Implementation of the MaxPooling layer. More...

Inheritance diagram for MaxPoolingType< MatType >:

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

	MaxPoolingType (const size_t kernelWidth, const size_t kernelHeight, const size_t strideWidth=1, const size_t strideHeight=1, const bool floor=true)
	Create the MaxPooling object using the specified number of units. More...

	MaxPoolingType (const MaxPoolingType &other)
	Copy the given MaxPoolingType. More...

	MaxPoolingType (MaxPoolingType &&other)
	Take ownership of the given MaxPoolingType. More...

virtual	~MaxPoolingType ()

void	Backward (const MatType &, const MatType &gy, MatType &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...

MaxPoolingType *	Clone () const
	Clone the MaxPoolingType object. This handles polymorphism correctly. More...

void	ComputeOutputDimensions ()
	Compute the size of the output given `InputDimensions()`. More...

bool const &	Floor () const
	Get the value of the rounding operation. More...

bool &	Floor ()
	Modify the value of the rounding operation. More...

void	Forward (const MatType &input, MatType &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 &	KernelHeight () const
	Get the kernel height. More...

size_t &	KernelHeight ()
	Modify the kernel height. More...

size_t const &	KernelWidth () const
	Get the kernel width. More...

size_t &	KernelWidth ()
	Modify the kernel width. More...

MaxPoolingType &	operator= (const MaxPoolingType &other)
	Copy the given MaxPoolingType. More...

MaxPoolingType &	operator= (MaxPoolingType &&other)
	Take ownership of the given MaxPoolingType. More...

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

size_t const &	StrideHeight () const
	Get the stride height. More...

size_t &	StrideHeight ()
	Modify the stride height. More...

size_t const &	StrideWidth () const
	Get the stride width. More...

size_t &	StrideWidth ()
	Modify the stride width. More...

Public Member Functions inherited from Layer< MatType >
	Layer ()
	Default constructor. More...

	Layer (const Layer &layer)
	Copy constructor. This is not responsible for copying weights! More...

	Layer (Layer &&layer)
	Move constructor. This is not responsible for moving weights! More...

virtual	~Layer ()
	Default deconstructor. More...

virtual void	CustomInitialize (MatType &, const size_t)
	Override the weight matrix of the layer. More...

virtual void	Forward (const MatType &, const MatType &)
	Takes an input and output object, and computes the corresponding loss of the layer. More...

virtual void	Gradient (const MatType &, const MatType &, MatType &)
	Computing the gradient of the layer with respect to its own input. More...

const std::vector< size_t > &	InputDimensions () const
	Get the input dimensions. More...

std::vector< size_t > &	InputDimensions ()
	Modify the input dimensions. More...

virtual double	Loss ()
	Get the layer loss. More...

virtual Layer &	operator= (const Layer &layer)
	Copy assignment operator. This is not responsible for copying weights! More...

virtual Layer &	operator= (Layer &&layer)
	Move assignment operator. This is not responsible for moving weights! More...

const std::vector< size_t > &	OutputDimensions ()
	Get the output dimensions. More...

virtual size_t	OutputSize () final
	Get the number of elements in the output from this layer. More...

virtual const MatType &	Parameters () const
	Get the parameters. More...

virtual MatType &	Parameters ()
	Set the parameters. More...

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

virtual void	SetWeights (typename MatType::elem_type *)
	Reset the layer parameter. More...

virtual bool const &	Training () const
	Get whether the layer is currently in training mode. More...

virtual bool &	Training ()
	Modify whether the layer is currently in training mode. More...

virtual size_t	WeightSize () const
	Get the total number of trainable weights in the layer. More...

Additional Inherited Members
Protected Attributes inherited from Layer< MatType >
std::vector< size_t >	inputDimensions
	Logical input dimensions of each point. More...

std::vector< size_t >	outputDimensions
	Logical output dimensions of each point. More...

bool	training
	If true, the layer is in training mode; otherwise, it is in testing mode. More...

bool	validOutputDimensions
	This is `true` if `ComputeOutputDimensions()` has been called, and `outputDimensions` can be considered to be up-to-date. More...

Detailed Description

template
<
typename
MatType
=
arma::mat
>

class mlpack::ann::MaxPoolingType< MatType >

Implementation of the MaxPooling layer.

Template Parameters

MatType Matrix representation to accept as input and use for computation.

Definition at line 61 of file max_pooling.hpp.

Constructor & Destructor Documentation

◆ MaxPoolingType() [1/4]

MaxPoolingType ( )

Create the MaxPooling object.

◆ MaxPoolingType() [2/4]

MaxPoolingType	(	const size_t	kernelWidth,
		const size_t	kernelHeight,
		const size_t	strideWidth = `1`,
		const size_t	strideHeight = `1`,
		const bool	floor = `true`
	)

Create the MaxPooling object using the specified number of units.

Parameters

kernelWidth	Width of the pooling window.
kernelHeight	Height of the pooling window.
strideWidth	Width of the stride operation.
strideHeight	Width of the stride operation.
floor	If true, then a pooling operation that would oly part of the input will be skipped.

◆ ~MaxPoolingType()

virtual ~MaxPoolingType ( )

inlinevirtual

Definition at line 84 of file max_pooling.hpp.

◆ MaxPoolingType() [3/4]

MaxPoolingType ( const MaxPoolingType< MatType > & other )

Copy the given MaxPoolingType.

◆ MaxPoolingType() [4/4]

MaxPoolingType ( MaxPoolingType< MatType > && other )

Take ownership of the given MaxPoolingType.

Member Function Documentation

◆ Backward()

void Backward	(	const MatType &	,
		const MatType &	gy,
		MatType &	g
	)

virtual

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.

Reimplemented from Layer< MatType >.

◆ Clone()

MaxPoolingType* Clone ( ) const

inlinevirtual

Clone the MaxPoolingType object. This handles polymorphism correctly.

Implements Layer< MatType >.

Definition at line 96 of file max_pooling.hpp.

◆ ComputeOutputDimensions()

void ComputeOutputDimensions ( )

virtual

Compute the size of the output given InputDimensions().

Reimplemented from Layer< MatType >.

◆ Floor() [1/2]

bool const& Floor ( ) const

inline

Get the value of the rounding operation.

Definition at line 141 of file max_pooling.hpp.

◆ Floor() [2/2]

bool& Floor ( )

inline

Modify the value of the rounding operation.

Definition at line 143 of file max_pooling.hpp.

◆ Forward()

void Forward	(	const MatType &	input,
		MatType &	output
	)

virtual

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.

Reimplemented from Layer< MatType >.

◆ KernelHeight() [1/2]

size_t const& KernelHeight ( ) const

inline

Get the kernel height.

Definition at line 126 of file max_pooling.hpp.

◆ KernelHeight() [2/2]

size_t& KernelHeight ( )

inline

Modify the kernel height.

Definition at line 128 of file max_pooling.hpp.

◆ KernelWidth() [1/2]

size_t const& KernelWidth ( ) const

inline

Get the kernel width.

Definition at line 121 of file max_pooling.hpp.

◆ KernelWidth() [2/2]

size_t& KernelWidth ( )

inline

Modify the kernel width.

Definition at line 123 of file max_pooling.hpp.

◆ operator=() [1/2]

MaxPoolingType& operator= ( const MaxPoolingType< MatType > & other )

Copy the given MaxPoolingType.

◆ operator=() [2/2]

MaxPoolingType& operator= ( MaxPoolingType< MatType > && other )

Take ownership of the given MaxPoolingType.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the layer.

◆ StrideHeight() [1/2]

size_t const& StrideHeight ( ) const

inline

Get the stride height.

Definition at line 136 of file max_pooling.hpp.

◆ StrideHeight() [2/2]

size_t& StrideHeight ( )

inline

Modify the stride height.

Definition at line 138 of file max_pooling.hpp.

◆ StrideWidth() [1/2]

size_t const& StrideWidth ( ) const

inline

Get the stride width.

Definition at line 131 of file max_pooling.hpp.

◆ StrideWidth() [2/2]

size_t& StrideWidth ( )

inline

Modify the stride width.

Definition at line 133 of file max_pooling.hpp.

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

/home/jenkins-mlpack/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/layer/max_pooling.hpp

Public Member Functions

Additional Inherited Members

Detailed Description

template<typenameMatType=arma::mat> class mlpack::ann::MaxPoolingType< MatType >

Constructor & Destructor Documentation

◆ MaxPoolingType() [1/4]

◆ MaxPoolingType() [2/4]

◆ ~MaxPoolingType()

◆ MaxPoolingType() [3/4]

◆ MaxPoolingType() [4/4]

Member Function Documentation

◆ Backward()

◆ Clone()

◆ ComputeOutputDimensions()

◆ Floor() [1/2]

◆ Floor() [2/2]

◆ Forward()

◆ KernelHeight() [1/2]

◆ KernelHeight() [2/2]

◆ KernelWidth() [1/2]

◆ KernelWidth() [2/2]

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ serialize()

◆ StrideHeight() [1/2]

◆ StrideHeight() [2/2]

◆ StrideWidth() [1/2]

◆ StrideWidth() [2/2]

template
<
typename
MatType
=
arma::mat
>

class mlpack::ann::MaxPoolingType< MatType >