Implementation of the Concat class. More...

Inheritance diagram for ConcatType< MatType >:

Public Member Functions
	ConcatType ()
	Create the Concat object. More...

	ConcatType (const size_t axis)
	Create the Concat object, specifying a particular axis on which the layer outputs should be concatenated. More...

	ConcatType (const ConcatType &other)
	Copy the given ConcatType layer. More...

	ConcatType (ConcatType &&other)
	Take ownership of the given ConcatType layer. More...

virtual	~ConcatType ()
	Destroy the layers held by the model. More...

size_t	Axis () const
	Get the axis of concatenation. More...

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...

void	Backward (const MatType &, const MatType &gy, MatType &g, const size_t index)
	This is the overload of Backward() that runs only a specific layer with the given input. More...

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

void	ComputeOutputDimensions ()
	Compute the output dimensions of the MultiLayer using `InputDimensions()`. 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...

void	Gradient (const MatType &, const MatType &error, MatType &)
	Calculate the gradient using the output delta and the input activation. More...

void	Gradient (const MatType &input, const MatType &error, MatType &gradient, const size_t index)
	This is the overload of Gradient() that runs a specific layer with the given input. More...

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

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

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

Public Member Functions inherited from MultiLayer< MatType >
	MultiLayer ()
	Create an empty MultiLayer that holds no layers of its own. More...

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

	MultiLayer (MultiLayer &&other)
	Take ownership of the layers of the given MultiLayer. More...

virtual	~MultiLayer ()
	Virtual destructor: delete all held layers. More...

template<typename LayerType , typename... Args>
void	Add (Args... args)

void	Add (Layer< MatType > *layer)

void	Forward (const MatType &input, MatType &output, const size_t start, const size_t end)
	Perform a forward pass with the given input data, but only on a subset of the layers in the MultiLayer. More...

virtual double	Loss () const
	Compute the loss that should be added to the objective. More...

const std::vector< Layer< MatType > * >	Network () const
	Get the network (series of layers) held by this MultiLayer. More...

std::vector< Layer< MatType > * > &	Network ()
	Modify the network (series of layers) held by this MultiLayer. More...

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

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

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

virtual void	SetWeights (typename MatType::elem_type *weightsPtr)
	Set the weights of the layer to use the memory given as `weightsPtr`. More...

virtual size_t	WeightSize () const
	Return the number of weights in the MultiLayer. 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	Forward (const MatType &, const MatType &)
	Takes an input and output object, and computes the corresponding loss of the layer. 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 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...

Additional Inherited Members
Protected Member Functions inherited from MultiLayer< MatType >
void	InitializeBackwardPassMemory (const size_t batchSize)
	Initialize memory that will be used by each layer for the backwards pass, assuming that the input will have the given `batchSize`. More...

void	InitializeForwardPassMemory (const size_t batchSize)
	Initialize memory that will be used by each layer for the forward pass, assuming that the input will have the given `batchSize`. More...

void	InitializeGradientPassMemory (MatType &gradient)
	Initialize memory for the gradient pass. More...

Protected Attributes inherited from MultiLayer< MatType >
size_t	inSize

MatType	layerDeltaMatrix
	This matrix stores all of the backwards pass results of each layer when Backward() is called. More...

std::vector< MatType >	layerDeltas
	These are aliases of `layerDeltaMatrix` for each layer. More...

std::vector< MatType >	layerGradients
	Gradient aliases for each layer. More...

MatType	layerOutputMatrix
	This matrix stores all of the outputs of each layer when Forward() is called. More...

std::vector< MatType >	layerOutputs
	These are aliases of `layerOutputMatrix` for each layer. More...

std::vector< Layer< MatType > * >	network
	The internally-held network. More...

size_t	totalInputSize

size_t	totalOutputSize

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::ConcatType< MatType >

Implementation of the Concat class.

The Concat class works as a feed-forward fully connected network container which plugs various layers together.

NOTE: this class is not intended to exist for long! It will be replaced with a more flexible DAG network type.

Template Parameters

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

Definition at line 35 of file concat.hpp.

Constructor & Destructor Documentation

◆ ConcatType() [1/4]

ConcatType ( )

Create the Concat object.

The axis used for concatenation will be the last one.

Referenced by ConcatType< MatType >::Clone().

◆ ConcatType() [2/4]

ConcatType ( const size_t axis )

Create the Concat object, specifying a particular axis on which the layer outputs should be concatenated.

Parameters

axis	Concat axis.

◆ ~ConcatType()

virtual ~ConcatType ( )

virtual

Destroy the layers held by the model.

◆ ConcatType() [3/4]

ConcatType ( const ConcatType< MatType > & other )

Copy the given ConcatType layer.

◆ ConcatType() [4/4]

ConcatType ( ConcatType< MatType > && other )

Take ownership of the given ConcatType layer.

Member Function Documentation

◆ Axis()

size_t Axis ( ) const

inline

Get the axis of concatenation.

Definition at line 131 of file concat.hpp.

◆ Backward() [1/2]

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 MultiLayer< MatType >.

Referenced by ConcatType< MatType >::Clone().

◆ Backward() [2/2]

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

This is the overload of Backward() that runs only a specific layer with the given input.

Parameters

*	(input) The propagated input activation.
gy	The backpropagated error.
g	The calculated gradient.
index	The index of the layer to run.

◆ Clone()

ConcatType* Clone ( ) const

inlinevirtual

Clone the ConcatType object. This handles polymorphism correctly.

Reimplemented from MultiLayer< MatType >.

Definition at line 58 of file concat.hpp.

References ConcatType< MatType >::Backward(), ConcatType< MatType >::ConcatType(), ConcatType< MatType >::Forward(), ConcatType< MatType >::Gradient(), and ConcatType< MatType >::operator=().

◆ ComputeOutputDimensions()

void ComputeOutputDimensions ( )

inlinevirtual

Compute the output dimensions of the MultiLayer using InputDimensions().

This computes the dimensions of each layer held by the MultiLayer, and the output dimensions are set to the output dimensions of the last layer.

Reimplemented from MultiLayer< MatType >.

Definition at line 136 of file concat.hpp.

References Layer< MatType >::inputDimensions, MultiLayer< MatType >::network, Layer< MatType >::OutputDimensions(), Layer< MatType >::outputDimensions, ConcatType< MatType >::serialize(), MultiLayer< MatType >::totalInputSize, and MultiLayer< MatType >::totalOutputSize.

◆ 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 MultiLayer< MatType >.

Referenced by ConcatType< MatType >::Clone().

◆ Gradient() [1/2]

void Gradient	(	const MatType &	,
		const MatType &	error,
		MatType &
	)

virtual

Calculate the gradient using the output delta and the input activation.

Parameters

input	The input parameter used for calculating the gradient.
error	The calculated error.
gradient	The calculated gradient.

Reimplemented from MultiLayer< MatType >.

Referenced by ConcatType< MatType >::Clone().

◆ Gradient() [2/2]

void Gradient	(	const MatType &	input,
		const MatType &	error,
		MatType &	gradient,
		const size_t	index
	)

This is the overload of Gradient() that runs a specific layer with the given input.

Parameters

input	The input parameter used for calculating the gradient.
error	The calculated error.
gradient	The calculated gradient.
The	index of the layer to run.

◆ operator=() [1/2]

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

Copy the given ConcatType layer.

Referenced by ConcatType< MatType >::Clone().

◆ operator=() [2/2]

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

Take ownership of the given ConcatType layer.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the layer.

Referenced by ConcatType< MatType >::ComputeOutputDimensions().

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

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

Public Member Functions

Additional Inherited Members

Detailed Description

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

Constructor & Destructor Documentation

◆ ConcatType() [1/4]

◆ ConcatType() [2/4]

◆ ~ConcatType()

◆ ConcatType() [3/4]

◆ ConcatType() [4/4]

Member Function Documentation

◆ Axis()

◆ Backward() [1/2]

◆ Backward() [2/2]

◆ Clone()

◆ ComputeOutputDimensions()

◆ Forward()

◆ Gradient() [1/2]

◆ Gradient() [2/2]

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ serialize()

template
<
typename
MatType
=
arma::mat
>

class mlpack::ann::ConcatType< MatType >