mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers > Class Template Reference

Implementation of the Concat class. More...

#include <concat.hpp>

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.
template<typename eT >
void	Forward (const 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	Backward (const arma::Mat< eT > &, const 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 > &, const 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...
template<typename eT >
void	Gradient (const arma::Mat< eT > &, const arma::Mat< eT > &error, arma::Mat< eT > &)
template<typename eT >
void	Gradient (const arma::Mat< eT > &input, const arma::Mat< eT > &error, arma::Mat< eT > &gradient, const size_t index)
template<class LayerType , class... Args>
void	Add (Args... args)
void	Add (LayerTypes< CustomLayers... > layer)
std::vector< LayerTypes< CustomLayers... > > &	Model ()
	Return the model modules.
const arma::mat &	Parameters () const
	Return the initial point for the optimization.
arma::mat &	Parameters ()
	Modify the initial point for the optimization.
bool	Run () const
	Get the value of run parameter.
bool &	Run ()
	Modify the value of run parameter.
arma::mat const &	InputParameter () const
arma::mat &	InputParameter ()
	Modify the input parameter.
arma::mat const &	OutputParameter () const
	Get the output parameter.
arma::mat &	OutputParameter ()
	Modify the output parameter.
arma::mat const &	Delta () const
	Get the delta.e.
arma::mat &	Delta ()
	Modify the delta.
arma::mat const &	Gradient () const
	Get the gradient.
arma::mat &	Gradient ()
	Modify the gradient.
size_t const &	ConcatAxis () const
	Get the axis of concatenation.
size_t	WeightSize () const
	Get the size of the weight matrix.
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

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.

Constructor & Destructor Documentation

Concat() [1/2]

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers >::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]

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers >::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.

Member Function Documentation

Backward() [1/2]

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

template<typename eT >

void mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers >::Backward	(	const arma::Mat< eT > &	,
		const 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]

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

template<typename eT >

void mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers >::Backward	(	const arma::Mat< eT > &	,
		const 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.
index	The index of the layer to run.

Forward()

template<typename InputDataType , typename OutputDataType , typename... CustomLayers>

template<typename eT >

void mlpack::ann::Concat< InputDataType, OutputDataType, CustomLayers >::Forward	(	const 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.

---

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

• src/mlpack/methods/ann/layer/concat.hpp
• src/mlpack/methods/ann/layer/concat_impl.hpp