mlpack::ann::DiceLoss< InputDataType, OutputDataType > Class Template Reference

The dice loss performance function measures the network's performance according to the dice coefficient between the input and target distributions. More...

#include <dice_loss.hpp>

Public Member Functions
	DiceLoss (const double smooth=1)
	Create the DiceLoss object. More...
template<typename PredictionType , typename TargetType >
PredictionType::elem_type	Forward (const PredictionType &prediction, const TargetType &target)
	Computes the dice loss function. 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...
OutputDataType &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
double	Smooth () const
	Get the smooth.
double &	Smooth ()
	Modify the smooth.
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::DiceLoss< InputDataType, OutputDataType >

The dice loss performance function measures the network's performance according to the dice coefficient between the input and target distributions.

For more information see the following.

@article{Milletari2016,
  author    = {Fausto Milletari and Nassir Navab and Seyed{-}Ahmad Ahmadi},
  title     = {V-Net: Fully Convolutional Neural Networks for
               Volumetric Medical Image Segmentation},
  journal   = {CoRR},
  volume    = {abs/1606.04797},
  year      = {2016},
  url       = {http://arxiv.org/abs/1606.04797},
  archivePrefix = {arXiv},
  eprint    = {1606.04797},
}

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).

Constructor & Destructor Documentation

DiceLoss()

template<typename InputDataType , typename OutputDataType >

mlpack::ann::DiceLoss< InputDataType, OutputDataType >::DiceLoss

(

const double

smooth = 1

)

Create the DiceLoss object.

Parameters

smooth

The Laplace smoothing parameter.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename PredictionType , typename TargetType , typename LossType >

void mlpack::ann::DiceLoss< InputDataType, OutputDataType >::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.

Forward()

template<typename InputDataType , typename OutputDataType >

template<typename PredictionType , typename TargetType >

PredictionType::elem_type mlpack::ann::DiceLoss< InputDataType, OutputDataType >::Forward	(	const PredictionType &	prediction,
		const TargetType &	target
	)

Computes the dice loss function.

Parameters

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

---

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

• src/mlpack/methods/ann/loss_functions/dice_loss.hpp
• src/mlpack/methods/ann/loss_functions/dice_loss_impl.hpp