mlpack 3.4.2
Public Member Functions | List of all members
Sequential< InputDataType, OutputDataType, Residual, CustomLayers > Class Template Reference

Implementation of the Sequential class. More...

#include <sequential.hpp>

Inheritance diagram for Sequential< InputDataType, OutputDataType, Residual, CustomLayers >:
Inheritance graph
[legend]

Public Member Functions

 Sequential (const bool model, const bool ownsLayers)
 Create the Sequential object using the specified parameters. More...
 
 Sequential (const bool model=true)
 Create the Sequential object using the specified parameters. More...
 
 Sequential (const Sequential &layer)
 Copy constructor. More...
 
 ~Sequential ()
 Destroy the Sequential object. More...
 
template<class LayerType , class... Args>
void Add (Args... args)
 
void Add (LayerTypes< CustomLayers... > layer)
 
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...
 
arma::mat & Delta ()
 Modify the delta. More...
 
arma::mat const & Delta () const
 Get the delta. More...
 
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...
 
arma::mat & Gradient ()
 Modify the gradient. More...
 
arma::mat const & Gradient () const
 Get the gradient. More...
 
template<typename eT >
void Gradient (const arma::Mat< eT > &input, const arma::Mat< eT > &error, arma::Mat< eT > &)
 
arma::mat & InputParameter ()
 Modify the input parameter. More...
 
arma::mat const & InputParameter () const
 Get the input parameter. More...
 
std::vector< LayerTypes< CustomLayers... > > & Model ()
 Return the model modules. More...
 
Sequentialoperator= (const Sequential &layer)
 Copy assignment operator. More...
 
arma::mat & OutputParameter ()
 Modify the output parameter. More...
 
arma::mat const & OutputParameter () const
 Get the output parameter. More...
 
arma::mat & Parameters ()
 Modify the initial point for the optimization. More...
 
const arma::mat & Parameters () const
 Return the initial point for the optimization. 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, 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},
}
Sequential< InputDataType, OutputDataType, true, CustomLayers... > Residual
Definition: sequential.hpp:258

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
InputDataTypeType of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
OutputDataTypeType of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
ResidualIf true, use the object as a Residual block.

Definition at line 72 of file sequential.hpp.

Constructor & Destructor Documentation

◆ Sequential() [1/3]

Sequential ( const bool  model = true)

Create the Sequential object using the specified parameters.

Parameters
modelExpose the all network modules.

◆ Sequential() [2/3]

Sequential ( const bool  model,
const bool  ownsLayers 
)

Create the Sequential object using the specified parameters.

Parameters
modelExpose all the network modules.
ownsLayersIf true, then this module will delete its layers when deallocated.

◆ Sequential() [3/3]

Sequential ( const Sequential< InputDataType, OutputDataType, Residual, CustomLayers > &  layer)

Copy constructor.

◆ ~Sequential()

~Sequential ( )

Destroy the Sequential object.

Member Function Documentation

◆ Add() [1/2]

void Add ( Args...  args)
inline

Definition at line 142 of file sequential.hpp.

◆ Add() [2/2]

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

Definition at line 149 of file sequential.hpp.

◆ Backward()

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.

Using the results from the feed forward pass.

Parameters
*(input) The propagated input activation.
gyThe backpropagated error.
gThe calculated gradient.

◆ Delta() [1/2]

arma::mat & Delta ( )
inline

Modify the delta.

Definition at line 180 of file sequential.hpp.

◆ Delta() [2/2]

arma::mat const & Delta ( ) const
inline

Get the delta.

Definition at line 178 of file sequential.hpp.

◆ Forward()

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.

Parameters
inputInput data used for evaluating the specified function.
outputResulting output activation.

◆ Gradient() [1/3]

arma::mat & Gradient ( )
inline

Modify the gradient.

Definition at line 185 of file sequential.hpp.

◆ Gradient() [2/3]

arma::mat const & Gradient ( ) const
inline

Get the gradient.

Definition at line 183 of file sequential.hpp.

◆ Gradient() [3/3]

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

◆ InputParameter() [1/2]

arma::mat & InputParameter ( )
inline

Modify the input parameter.

Definition at line 170 of file sequential.hpp.

◆ InputParameter() [2/2]

arma::mat const & InputParameter ( ) const
inline

Get the input parameter.

Definition at line 168 of file sequential.hpp.

◆ Model()

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

Return the model modules.

Definition at line 152 of file sequential.hpp.

◆ operator=()

Sequential & operator= ( const Sequential< InputDataType, OutputDataType, Residual, CustomLayers > &  layer)

Copy assignment operator.

◆ OutputParameter() [1/2]

arma::mat & OutputParameter ( )
inline

Modify the output parameter.

Definition at line 175 of file sequential.hpp.

◆ OutputParameter() [2/2]

arma::mat const & OutputParameter ( ) const
inline

Get the output parameter.

Definition at line 173 of file sequential.hpp.

◆ Parameters() [1/2]

arma::mat & Parameters ( )
inline

Modify the initial point for the optimization.

Definition at line 165 of file sequential.hpp.

◆ Parameters() [2/2]

const arma::mat & Parameters ( ) const
inline

Return the initial point for the optimization.

Definition at line 163 of file sequential.hpp.

◆ serialize()

void serialize ( Archive &  ,
const unsigned int   
)

Serialize the layer.


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