The RecurrentLayer provides a base layer for all layers that have recurrent functionality and store state between steps in a recurrent network. More...

Inheritance diagram for RecurrentLayer< MatType >:

[legend]

Public Member Functions
	RecurrentLayer ()
	Create the RecurrentLayer. More...

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

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

virtual	~RecurrentLayer ()

virtual void	ClearRecurrentState (const size_t bpttSteps, const size_t batchSize)=0
	ClearRecurrentState() is called before any forward pass of a recurrent network. More...

size_t	CurrentStep () const
	Get the current step index to use in a forward or backward pass. More...

size_t &	CurrentStep ()
	Modify the current step index to use in a forward or backward pass. More...

bool	HasPreviousStep () const
	If Forward() or Backward() has been called since ClearRecurrentState(), this will return true. More...

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

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

size_t	PreviousStep () const
	Get the previous step index, representing the value of CurrentStep() in the previous call to Forward() or Backward(). More...

size_t &	PreviousStep ()
	Modify the previous step index, representing the value of CurrentStep() in the previous call to Forward() or Backward(). More...

template < typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the recurrent layer. 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	Backward (const MatType &, const MatType &, MatType &)
	Performs a backpropagation step through the layer, with respect to the given input. More...

virtual Layer *	Clone () const =0
	Make a copy of the object. More...

virtual void	ComputeOutputDimensions ()
	Compute the output dimensions. More...

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

virtual void	Forward (const MatType &, MatType &)
	Takes an input object, and computes the corresponding output 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::RecurrentLayer< MatType >

The RecurrentLayer provides a base layer for all layers that have recurrent functionality and store state between steps in a recurrent network.

Any RecurrentLayer should only be used with a network type such as RNN that supports recurrent layers.

Any recurrent layer that inherits from RecurrentLayer must implement the ClearRecurrentState(bpttSteps, batchSize) function; this function should allocate space to store previous states with the given batch size. See the documentation for that function for more details.

Template Parameters

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

Definition at line 36 of file recurrent_layer.hpp.

Constructor & Destructor Documentation

◆ RecurrentLayer() [1/3]

RecurrentLayer ( )

Create the RecurrentLayer.

Referenced by RecurrentLayer< MatType >::~RecurrentLayer().

◆ ~RecurrentLayer()

virtual ~RecurrentLayer ( )

inlinevirtual

Definition at line 45 of file recurrent_layer.hpp.

References RecurrentLayer< MatType >::ClearRecurrentState(), RecurrentLayer< MatType >::operator=(), and RecurrentLayer< MatType >::RecurrentLayer().

◆ RecurrentLayer() [2/3]

RecurrentLayer ( const RecurrentLayer< MatType > & other )

Copy the given RecurrentLayer.

◆ RecurrentLayer() [3/3]

RecurrentLayer ( RecurrentLayer< MatType > && other )

Take ownership of the given RecurrentLayer.

Member Function Documentation

◆ ClearRecurrentState()

virtual void ClearRecurrentState	(	const size_t	bpttSteps,
		const size_t	batchSize
	)

pure virtual

ClearRecurrentState() is called before any forward pass of a recurrent network.

This function is responsible for allocating any memory necessary to store bpttSteps steps of previous forward and backward passes, with a batch size of batchSize.

Any internal state of the recurrent layer should be set to 0.

Implemented in LSTMType< MatType >.

Referenced by RecurrentLayer< MatType >::~RecurrentLayer().

◆ CurrentStep() [1/2]

size_t CurrentStep ( ) const

inline

Get the current step index to use in a forward or backward pass.

Definition at line 69 of file recurrent_layer.hpp.

◆ CurrentStep() [2/2]

size_t& CurrentStep ( )

inline

Modify the current step index to use in a forward or backward pass.

(Don't do this inside of your recurrent layer's implementation! This is meant to be done by the enclosing network.)

Definition at line 73 of file recurrent_layer.hpp.

◆ HasPreviousStep()

bool HasPreviousStep ( ) const

inline

If Forward() or Backward() has been called since ClearRecurrentState(), this will return true.

This should be used to determine if recurrent state should be considered in computations.

Definition at line 87 of file recurrent_layer.hpp.

References RecurrentLayer< MatType >::serialize().

◆ operator=() [1/2]

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

Copy the given RecurrentLayer.

Referenced by RecurrentLayer< MatType >::~RecurrentLayer().

◆ operator=() [2/2]

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

Take ownership of the given RecurrentLayer.

◆ PreviousStep() [1/2]

size_t PreviousStep ( ) const

inline

Get the previous step index, representing the value of CurrentStep() in the previous call to Forward() or Backward().

Definition at line 77 of file recurrent_layer.hpp.

◆ PreviousStep() [2/2]

size_t& PreviousStep ( )

inline

Modify the previous step index, representing the value of CurrentStep() in the previous call to Forward() or Backward().

(Don't modify this inside of your recurrent layer's implementation! This is meant to be done by the enclosing network.)

Definition at line 82 of file recurrent_layer.hpp.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the recurrent layer.

Referenced by RecurrentLayer< MatType >::HasPreviousStep().

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

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

Public Member Functions

Additional Inherited Members

Detailed Description

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

Constructor & Destructor Documentation

◆ RecurrentLayer() [1/3]

◆ ~RecurrentLayer()

◆ RecurrentLayer() [2/3]

◆ RecurrentLayer() [3/3]

Member Function Documentation

◆ ClearRecurrentState()

◆ CurrentStep() [1/2]

◆ CurrentStep() [2/2]

◆ HasPreviousStep()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ PreviousStep() [1/2]

◆ PreviousStep() [2/2]

◆ serialize()

template
<
typename
MatType
=
arma::mat
>

class mlpack::ann::RecurrentLayer< MatType >