BCELoss< InputDataType, OutputDataType > Class Template Reference

The binary-cross-entropy performance function measures the Binary Cross Entropy between the target and the output. More...

Public Member Functions
	BCELoss (const double eps=1e-10, const bool reduction=true)
	Create the BinaryCrossEntropyLoss 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...
double	Eps () const
	Get the epsilon. More...
double &	Eps ()
	Modify the epsilon. More...
template < typename PredictionType , typename TargetType >
PredictionType::elem_type	Forward (const PredictionType &prediction, const TargetType &target)
	Computes the cross-entropy function. More...
OutputDataType &	OutputParameter () const
	Get the output parameter. More...
OutputDataType &	OutputParameter ()
	Modify the output parameter. More...
bool	Reduction () const
	Get the reduction. More...
bool &	Reduction ()
	Set the reduction. 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::BCELoss< InputDataType, OutputDataType >

The binary-cross-entropy performance function measures the Binary Cross Entropy between the target and the output.

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).

Definition at line 33 of file binary_cross_entropy_loss.hpp.

Constructor & Destructor Documentation

BCELoss()

BCELoss	(	const double	eps = 1e-10,
		const bool	reduction = true
	)

Create the BinaryCrossEntropyLoss object.

Parameters

eps	The minimum value used for computing logarithms and denominators in a numerically stable way.
reduction	Reduction type. If true, it returns the mean of the loss. Else, it returns the sum.

Member Function Documentation

Backward()

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

Ordinary feed backward pass of a neural network.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The target vector.
loss	The calculated error.

Eps() [1/2]

double Eps ( ) const

inline

Get the epsilon.

Definition at line 76 of file binary_cross_entropy_loss.hpp.

Eps() [2/2]

double& Eps ( )

inline

Modify the epsilon.

Definition at line 78 of file binary_cross_entropy_loss.hpp.

Forward()

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

Computes the cross-entropy function.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The target vector.

OutputParameter() [1/2]

OutputDataType& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 71 of file binary_cross_entropy_loss.hpp.

OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 73 of file binary_cross_entropy_loss.hpp.

Reduction() [1/2]

bool Reduction ( ) const

inline

Get the reduction.

Definition at line 81 of file binary_cross_entropy_loss.hpp.

Reduction() [2/2]

bool& Reduction ( )

inline

Set the reduction.

Definition at line 83 of file binary_cross_entropy_loss.hpp.

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

serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the layer.

Referenced by BCELoss< InputDataType, OutputDataType >::Reduction().

---

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

• /home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/loss_functions/binary_cross_entropy_loss.hpp