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

Implementation of the Sequential class. More...

#include <sequential.hpp>

Public Member Functions
	Sequential (const bool model=true)
	Create the Sequential object using the specified parameters. More...
	Sequential (const bool model, const bool ownsLayers)
	Create the Sequential object using the specified parameters. More...
	Sequential (const Sequential &layer)
	Copy constructor.
Sequential &	operator= (const Sequential &layer)
	Copy assignment operator.
	~Sequential ()
	Destroy the Sequential object.
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	Gradient (const arma::Mat< eT > &input, const arma::Mat< eT > &error, arma::Mat< eT > &)
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.
arma::mat const &	InputParameter () const
	Get the input parameter.
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.
arma::mat &	Delta ()
	Modify the delta.
arma::mat const &	Gradient () const
	Get the gradient.
arma::mat &	Gradient ()
	Modify the gradient.
size_t	InputShape () const
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat, bool Residual = false, typename... CustomLayers>
class mlpack::ann::Sequential< InputDataType, OutputDataType, Residual, CustomLayers >

Implementation of the Sequential class.

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

This class can also be used as a container for a residual block. In that case, the sizes of the input and output matrices of this class should be equal. A typedef has been added for use as a Residual<> class.

For more information, refer the following paper.

@article{He15,
  author    = {Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun},
  title     = {Deep Residual Learning for Image Recognition},
  year      = {2015},
  url       = {https://arxiv.org/abs/1512.03385},
  eprint    = {1512.03385},
}

Note: If this class is used as the first layer of a network, it should be preceded by IdentityLayer<>.

Note: This class should at least have two layers for a call to its Gradient() function.

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).
Residual	If true, use the object as a Residual block.

Constructor & Destructor Documentation

Sequential() [1/2]

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

mlpack::ann::Sequential< InputDataType, OutputDataType, Residual, CustomLayers >::Sequential

(

const bool

model = true

)

Create the Sequential object using the specified parameters.

Parameters

model

Expose the all network modules.

Sequential() [2/2]

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

mlpack::ann::Sequential< InputDataType, OutputDataType, Residual, CustomLayers >::Sequential	(	const bool	model,
		const bool	ownsLayers
	)

Create the Sequential object using the specified parameters.

Parameters

model	Expose all the network modules.
ownsLayers	If true, then this module will delete its layers when deallocated.

Member Function Documentation

Backward()

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

template<typename eT >

void mlpack::ann::Sequential< InputDataType, OutputDataType, Residual, 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.

Forward()

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

template<typename eT >

void mlpack::ann::Sequential< InputDataType, OutputDataType, Residual, 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/layer_types.hpp
• src/mlpack/methods/ann/layer/sequential.hpp
• src/mlpack/methods/ann/layer/sequential_impl.hpp