ar,
		const unsigned	int
	)

Serialize the layer.

Referenced by AtrousConvolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Bias().

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

/home/jenkins-mlpack/mlpack.org/_src/mlpack-3.2.1/src/mlpack/methods/ann/layer/atrous_convolution.hpp

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ AtrousConvolution() [1/2]

◆ AtrousConvolution() [2/2]

Member Function Documentation

◆ Backward()

◆ Bias()

◆ Delta() [1/2]

◆ Delta() [2/2]

◆ Forward()

◆ Gradient() [1/3]

◆ Gradient() [2/3]

◆ Gradient() [3/3]

◆ InputHeight() [1/2]

◆ InputHeight() [2/2]

◆ InputWidth() [1/2]

◆ InputWidth() [2/2]

◆ OutputHeight() [1/2]

◆ OutputHeight() [2/2]

◆ OutputParameter() [1/2]

◆ OutputParameter() [2/2]

◆ OutputWidth() [1/2]

◆ OutputWidth() [2/2]

◆ Parameters() [1/2]

◆ Parameters() [2/2]

◆ Reset()

◆ serialize()