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

Implementation of the Softmax layer. More...

#include <softmax.hpp>

Public Member Functions

 Softmax ()
 Create the Softmax object. More...
 
template<typename eT >
void Backward (const arma::Mat< eT > &input, const 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 through f. More...
 
InputDataType & Delta ()
 Modify the delta. More...
 
InputDataType & Delta () const
 Get the delta. More...
 
template<typename InputType , typename OutputType >
void Forward (const InputType &input, OutputType &output)
 Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...
 
OutputDataType & OutputParameter ()
 Modify the output parameter. More...
 
OutputDataType & OutputParameter () const
 Get the output 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>
class mlpack::ann::Softmax< InputDataType, OutputDataType >

Implementation of the Softmax layer.

The softmax function takes as input a vector of K real numbers, and normalizes it into a probability distribution consisting of K probabilities proportional to the exponentials of the input numbers. It should be used for inference only and not with NLL loss (use LogSoftMax instead).

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 38 of file softmax.hpp.

Constructor & Destructor Documentation

◆ Softmax()

Softmax ( )

Create the Softmax object.

Member Function Documentation

◆ Backward()

void Backward ( const arma::Mat< eT > &  input,
const 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 through f.

Using the results from the feed forward pass.

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

Referenced by CategoricalDQN< OutputLayerType, InitType, NetworkType >::Backward().

◆ Delta() [1/2]

InputDataType & Delta ( )
inline

Modify the delta.

Definition at line 78 of file softmax.hpp.

◆ Delta() [2/2]

InputDataType & Delta ( ) const
inline

Get the delta.

Definition at line 76 of file softmax.hpp.

◆ Forward()

void Forward ( const InputType &  input,
OutputType &  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.

Referenced by CategoricalDQN< OutputLayerType, InitType, NetworkType >::Forward(), and CategoricalDQN< OutputLayerType, InitType, NetworkType >::Predict().

◆ OutputParameter() [1/2]

OutputDataType & OutputParameter ( )
inline

Modify the output parameter.

Definition at line 73 of file softmax.hpp.

◆ OutputParameter() [2/2]

OutputDataType & OutputParameter ( ) const
inline

Get the output parameter.

Definition at line 71 of file softmax.hpp.

◆ serialize()

void serialize ( Archive &  ,
const unsigned int   
)

Serialize the layer.


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