PoissonNLLLoss< InputDataType, OutputDataType > Class Template Reference

Implementation of the Poisson negative log likelihood loss. More...

Public Member Functions

 PoissonNLLLoss (const bool logInput=true, const bool full=false, const typename InputDataType::elem_type eps=1e-08, const bool mean=true)
 Create the PoissonNLLLoss object. More...

 
template
<
typename
PredictionType
,
typename
TargetType
,
typename
LossType
>
void Backward (const PredictionType &prediction, const TargetType &target, LossType &loss)
 Ordinary feed backward pass of a neural network. More...

 
InputDataType::elem_type Eps () const
 Get the value of eps. More...

 
InputDataType::elem_type & Eps ()
 Modify the value of eps. More...

 
template
<
typename
PredictionType
,
typename
TargetType
>
InputDataType::elem_type Forward (const PredictionType &prediction, const TargetType &target)
 Computes the Poisson negative log likelihood Loss. More...

 
bool Full () const
 Get the value of full. More...

 
bool & Full ()
 Modify the value of full. More...

 
InputDataType & InputParameter () const
 Get the input parameter. More...

 
InputDataType & InputParameter ()
 Modify the input parameter. More...

 
bool LogInput () const
 Get the value of logInput. More...

 
bool & LogInput ()
 Modify the value of logInput. More...

 
bool Mean () const
 Get the value of mean. More...

 
bool & Mean ()
 Modify the value of mean. More...

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

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

 
template
<
typename
Archive
>
void serialize (Archive &ar, const uint32_t)
 Serialize the layer. More...

 

Detailed Description


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

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

Implementation of the Poisson negative log likelihood loss.

This loss function expects input for each class. It also expects a class index, in the range between 1 and the number of classes, as target when calling the Forward 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).

Definition at line 36 of file poisson_nll_loss.hpp.

Constructor & Destructor Documentation

◆ PoissonNLLLoss()

PoissonNLLLoss ( const bool  logInput = true,
const bool  full = false,
const typename InputDataType::elem_type  eps = 1e-08,
const bool  mean = true 
)

Create the PoissonNLLLoss object.

Parameters
logInputIf true the loss is computed as $ \exp(input) - target \cdot input $, if false then the loss is $ input - target \cdot \log(input + eps) $.
fullBoolean value that determines whether to include Stirling's approximation term.
epsA small value to prevent 0 in denominators and logarithms.
meanWhen true, mean loss is computed otherwise total loss.

Member Function Documentation

◆ Backward()

void Backward ( const PredictionType &  prediction,
const TargetType &  target,
LossType &  loss 
)

Ordinary feed backward pass of a neural network.

The Poisson Negative Log Likelihood loss function expects the input for each class. It expects a class index, in the range between 1 and the number of classes, as target when calling the Forward function.

Parameters
predictionPredictions used for evaluating the specified loss function.
targetThe target vector, that contains the class index in the range between 1 and the number of classes.
lossThe calculated error.

◆ Eps() [1/2]

InputDataType::elem_type Eps ( ) const
inline

Get the value of eps.

eps is a small value required to prevent 0 in logarithms and denominators.

Definition at line 110 of file poisson_nll_loss.hpp.

◆ Eps() [2/2]

InputDataType::elem_type& Eps ( )
inline

Modify the value of eps.

eps is a small value required to prevent 0 in logarithms and denominators.

Definition at line 113 of file poisson_nll_loss.hpp.

◆ Forward()

InputDataType::elem_type Forward ( const PredictionType &  prediction,
const TargetType &  target 
)

Computes the Poisson negative log likelihood Loss.

Parameters
predictionPredictions used for evaluating the specified loss function.
targetThe target vector, that contains the class index in the range between 1 and the number of classes.

◆ Full() [1/2]

bool Full ( ) const
inline

Get the value of full.

full is a boolean value that determines whether to include Stirling's approximation term.

Definition at line 103 of file poisson_nll_loss.hpp.

◆ Full() [2/2]

bool& Full ( )
inline

Modify the value of full.

full is a boolean value that determines whether to include Stirling's approximation term.

Definition at line 106 of file poisson_nll_loss.hpp.

◆ InputParameter() [1/2]

InputDataType& InputParameter ( ) const
inline

Get the input parameter.

Definition at line 85 of file poisson_nll_loss.hpp.

◆ InputParameter() [2/2]

InputDataType& InputParameter ( )
inline

Modify the input parameter.

Definition at line 87 of file poisson_nll_loss.hpp.

◆ LogInput() [1/2]

bool LogInput ( ) const
inline

Get the value of logInput.

logInput is a boolean value that tells if logits are given as input.

Definition at line 96 of file poisson_nll_loss.hpp.

◆ LogInput() [2/2]

bool& LogInput ( )
inline

Modify the value of logInput.

logInput is a boolean value that tells if logits are given as input.

Definition at line 99 of file poisson_nll_loss.hpp.

◆ Mean() [1/2]

bool Mean ( ) const
inline

Get the value of mean.

It's a boolean value that tells if mean of the total loss has to be taken.

Definition at line 117 of file poisson_nll_loss.hpp.

◆ Mean() [2/2]

bool& Mean ( )
inline

Modify the value of mean.

It's a boolean value that tells if mean of the total loss has to be taken.

Definition at line 120 of file poisson_nll_loss.hpp.

References Log::Fatal, and PoissonNLLLoss< InputDataType, OutputDataType >::serialize().

◆ OutputParameter() [1/2]

OutputDataType& OutputParameter ( ) const
inline

Get the output parameter.

Definition at line 90 of file poisson_nll_loss.hpp.

◆ OutputParameter() [2/2]

OutputDataType& OutputParameter ( )
inline

Modify the output parameter.

Definition at line 92 of file poisson_nll_loss.hpp.

◆ serialize()

void serialize ( Archive &  ar,
const uint32_t   
)

Serialize the layer.

Referenced by PoissonNLLLoss< InputDataType, OutputDataType >::Mean().


The documentation for this class was generated from the following file:
  • /home/jenkins-mlpack/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/loss_functions/poisson_nll_loss.hpp