mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType > Class Template Reference

Implementation of the Convolution class. More...

Public Member Functions
	Convolution ()
	Create the Convolution object. More...
	Convolution (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)
	Create the Convolution object using the specified number of input maps, output maps, filter size, stride 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...
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...
InputDataType const &	InputParameter () const
	Get the input parameter. More...
InputDataType &	InputParameter ()
	Modify the input parameter. 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...

Private Member Functions
size_t	ConvOutSize (const size_t size, const size_t k, const size_t s, const size_t p)
template<typename eT >
void	Pad (const arma::Mat< eT > &input, size_t wPad, size_t hPad, arma::Mat< eT > &output)
template<typename eT >
void	Pad (const arma::Cube< eT > &input, size_t wPad, size_t hPad, arma::Cube< eT > &output)
template<typename eT >
void	Rotate180 (const arma::Cube< eT > &input, arma::Cube< eT > &output)
template<typename eT >
void	Rotate180 (const arma::Mat< eT > &input, arma::Mat< eT > &output)

Private Attributes
arma::mat	bias
	Locally-stored bias term object. More...
OutputDataType	delta
	Locally-stored delta object. More...
size_t	dH
	Locally-stored stride of the filter in y-direction. More...
size_t	dW
	Locally-stored stride of the filter in x-direction. More...
OutputDataType	gradient
	Locally-stored gradient object. More...
arma::cube	gradientTemp
	Locally-stored transformed gradient parameter. More...
arma::cube	gTemp
	Locally-stored transformed error parameter. More...
size_t	inputHeight
	Locally-stored input height. More...
arma::cube	inputPaddedTemp
	Locally-stored transformed padded input parameter. More...
InputDataType	inputParameter
	Locally-stored input parameter object. More...
arma::cube	inputTemp
	Locally-stored transformed input parameter. More...
size_t	inputWidth
	Locally-stored input width. More...
size_t	inSize
	Locally-stored number of input units. More...
size_t	kH
	Locally-stored filter/kernel height. More...
size_t	kW
	Locally-stored filter/kernel width. More...
size_t	outputHeight
	Locally-stored output height. More...
OutputDataType	outputParameter
	Locally-stored output parameter object. More...
arma::cube	outputTemp
	Locally-stored transformed output parameter. More...
size_t	outputWidth
	Locally-stored output width. More...
size_t	outSize
	Locally-stored number of output units. More...
size_t	padH
	Locally-stored padding height. More...
size_t	padW
	Locally-stored padding width. More...
arma::cube	weight
	Locally-stored weight object. More...
OutputDataType	weights
	Locally-stored weight object. 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::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >

Implementation of the Convolution class.

The Convolution class represents a single layer of a neural network.

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).

Definition at line 46 of file convolution.hpp.

Constructor & Destructor Documentation

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

mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Convolution

(

)

Create the Convolution object.

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

mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Convolution	(	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
	)

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.
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.

Member Function Documentation

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

template<typename eT >

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::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.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::ConvOutSize ( const size_t  size, const size_t  k, const size_t  s, const size_t  p  )

inlineprivate

Definition at line 181 of file convolution.hpp.

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

OutputDataType const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Delta ( ) const

inline

Get the delta.

Definition at line 135 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::delta.

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

OutputDataType& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Delta ( )

inline

Modify the delta.

Definition at line 137 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::delta.

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

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.

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

template<typename eT >

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Gradient	(	const arma::Mat< eT > &&	,
		arma::Mat< eT > &&	error,
		arma::Mat< eT > &&	gradient
	)

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

OutputDataType const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Gradient ( ) const

inline

Get the gradient.

Definition at line 140 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::gradient.

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

OutputDataType& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Gradient ( )

inline

Modify the gradient.

Definition at line 142 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::gradient.

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

size_t const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputHeight ( ) const

inline

Get the input height.

Definition at line 150 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputHeight.

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

size_t& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputHeight ( )

inline

Modify the input height.

Definition at line 152 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputHeight.

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

InputDataType const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputParameter ( ) const

inline

Get the input parameter.

Definition at line 125 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputParameter.

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

InputDataType& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputParameter ( )

inline

Modify the input parameter.

Definition at line 127 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputParameter.

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

size_t const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputWidth ( ) const

inline

Get the input width.

Definition at line 145 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputWidth.

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

size_t& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputWidth ( )

inline

Modify input the width.

Definition at line 147 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputWidth.

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

size_t const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputHeight ( ) const

inline

Get the output height.

Definition at line 160 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputHeight.

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

size_t& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputHeight ( )

inline

Modify the output height.

Definition at line 162 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputHeight, and mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Serialize().

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

OutputDataType const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 130 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputParameter.

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

OutputDataType& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputParameter ( )

inline

Modify the output parameter.

Definition at line 132 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputParameter.

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

size_t const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputWidth ( ) const

inline

Get the output width.

Definition at line 155 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputWidth.

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

size_t& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputWidth ( )

inline

Modify the output width.

Definition at line 157 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputWidth.

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

template<typename eT >

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

inlineprivate

Definition at line 227 of file convolution.hpp.

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

template<typename eT >

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Pad ( const arma::Cube< eT > &  input, size_t  wPad, size_t  hPad, arma::Cube< eT > &  output  )

inlineprivate

Definition at line 251 of file convolution.hpp.

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

OutputDataType const& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Parameters ( ) const

inline

Get the parameters.

Definition at line 120 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::weights.

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

OutputDataType& mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Parameters ( )

inline

Modify the parameters.

Definition at line 122 of file convolution.hpp.

References mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::weights.

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

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Reset

(

)

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

template<typename eT >

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Rotate180 ( const arma::Cube< eT > &  input, arma::Cube< eT > &  output  )

inlineprivate

Definition at line 196 of file convolution.hpp.

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

template<typename eT >

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Rotate180 ( const arma::Mat< eT > &  input, arma::Mat< eT > &  output  )

inlineprivate

Definition at line 212 of file convolution.hpp.

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

template<typename Archive >

void mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Serialize	(	Archive &	ar,
		const unsigned	int
	)

Serialize the layer.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputHeight().

Member Data Documentation

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

arma::mat mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::bias

private

Locally-stored bias term object.

Definition at line 296 of file convolution.hpp.

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

OutputDataType mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::delta

private

Locally-stored delta object.

Definition at line 326 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Delta().

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::dH

private

Locally-stored stride of the filter in y-direction.

Definition at line 281 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::dW

private

Locally-stored stride of the filter in x-direction.

Definition at line 278 of file convolution.hpp.

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

OutputDataType mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::gradient

private

Locally-stored gradient object.

Definition at line 329 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Gradient().

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

arma::cube mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::gradientTemp

private

Locally-stored transformed gradient parameter.

Definition at line 323 of file convolution.hpp.

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

arma::cube mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::gTemp

private

Locally-stored transformed error parameter.

Definition at line 320 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputHeight

private

Locally-stored input height.

Definition at line 302 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputHeight().

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

arma::cube mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputPaddedTemp

private

Locally-stored transformed padded input parameter.

Definition at line 317 of file convolution.hpp.

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

InputDataType mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputParameter

private

Locally-stored input parameter object.

Definition at line 332 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputParameter().

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

arma::cube mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputTemp

private

Locally-stored transformed input parameter.

Definition at line 314 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inputWidth

private

Locally-stored input width.

Definition at line 299 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::InputWidth().

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::inSize

private

Locally-stored number of input units.

Definition at line 266 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::kH

private

Locally-stored filter/kernel height.

Definition at line 275 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::kW

private

Locally-stored filter/kernel width.

Definition at line 272 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputHeight

private

Locally-stored output height.

Definition at line 308 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputHeight().

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

OutputDataType mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputParameter

private

Locally-stored output parameter object.

Definition at line 335 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputParameter().

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

arma::cube mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputTemp

private

Locally-stored transformed output parameter.

Definition at line 311 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outputWidth

private

Locally-stored output width.

Definition at line 305 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::OutputWidth().

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::outSize

private

Locally-stored number of output units.

Definition at line 269 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::padH

private

Locally-stored padding height.

Definition at line 287 of file convolution.hpp.

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

size_t mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::padW

private

Locally-stored padding width.

Definition at line 284 of file convolution.hpp.

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

arma::cube mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::weight

private

Locally-stored weight object.

Definition at line 293 of file convolution.hpp.

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

OutputDataType mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::weights

private

Locally-stored weight object.

Definition at line 290 of file convolution.hpp.

Referenced by mlpack::ann::Convolution< ForwardConvolutionRule, BackwardConvolutionRule, GradientConvolutionRule, InputDataType, OutputDataType >::Parameters().

---

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

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