GRU< InputDataType, OutputDataType > Class Template Reference

An implementation of a gru network layer. More...

Public Member Functions

 GRU ()
 Create the GRU object. More...

 
 GRU (const size_t inSize, const size_t outSize, const size_t rho=std::numeric_limits< size_t >::max())
 Create the GRU layer object using the specified parameters. More...

 
 ~GRU ()
 Delete the GRU and the layers it holds. More...

 
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, calculating the function f(x) by propagating x backwards trough f. More...

 
OutputDataType const & Delta () const
 Get the delta. More...

 
OutputDataType & Delta ()
 Modify the delta. More...

 
bool Deterministic () const
 The value of the deterministic parameter. More...

 
bool & Deterministic ()
 Modify the value of the deterministic parameter. 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 > &&input, arma::Mat< eT > &&, arma::Mat< eT > &&)
 
OutputDataType const & Gradient () const
 Get the gradient. More...

 
OutputDataType & Gradient ()
 Modify the gradient. More...

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

 
OutputDataType const & OutputParameter () const
 Get the output parameter. More...

 
OutputDataType & OutputParameter ()
 Modify the output parameter. More...

 
OutputDataType const & Parameters () const
 Get the parameters. More...

 
OutputDataType & Parameters ()
 Modify the parameters. More...

 
void ResetCell (const size_t size)
 
size_t Rho () const
 Get the maximum number of steps to backpropagate through time (BPTT). More...

 
size_t & Rho ()
 Modify the maximum number of steps to backpropagate through time (BPTT). More...

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

 

Detailed Description


template
<
typename
InputDataType
=
arma::mat
,
typename
OutputDataType
=
arma::mat
>

class mlpack::ann::GRU< InputDataType, OutputDataType >

An implementation of a gru network layer.

This cell can be used in RNN networks.

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).

Definition at line 57 of file gru.hpp.

Constructor & Destructor Documentation

◆ GRU() [1/2]

GRU ( )

Create the GRU object.

◆ GRU() [2/2]

GRU ( const size_t  inSize,
const size_t  outSize,
const size_t  rho = std::numeric_limits< size_t >::max() 
)

Create the GRU layer object using the specified parameters.

Parameters
inSizeThe number of input units.
outSizeThe number of output units.
rhoMaximum number of steps to backpropagate through time (BPTT).

◆ ~GRU()

~GRU ( )

Delete the GRU and the layers it holds.

Member Function Documentation

◆ Backward()

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

Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards trough f.

Using the results from the feed forward pass.

Parameters
inputThe propagated input activation.
gyThe backpropagated error.
gThe calculated gradient.

◆ Delta() [1/2]

OutputDataType const& Delta ( ) const
inline

Get the delta.

Definition at line 144 of file gru.hpp.

◆ Delta() [2/2]

OutputDataType& Delta ( )
inline

Modify the delta.

Definition at line 146 of file gru.hpp.

◆ Deterministic() [1/2]

bool Deterministic ( ) const
inline

The value of the deterministic parameter.

Definition at line 124 of file gru.hpp.

◆ Deterministic() [2/2]

bool& Deterministic ( )
inline

Modify the value of the deterministic parameter.

Definition at line 126 of file gru.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
inputInput data used for evaluating the specified function.
outputResulting output activation.

◆ Gradient() [1/3]

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

◆ Gradient() [2/3]

OutputDataType const& Gradient ( ) const
inline

Get the gradient.

Definition at line 149 of file gru.hpp.

◆ Gradient() [3/3]

OutputDataType& Gradient ( )
inline

Modify the gradient.

Definition at line 151 of file gru.hpp.

◆ Model()

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

Get the model modules.

Definition at line 154 of file gru.hpp.

References GRU< InputDataType, OutputDataType >::serialize().

◆ OutputParameter() [1/2]

OutputDataType const& OutputParameter ( ) const
inline

Get the output parameter.

Definition at line 139 of file gru.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )
inline

Modify the output parameter.

Definition at line 141 of file gru.hpp.

◆ Parameters() [1/2]

OutputDataType const& Parameters ( ) const
inline

Get the parameters.

Definition at line 134 of file gru.hpp.

◆ Parameters() [2/2]

OutputDataType& Parameters ( )
inline

Modify the parameters.

Definition at line 136 of file gru.hpp.

◆ ResetCell()

void ResetCell ( const size_t  size)

◆ Rho() [1/2]

size_t Rho ( ) const
inline

Get the maximum number of steps to backpropagate through time (BPTT).

Definition at line 129 of file gru.hpp.

◆ Rho() [2/2]

size_t& Rho ( )
inline

Modify the maximum number of steps to backpropagate through time (BPTT).

Definition at line 131 of file gru.hpp.

◆ serialize()

void serialize ( Archive &  ar,
const unsigned  int 
)

Serialize the layer.

Referenced by GRU< InputDataType, OutputDataType >::Model().


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/gru.hpp