Implementation of the base layer. More...

Inheritance diagram for BaseLayer< ActivationFunction, MatType >:

Public Member Functions
	BaseLayer ()
	Create the BaseLayer object. More...

virtual	~BaseLayer ()

void	Backward (const MatType &input, const MatType &gy, MatType &g)
	Backward pass: compute the function f(x) by propagating x backwards through f, using the results from the forward pass. More...

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

void	Forward (const MatType &input, MatType &output)
	Forward pass: apply the activation to the inputs. More...

template < typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the 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	ComputeOutputDimensions ()
	Compute the output dimensions. 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
<
class
ActivationFunction
=
LogisticFunction
,
typename
MatType
=
arma::mat
>

class mlpack::ann::BaseLayer< ActivationFunction, MatType >

Implementation of the base layer.

The base layer works as a metaclass which attaches various functions to the embedding layer.

A few convenience typedefs are given:

Sigmoid
ReLU
TanH
Softplus
HardSigmoid
Swish
Mish
LiSHT
GELU
ELiSH
Elliot
Gaussian
HardSwish
TanhExp
SILU

Template Parameters

ActivationFunction Activation function used for the embedding layer.

Definition at line 66 of file base_layer.hpp.

Constructor & Destructor Documentation

◆ BaseLayer()

BaseLayer ( )

inline

Create the BaseLayer object.

Definition at line 72 of file base_layer.hpp.

Referenced by BaseLayer< ActivationFunction, MatType >::Clone().

◆ ~BaseLayer()

virtual ~BaseLayer ( )

inlinevirtual

Definition at line 78 of file base_layer.hpp.

Member Function Documentation

◆ Backward()

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

inlinevirtual

Backward pass: compute the function f(x) by propagating x backwards through f, using the results from the forward pass.

Parameters

input	The propagated input activation.
gy	The backpropagated error.
g	The calculated gradient.

Reimplemented from Layer< MatType >.

Definition at line 105 of file base_layer.hpp.

◆ Clone()

BaseLayer* Clone ( ) const

inlinevirtual

Clone the BaseLayer object. This handles polymorphism correctly.

Implements Layer< MatType >.

Definition at line 84 of file base_layer.hpp.

References BaseLayer< ActivationFunction, MatType >::BaseLayer().

◆ Forward()

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

inlinevirtual

Forward pass: apply the activation to the inputs.

Parameters

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

Reimplemented from Layer< MatType >.

Definition at line 92 of file base_layer.hpp.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

inline

Serialize the layer.

Definition at line 116 of file base_layer.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/base_layer.hpp

Public Member Functions

Additional Inherited Members

Detailed Description

template<classActivationFunction=LogisticFunction,typenameMatType=arma::mat> class mlpack::ann::BaseLayer< ActivationFunction, MatType >

Constructor & Destructor Documentation

◆ BaseLayer()

◆ ~BaseLayer()

Member Function Documentation

◆ Backward()

◆ Clone()

◆ Forward()

◆ serialize()

template
<
class
ActivationFunction
=
LogisticFunction
,
typename
MatType
=
arma::mat
>

class mlpack::ann::BaseLayer< ActivationFunction, MatType >