MultiLabelSoftMarginLoss< InputDataType, OutputDataType > Class Template Reference

Public Member Functions
	MultiLabelSoftMarginLoss (const bool reduction=true, const arma::rowvec &weights=arma::rowvec())
	Create the MultiLabelSoftMarginLoss object. More...
template < typename InputType , typename TargetType , typename OutputType >
void	Backward (const InputType &input, const TargetType &target, OutputType &output)
	Ordinary feed backward pass of a neural network. More...
const arma::rowvec &	ClassWeights () const
	Get the weights assigned to each class. More...
arma::rowvec &	ClassWeights ()
	Modify the weights assigned to each class. More...
template < typename InputType , typename TargetType >
InputType::elem_type	Forward (const InputType &input, const TargetType &target)
	Computes the Multi Label Soft Margin Loss function. More...
OutputDataType &	OutputParameter () const
	Get the output parameter. More...
OutputDataType &	OutputParameter ()
	Modify the output parameter. More...
bool	Reduction () const
	Get the type of reduction used. More...
bool &	Reduction ()
	Modify the type of reduction used. 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::MultiLabelSoftMarginLoss< InputDataType, OutputDataType >

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 34 of file multilabel_softmargin_loss.hpp.

Constructor & Destructor Documentation

MultiLabelSoftMarginLoss()

MultiLabelSoftMarginLoss	(	const bool	reduction = true,
		const arma::rowvec &	weights = arma::rowvec()
	)

Create the MultiLabelSoftMarginLoss object.

Parameters

reduction	Specifies the reduction to apply to the output. If false, 'mean' reduction is used, where sum of the output will be divided by the number of elements in the output. If true, 'sum' reduction is used and the output will be summed. It is set to true by default.
weights	A manual rescaling weight given to each class. It is a (1, numClasses) row vector.

Member Function Documentation

Backward()

void Backward	(	const InputType &	input,
		const TargetType &	target,
		OutputType &	output
	)

Ordinary feed backward pass of a neural network.

Parameters

input	The propagated input activation.
target	The target vector.
output	The calculated error.

ClassWeights() [1/2]

const arma::rowvec& ClassWeights ( ) const

inline

Get the weights assigned to each class.

Definition at line 79 of file multilabel_softmargin_loss.hpp.

ClassWeights() [2/2]

arma::rowvec& ClassWeights ( )

inline

Modify the weights assigned to each class.

Definition at line 81 of file multilabel_softmargin_loss.hpp.

Forward()

InputType::elem_type Forward	(	const InputType &	input,
		const TargetType &	target
	)

Computes the Multi Label Soft Margin Loss function.

Parameters

input	Input data used for evaluating the specified function.
target	The target vector with same shape as input.

OutputParameter() [1/2]

OutputDataType& OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 74 of file multilabel_softmargin_loss.hpp.

OutputParameter() [2/2]

OutputDataType& OutputParameter ( )

inline

Modify the output parameter.

Definition at line 76 of file multilabel_softmargin_loss.hpp.

Reduction() [1/2]

bool Reduction ( ) const

inline

Get the type of reduction used.

Definition at line 84 of file multilabel_softmargin_loss.hpp.

Reduction() [2/2]

bool& Reduction ( )

inline

Modify the type of reduction used.

Definition at line 86 of file multilabel_softmargin_loss.hpp.

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

serialize()

void serialize	(	Archive &	ar,
		const unsigned	int
	)

Serialize the layer.

Referenced by MultiLabelSoftMarginLoss< 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/multilabel_softmargin_loss.hpp