Implementation of the AdaptiveMaxPooling layer. More...

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

	AdaptiveMaxPooling (const size_t outputWidth, const size_t outputHeight)
	Create the AdaptiveMaxPooling object. More...

	AdaptiveMaxPooling (const std::tuple< size_t, size_t > &outputShape)
	Create the AdaptiveMaxPooling object. More...

template < typename eT >
void	Backward (const arma::Mat< eT > &input, const arma::Mat< eT > &gy, arma::Mat< eT > &g)
	Ordinary feed backward pass of a neural network, using 3rd-order tensors as input, calculating the function f(x) by propagating x backwards through f. More...

const OutputDataType &	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...

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

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

size_t	InputSize () const
	Get the input size. More...

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

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

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

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

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

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

size_t	OutputSize () const
	Get the output size. More...

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

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

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

size_t	WeightSize () const
	Get the size of the weights. More...

Detailed Description

template
<
typename
InputDataType
=
arma::mat
,
typename
OutputDataType
=
arma::mat
>

class mlpack::ann::AdaptiveMaxPooling< InputDataType, OutputDataType >

Implementation of the AdaptiveMaxPooling layer.

Template Parameters

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 33 of file adaptive_max_pooling.hpp.

Constructor & Destructor Documentation

◆ AdaptiveMaxPooling() [1/3]

AdaptiveMaxPooling ( )

Create the AdaptiveMaxPooling object.

◆ AdaptiveMaxPooling() [2/3]

AdaptiveMaxPooling	(	const size_t	outputWidth,
		const size_t	outputHeight
	)

Create the AdaptiveMaxPooling object.

Parameters

outputWidth	Width of the output.
outputHeight	Height of the output.

◆ AdaptiveMaxPooling() [3/3]

AdaptiveMaxPooling ( const std::tuple< size_t, size_t > & outputShape )

Create the AdaptiveMaxPooling object.

Parameters

outputShape A two-value tuple indicating width and height of the output.

Member Function Documentation

◆ Backward()

void Backward	(	const arma::Mat< eT > &	input,
		const arma::Mat< eT > &	gy,
		arma::Mat< eT > &	g
	)

Ordinary feed backward pass of a neural network, using 3rd-order tensors as input, 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.

◆ Delta() [1/2]

const OutputDataType& Delta ( ) const

inline

Get the delta.

Definition at line 87 of file adaptive_max_pooling.hpp.

◆ Delta() [2/2]

OutputDataType& Delta ( )

inline

Modify the delta.

Definition at line 89 of file adaptive_max_pooling.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.

◆ InputHeight() [1/2]

size_t InputHeight ( ) const

inline

Get the input height.

Definition at line 97 of file adaptive_max_pooling.hpp.

◆ InputHeight() [2/2]

size_t& InputHeight ( )

inline

Modify the input height.

Definition at line 99 of file adaptive_max_pooling.hpp.

◆ InputSize()

size_t InputSize ( ) const

inline

Get the input size.

Definition at line 112 of file adaptive_max_pooling.hpp.

◆ InputWidth() [1/2]

size_t InputWidth ( ) const

inline

Get the input width.

Definition at line 92 of file adaptive_max_pooling.hpp.

◆ InputWidth() [2/2]

size_t& InputWidth ( )

inline

Modify the input width.

Definition at line 94 of file adaptive_max_pooling.hpp.

◆ OutputHeight() [1/2]

size_t OutputHeight ( ) const

inline

Get the output height.

Definition at line 107 of file adaptive_max_pooling.hpp.

◆ OutputHeight() [2/2]

size_t& OutputHeight ( )

inline

Modify the output height.

Definition at line 109 of file adaptive_max_pooling.hpp.

◆ OutputParameter() [1/2]

const OutputDataType& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 80 of file adaptive_max_pooling.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 84 of file adaptive_max_pooling.hpp.

◆ OutputSize()

size_t OutputSize ( ) const

inline

Get the output size.

Definition at line 115 of file adaptive_max_pooling.hpp.

◆ OutputWidth() [1/2]

size_t OutputWidth ( ) const

inline

Get the output width.

Definition at line 102 of file adaptive_max_pooling.hpp.

◆ OutputWidth() [2/2]

size_t& OutputWidth ( )

inline

Modify the output width.

Definition at line 104 of file adaptive_max_pooling.hpp.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t	version
	)

Serialize the layer.

Referenced by AdaptiveMaxPooling< InputDataType, OutputDataType >::WeightSize().

◆ WeightSize()

size_t WeightSize ( ) const

inline

Get the size of the weights.

Definition at line 118 of file adaptive_max_pooling.hpp.

References Log::Fatal, and AdaptiveMaxPooling< InputDataType, OutputDataType >::serialize().

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

/home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/adaptive_max_pooling.hpp

Public Member Functions

Detailed Description

template<typenameInputDataType=arma::mat,typenameOutputDataType=arma::mat> class mlpack::ann::AdaptiveMaxPooling< InputDataType, OutputDataType >

Constructor & Destructor Documentation

◆ AdaptiveMaxPooling() [1/3]

◆ AdaptiveMaxPooling() [2/3]

◆ AdaptiveMaxPooling() [3/3]

Member Function Documentation

◆ Backward()

◆ Delta() [1/2]

◆ Delta() [2/2]

◆ Forward()

◆ InputHeight() [1/2]

◆ InputHeight() [2/2]

◆ InputSize()

◆ InputWidth() [1/2]

◆ InputWidth() [2/2]

◆ OutputHeight() [1/2]

◆ OutputHeight() [2/2]

◆ OutputParameter() [1/2]

◆ OutputParameter() [2/2]

◆ OutputSize()

◆ OutputWidth() [1/2]

◆ OutputWidth() [2/2]

◆ serialize()

◆ WeightSize()

template
<
typename
InputDataType
=
arma::mat
,
typename
OutputDataType
=
arma::mat
>

class mlpack::ann::AdaptiveMaxPooling< InputDataType, OutputDataType >