Implementation of the Concat class. More...

Public Member Functions
	Concat (const bool model=false, const bool run=true)
	Create the Concat object using the specified parameters. More...

	Concat (arma::Row< size_t > &inputSize, const size_t axis, const bool model=false, const bool run=true)
	Create the Concat object using the specified parameters. More...

	~Concat ()
	Destroy the layers held by the model. More...

template < typename LayerType >
void	Add (const LayerType &layer)

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

void	Add (LayerTypes< CustomLayers... > layer)

template < typename eT >
void	Backward (const arma::Mat< eT > &&, arma::Mat< eT > &&gy, arma::Mat< eT > &&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...

template < typename eT >
void	Backward (const arma::Mat< eT > &&, arma::Mat< eT > &&gy, arma::Mat< eT > &&g, const size_t index)
	This is the overload of Backward() that runs only a specific layer with the given input. More...

arma::mat const &	Delta () const
	Get the delta.e. More...

arma::mat &	Delta ()
	Modify the delta. More...

template < typename eT >
void	Forward (arma::Mat< eT > &&input, arma::Mat< eT > &&output)
	Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...

template < typename eT >
void	Gradient (arma::Mat< eT > &&, arma::Mat< eT > &&error, arma::Mat< eT > &&)

template < typename eT >
void	Gradient (arma::Mat< eT > &&input, arma::Mat< eT > &&error, arma::Mat< eT > &&gradient, const size_t index)

arma::mat const &	Gradient () const
	Get the gradient. More...

arma::mat &	Gradient ()
	Modify the gradient. More...

arma::mat const &	InputParameter () const

arma::mat &	InputParameter ()
	Modify the input parameter. More...

std::vector< LayerTypes< CustomLayers... > > &	Model ()
	Return the model modules. More...

arma::mat const &	OutputParameter () const
	Get the output parameter. More...

arma::mat &	OutputParameter ()
	Modify the output parameter. More...

const arma::mat &	Parameters () const
	Return the initial point for the optimization. More...

arma::mat &	Parameters ()
	Modify the initial point for the optimization. More...

bool	Run () const
	Get the value of run parameter. More...

bool &	Run ()
	Modify the value of run parameter. More...

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

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat, typename... CustomLayers>
class mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers >

Implementation of the Concat class.

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

Template Parameters

InputDataType	Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataType	Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
CustomLayers	Additional custom layers if required.

Definition at line 45 of file concat.hpp.

Constructor & Destructor Documentation

◆ Concat() [1/2]

Concat	(	const bool	model = `false`,
		const bool	run = `true`
	)

Create the Concat object using the specified parameters.

Parameters

model	Expose all network modules.
run	Call the Forward/Backward method before the output is merged.

◆ Concat() [2/2]

Concat	(	arma::Row< size_t > &	inputSize,
		const size_t	axis,
		const bool	model = `false`,
		const bool	run = `true`
	)

Create the Concat object using the specified parameters.

Parameters

inputSize	A vector denoting input size of each layer added.
axis	Concat axis.
model	Expose all network modules.
run	Call the Forward/Backward method before the output is merged.

◆ ~Concat()

~Concat ( )

Destroy the layers held by the model.

Member Function Documentation

◆ Add() [1/3]

void Add ( const LayerType & layer )

inline

Definition at line 147 of file concat.hpp.

◆ Add() [2/3]

void Add ( Args... args )

inline

Definition at line 155 of file concat.hpp.

◆ Add() [3/3]

void Add ( LayerTypes< CustomLayers... > layer )

inline

Definition at line 162 of file concat.hpp.

◆ Backward() [1/2]

void Backward	(	const arma::Mat< eT > &&	,
		arma::Mat< eT > &&	gy,
		arma::Mat< eT > &&	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.

Using the results from the feed forward pass.

Parameters

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

◆ Backward() [2/2]

void Backward	(	const arma::Mat< eT > &&	,
		arma::Mat< eT > &&	gy,
		arma::Mat< eT > &&	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.
The	index of the layer to run.

◆ Delta() [1/2]

arma::mat const& Delta ( ) const

inline

Get the delta.e.

Definition at line 195 of file concat.hpp.

◆ Delta() [2/2]

arma::mat& Delta ( )

inline

Modify the delta.

Definition at line 197 of file concat.hpp.

◆ Forward()

void Forward	(	arma::Mat< eT > &&	input,
		arma::Mat< eT > &&	output
	)

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.

◆ Gradient() [1/4]

void Gradient	(	arma::Mat< eT > &&	,
		arma::Mat< eT > &&	error,
		arma::Mat< eT > &&
	)

◆ Gradient() [2/4]

void Gradient	(	arma::Mat< eT > &&	input,
		arma::Mat< eT > &&	error,
		arma::Mat< eT > &&	gradient,
		const size_t	index
	)

◆ Gradient() [3/4]

arma::mat const& Gradient ( ) const

inline

Get the gradient.

Definition at line 200 of file concat.hpp.

◆ Gradient() [4/4]

arma::mat& Gradient ( )

inline

Modify the gradient.

Definition at line 202 of file concat.hpp.

References Concat< InputDataType, OutputDataType, CustomLayers >::serialize().

◆ InputParameter() [1/2]

arma::mat const& InputParameter ( ) const

inline

Definition at line 185 of file concat.hpp.

◆ InputParameter() [2/2]

arma::mat& InputParameter ( )

inline

Modify the input parameter.

Definition at line 187 of file concat.hpp.

◆ Model()

std::vector<LayerTypes<CustomLayers...> >& Model ( )

inline

Return the model modules.

Definition at line 165 of file concat.hpp.

◆ OutputParameter() [1/2]

arma::mat const& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 190 of file concat.hpp.

◆ OutputParameter() [2/2]

arma::mat& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 192 of file concat.hpp.

◆ Parameters() [1/2]

const arma::mat& Parameters ( ) const

inline

Return the initial point for the optimization.

Definition at line 176 of file concat.hpp.

◆ Parameters() [2/2]

arma::mat& Parameters ( )

inline

Modify the initial point for the optimization.

Definition at line 178 of file concat.hpp.

◆ Run() [1/2]

bool Run ( ) const

inline

Get the value of run parameter.

Definition at line 181 of file concat.hpp.

◆ Run() [2/2]

bool& Run ( )

inline

Modify the value of run parameter.

Definition at line 183 of file concat.hpp.

◆ serialize()

void serialize	(	Archive &	,
		const unsigned	int
	)

Serialize the layer.

Referenced by Concat< InputDataType, OutputDataType, CustomLayers >::Gradient().

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

/home/jenkins-mlpack/mlpack.org/_src/mlpack-3.2.1/src/mlpack/methods/ann/layer/concat.hpp

Public Member Functions

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat, typename... CustomLayers> class mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers >

Constructor & Destructor Documentation

◆ Concat() [1/2]

◆ Concat() [2/2]

◆ ~Concat()

Member Function Documentation

◆ Add() [1/3]

◆ Add() [2/3]

◆ Add() [3/3]

◆ Backward() [1/2]

◆ Backward() [2/2]

◆ Delta() [1/2]

◆ Delta() [2/2]

◆ Forward()

◆ Gradient() [1/4]

◆ Gradient() [2/4]

◆ Gradient() [3/4]

◆ Gradient() [4/4]

◆ InputParameter() [1/2]

◆ InputParameter() [2/2]

◆ Model()

◆ OutputParameter() [1/2]

◆ OutputParameter() [2/2]

◆ Parameters() [1/2]

◆ Parameters() [2/2]

◆ Run() [1/2]

◆ Run() [2/2]

◆ serialize()

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat, typename... CustomLayers>
class mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers >