Implementation of the MaxPooling layer. More...

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

	MaxPooling (const size_t kW, const size_t kH, const size_t dW=1, const size_t dH=1, const bool floor=true)
	Create the MaxPooling object using the specified number of units. 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, using 3rd-order tensors as input, 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...

bool	Deterministic () const
	Get the value of the deterministic parameter. More...

bool &	Deterministic ()
	Modify the value of the deterministic parameter. 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 const &	InputHeight () const
	Get the height. More...

size_t &	InputHeight ()
	Modify the 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 width. More...

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

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

size_t &	OutputHeight ()
	Modify the 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 width. More...

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

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

Detailed Description

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

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

Implementation of the MaxPooling 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 52 of file max_pooling.hpp.

Constructor & Destructor Documentation

◆ MaxPooling() [1/2]

MaxPooling ( )

Create the MaxPooling object.

◆ MaxPooling() [2/2]

MaxPooling	(	const size_t	kW,
		const size_t	kH,
		const size_t	dW = `1`,
		const size_t	dH = `1`,
		const bool	floor = `true`
	)

Create the MaxPooling object using the specified number of units.

Parameters

kW	Width of the pooling window.
kH	Height of the pooling window.
dW	Width of the stride operation.
dH	Width of the stride operation.
floor	Rounding operator (floor or ceil).

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, 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]

OutputDataType const& Delta ( ) const

inline

Get the delta.

Definition at line 108 of file max_pooling.hpp.

◆ Delta() [2/2]

OutputDataType& Delta ( )

inline

Modify the delta.

Definition at line 110 of file max_pooling.hpp.

◆ Deterministic() [1/2]

bool Deterministic ( ) const

inline

Get the value of the deterministic parameter.

Definition at line 133 of file max_pooling.hpp.

◆ Deterministic() [2/2]

bool& Deterministic ( )

inline

Modify the value of the deterministic parameter.

Definition at line 135 of file 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 const& InputHeight ( ) const

inline

Get the height.

Definition at line 118 of file max_pooling.hpp.

◆ InputHeight() [2/2]

size_t& InputHeight ( )

inline

Modify the height.

Definition at line 120 of file max_pooling.hpp.

◆ InputParameter() [1/2]

InputDataType const& InputParameter ( ) const

inline

Get the input parameter.

Definition at line 98 of file max_pooling.hpp.

◆ InputParameter() [2/2]

InputDataType& InputParameter ( )

inline

Modify the input parameter.

Definition at line 100 of file max_pooling.hpp.

◆ InputWidth() [1/2]

size_t const& InputWidth ( ) const

inline

Get the width.

Definition at line 113 of file max_pooling.hpp.

◆ InputWidth() [2/2]

size_t& InputWidth ( )

inline

Modify the width.

Definition at line 115 of file max_pooling.hpp.

◆ OutputHeight() [1/2]

size_t const& OutputHeight ( ) const

inline

Get the height.

Definition at line 128 of file max_pooling.hpp.

◆ OutputHeight() [2/2]

size_t& OutputHeight ( )

inline

Modify the height.

Definition at line 130 of file max_pooling.hpp.

◆ OutputParameter() [1/2]

OutputDataType const& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 103 of file max_pooling.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 105 of file max_pooling.hpp.

◆ OutputWidth() [1/2]

size_t const& OutputWidth ( ) const

inline

Get the width.

Definition at line 123 of file max_pooling.hpp.

◆ OutputWidth() [2/2]

size_t& OutputWidth ( )

inline

Modify the width.

Definition at line 125 of file max_pooling.hpp.

◆ serialize()

void serialize	(	Archive &	ar,
		const unsigned	int
	)

Serialize the layer.

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

src/mlpack/methods/ann/layer/max_pooling.hpp

Public Member Functions

Detailed Description

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

Constructor & Destructor Documentation

◆ MaxPooling() [1/2]

◆ MaxPooling() [2/2]

Member Function Documentation

◆ Backward()

◆ Delta() [1/2]

◆ Delta() [2/2]

◆ Deterministic() [1/2]

◆ Deterministic() [2/2]

◆ Forward()

◆ InputHeight() [1/2]

◆ InputHeight() [2/2]

◆ InputParameter() [1/2]

◆ InputParameter() [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]

◆ serialize()

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

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