Implementation of the constant layer. More...

Inheritance diagram for ConstantType< InputType, OutputType >:

Public Member Functions
	ConstantType ()
	Create an empty Constant layer. More...

	ConstantType (const size_t outSize, const double scalar=0)
	Create the Constant object that outputs a given constant scalar value given any input value. More...

	ConstantType (const ConstantType &layer)
	Copy another ConstantType. More...

	ConstantType (ConstantType &&layer)
	Take ownership of another ConstantType. More...

void	Backward (const InputType &, const OutputType &, OutputType &g)
	Ordinary feed backward pass of a neural network. More...

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

void	Forward (const InputType &input, OutputType &output)
	Ordinary feed forward pass of a neural network. More...

ConstantType &	operator= (const ConstantType &layer)
	Copy another ConstantType. More...

ConstantType &	operator= (ConstantType &&layer)
	Take ownership of another ConstantType. More...

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

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

Public Member Functions inherited from Layer< InputType, OutputType >
	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 InputType &, const InputType &, InputType &)
	Performs a backpropagation step through the layer, with respect to the given input. More...

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

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

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

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

virtual void	Gradient (const InputType &, const InputType &, InputType &)
	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 InputType &	Parameters () const
	Get the parameters. More...

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

void	serialize (Archive &ar, const uint32_t)
	Serialize the layer. More...

virtual void	SetWeights (typename InputType ::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< InputType, OutputType >
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
InputType
=
arma::mat
,
typename
OutputType
=
arma::mat
>

class mlpack::ann::ConstantType< InputType, OutputType >

Implementation of the constant layer.

The constant layer outputs a given constant value given any input value.

Template Parameters

InputType	The type of the layer's inputs. The layer automatically cast inputs to this type (Default: arma::mat).
OutputType	The type of the computation which also causes the output to also be in this type. The type also allows the computation and weight type to differ from the input type (Default: arma::mat).

Definition at line 34 of file constant.hpp.

Constructor & Destructor Documentation

◆ ConstantType() [1/4]

ConstantType ( )

Create an empty Constant layer.

Referenced by ConstantType< InputType, OutputType >::Clone().

◆ ConstantType() [2/4]

ConstantType	(	const size_t	outSize,
		const double	scalar = `0`
	)

Create the Constant object that outputs a given constant scalar value given any input value.

Parameters

outSize	The number of output units.
scalar	The constant value used to create the constant output.

◆ ConstantType() [3/4]

ConstantType ( const ConstantType< InputType, OutputType > & layer )

Copy another ConstantType.

◆ ConstantType() [4/4]

ConstantType ( ConstantType< InputType, OutputType > && layer )

Take ownership of another ConstantType.

Member Function Documentation

◆ Backward()

void Backward	(	const InputType &	,
		const OutputType &	,
		OutputType &	g
	)

Ordinary feed backward pass of a neural network.

The backward pass of the constant layer is returns always a zero output error matrix.

Parameters

*	(input) The propagated input activation.
*	(gy) The backpropagated error.
g	The calculated gradient.

Referenced by ConstantType< InputType, OutputType >::Clone().

◆ Clone()

ConstantType* Clone ( ) const

inlinevirtual

Clone the ConstantType object. This handles polymorphism correctly.

Implements Layer< InputType, OutputType >.

Definition at line 61 of file constant.hpp.

References ConstantType< InputType, OutputType >::Backward(), ConstantType< InputType, OutputType >::ConstantType(), and ConstantType< InputType, OutputType >::Forward().

◆ Forward()

void Forward	(	const InputType &	input,
		OutputType &	output
	)

Ordinary feed forward pass of a neural network.

The forward pass fills the output with the specified constant parameter.

Parameters

input	Input data used for evaluating the specified function.
output	Resulting output activation.

Referenced by ConstantType< InputType, OutputType >::Clone().

◆ operator=() [1/2]

ConstantType& operator= ( const ConstantType< InputType, OutputType > & layer )

Copy another ConstantType.

◆ operator=() [2/2]

ConstantType& operator= ( ConstantType< InputType, OutputType > && layer )

Take ownership of another ConstantType.

◆ OutputDimensions()

const std::vector<size_t>& OutputDimensions ( ) const

inline

Get the output size.

Definition at line 85 of file constant.hpp.

References Layer< InputType, OutputType >::inputDimensions, and ConstantType< InputType, OutputType >::serialize().

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the layer.

Referenced by ConstantType< InputType, OutputType >::OutputDimensions().

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

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

Public Member Functions

Additional Inherited Members

Detailed Description

template<typenameInputType=arma::mat,typenameOutputType=arma::mat> class mlpack::ann::ConstantType< InputType, OutputType >

Constructor & Destructor Documentation

◆ ConstantType() [1/4]

◆ ConstantType() [2/4]

◆ ConstantType() [3/4]

◆ ConstantType() [4/4]

Member Function Documentation

◆ Backward()

◆ Clone()

◆ Forward()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ OutputDimensions()

◆ serialize()

template
<
typename
InputType
=
arma::mat
,
typename
OutputType
=
arma::mat
>

class mlpack::ann::ConstantType< InputType, OutputType >