Implementation of the log softmax layer. More...

Inheritance diagram for LogSoftMaxType< MatType >:

Public Member Functions
	LogSoftMaxType ()
	Create the LogSoftmax layer. More...

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

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

virtual	~LogSoftMaxType ()

void	Backward (const MatType &input, const MatType &gy, MatType &g)
	Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f. More...

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

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

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

template < typename Archive >
void	serialize (Archive &ar, const uint32_t)

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	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 &, 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::LogSoftMaxType< MatType >

Implementation of the log softmax layer.

The log softmax loss layer computes the multinomial logistic loss of the softmax of its inputs. This layer is meant to be used in combination with the negative log likelihood layer (NegativeLogLikelihoodLayer), which expects that the input contains log-probabilities for each class.

Template Parameters

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

Definition at line 33 of file log_softmax.hpp.

Constructor & Destructor Documentation

◆ LogSoftMaxType() [1/3]

LogSoftMaxType ( )

Create the LogSoftmax layer.

Referenced by LogSoftMaxType< MatType >::Clone(), and LogSoftMaxType< MatType >::~LogSoftMaxType().

◆ ~LogSoftMaxType()

virtual ~LogSoftMaxType ( )

inlinevirtual

Definition at line 45 of file log_softmax.hpp.

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

◆ LogSoftMaxType() [2/3]

LogSoftMaxType ( const LogSoftMaxType< MatType > & other )

Copy the given LogSoftMaxType.

◆ LogSoftMaxType() [3/3]

LogSoftMaxType ( LogSoftMaxType< MatType > && other )

Take ownership of the given LogSoftMaxType.

Member Function Documentation

◆ Backward()

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

virtual

Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough 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 >.

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

◆ Clone()

LogSoftMaxType* Clone ( ) const

inlinevirtual

Clone the LogSoftMaxType object. This handles polymorphism correctly.

Implements Layer< MatType >.

Definition at line 42 of file log_softmax.hpp.

References LogSoftMaxType< MatType >::LogSoftMaxType().

◆ 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 >.

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

◆ operator=() [1/2]

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

Copy the given LogSoftMaxType.

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

◆ operator=() [2/2]

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

Take ownership of the given LogSoftMaxType.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

inline

Definition at line 77 of file log_softmax.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/log_softmax.hpp

Public Member Functions

Additional Inherited Members

Detailed Description

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

Constructor & Destructor Documentation

◆ LogSoftMaxType() [1/3]

◆ ~LogSoftMaxType()

◆ LogSoftMaxType() [2/3]

◆ LogSoftMaxType() [3/3]

Member Function Documentation

◆ Backward()

◆ Clone()

◆ Forward()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ serialize()

template
<
typename
MatType
=
arma::mat
>

class mlpack::ann::LogSoftMaxType< MatType >