itk::SingleValuedVnlCostFunctionAdaptor Class Reference

#include <itkSingleValuedVnlCostFunctionAdaptor.h>

Detailed Description

This class is an Adaptor that allows to pass itk::SingleValuedCostFunctions to vnl_optimizers expecting a vnl_cost_function.

This class returns a single valued.

Definition at line 37 of file itkSingleValuedVnlCostFunctionAdaptor.h.

Inheritance diagram for itk::SingleValuedVnlCostFunctionAdaptor:

Collaboration diagram for itk::SingleValuedVnlCostFunctionAdaptor:

Public Types
using	DerivativeType = SingleValuedCostFunction::DerivativeType
using	InternalDerivativeType = vnl_vector<double>
using	InternalMeasureType = double
using	InternalParametersType = vnl_vector<double>
using	MeasureType = SingleValuedCostFunction::MeasureType
using	ParametersType = SingleValuedCostFunction::ParametersType
using	ScalesType = Array<double>

Public Member Functions
unsigned long	AddObserver (const EventObject &event, Command *) const
void	compute (const InternalParametersType &x, InternalMeasureType *fun, InternalDerivativeType *g) override
void	ConvertExternalToInternalGradient (const DerivativeType &input, InternalDerivativeType &output) const
InternalMeasureType	f (const InternalParametersType &inparameters) override
const ParametersType &	GetCachedCurrentParameters () const
const DerivativeType &	GetCachedDerivative () const
const MeasureType &	GetCachedValue () const
const SingleValuedCostFunction *	GetCostFunction () const
bool	GetNegateCostFunction () const
void	gradf (const InternalParametersType &inparameters, InternalDerivativeType &gradient) override
void	NegateCostFunctionOff ()
void	NegateCostFunctionOn ()
void	SetCostFunction (SingleValuedCostFunction *costFunction)
void	SetNegateCostFunction (bool flag)
void	SetScales (const ScalesType &scales)
	SingleValuedVnlCostFunctionAdaptor (unsigned int spaceDimension)

Protected Member Functions
void	ReportIteration (const EventObject &event) const

Private Member Functions
virtual const ScalesType &	GetInverseScales () const

Private Attributes
ParametersType	m_CachedCurrentParameters {}
DerivativeType	m_CachedDerivative {}
MeasureType	m_CachedValue {}
SingleValuedCostFunction::Pointer	m_CostFunction {}
ScalesType	m_InverseScales {}
bool	m_NegateCostFunction {}
Object::Pointer	m_Reporter {}
bool	m_ScalesInitialized {}

Member Typedef Documentation

DerivativeType

using itk::SingleValuedVnlCostFunctionAdaptor::DerivativeType = SingleValuedCostFunction::DerivativeType

Derivatives of the SingleValuedCostFunction

Definition at line 53 of file itkSingleValuedVnlCostFunctionAdaptor.h.

InternalDerivativeType

using itk::SingleValuedVnlCostFunctionAdaptor::InternalDerivativeType = vnl_vector<double>

InternalGradientType type alias.

Definition at line 47 of file itkSingleValuedVnlCostFunctionAdaptor.h.

InternalMeasureType

using itk::SingleValuedVnlCostFunctionAdaptor::InternalMeasureType = double

InternalMeasureType type alias.

Definition at line 44 of file itkSingleValuedVnlCostFunctionAdaptor.h.

InternalParametersType

using itk::SingleValuedVnlCostFunctionAdaptor::InternalParametersType = vnl_vector<double>

InternalParametersType type alias.

Definition at line 41 of file itkSingleValuedVnlCostFunctionAdaptor.h.

MeasureType

using itk::SingleValuedVnlCostFunctionAdaptor::MeasureType = SingleValuedCostFunction::MeasureType

Type of the SingleValuedCostFunction value

Definition at line 56 of file itkSingleValuedVnlCostFunctionAdaptor.h.

ParametersType

using itk::SingleValuedVnlCostFunctionAdaptor::ParametersType = SingleValuedCostFunction::ParametersType

Parameters of the SingleValuedCostFunction

Definition at line 50 of file itkSingleValuedVnlCostFunctionAdaptor.h.

ScalesType

using itk::SingleValuedVnlCostFunctionAdaptor::ScalesType = Array<double>

Scales type alias

Definition at line 59 of file itkSingleValuedVnlCostFunctionAdaptor.h.

Constructor & Destructor Documentation

SingleValuedVnlCostFunctionAdaptor()

itk::SingleValuedVnlCostFunctionAdaptor::SingleValuedVnlCostFunctionAdaptor

(

unsigned int

spaceDimension

)

Constructor with size

Member Function Documentation

AddObserver()

unsigned long itk::SingleValuedVnlCostFunctionAdaptor::AddObserver	(	const EventObject &	event,
		Command *	) const

This AddObserver method allows to simulate that this class derives from an itkObject for the purpose of reporting iteration events. The goal of this method is to allow ITK-vnl optimizer adaptors to get iteration events despite the fact that VNL does not provide callbacks.

compute()

void itk::SingleValuedVnlCostFunctionAdaptor::compute ( const InternalParametersType & x, InternalMeasureType * fun, InternalDerivativeType * g )

override

Delegate computation of value and gradient to the costFunction.

ConvertExternalToInternalGradient()

void itk::SingleValuedVnlCostFunctionAdaptor::ConvertExternalToInternalGradient	(	const DerivativeType &	input,
		InternalDerivativeType &	output ) const

Convert external derivative measures into internal type

f()

InternalMeasureType itk::SingleValuedVnlCostFunctionAdaptor::f ( const InternalParametersType & inparameters )

override

Delegate computation of the value to the CostFunction.

GetCachedCurrentParameters()

const ParametersType & itk::SingleValuedVnlCostFunctionAdaptor::GetCachedCurrentParameters

(

)

const

GetCachedDerivative()

const DerivativeType & itk::SingleValuedVnlCostFunctionAdaptor::GetCachedDerivative

(

)

const

GetCachedValue()

const MeasureType & itk::SingleValuedVnlCostFunctionAdaptor::GetCachedValue

(

)

const

Return the value of the last evaluation to the value of the cost function. Note that this method DOES NOT triggers a computation of the function or the derivatives, it only returns previous values. Therefore the values here are only valid after you invoke the f() or gradf() methods.

GetCostFunction()

const SingleValuedCostFunction * itk::SingleValuedVnlCostFunctionAdaptor::GetCostFunction ( ) const

inline

Get the CostFunction deriving from SingleValuedCostFunction

Definition at line 73 of file itkSingleValuedVnlCostFunctionAdaptor.h.

References m_CostFunction.

GetInverseScales()

virtual const ScalesType & itk::SingleValuedVnlCostFunctionAdaptor::GetInverseScales ( ) const

privatevirtual

Get current parameters scaling.

GetNegateCostFunction()

bool itk::SingleValuedVnlCostFunctionAdaptor::GetNegateCostFunction

(

)

const

gradf()

void itk::SingleValuedVnlCostFunctionAdaptor::gradf ( const InternalParametersType & inparameters, InternalDerivativeType & gradient )

override

Delegate computation of the gradient to the costFunction.

NegateCostFunctionOff()

void itk::SingleValuedVnlCostFunctionAdaptor::NegateCostFunctionOff ( )

inline

Definition at line 118 of file itkSingleValuedVnlCostFunctionAdaptor.h.

References m_NegateCostFunction.

NegateCostFunctionOn()

void itk::SingleValuedVnlCostFunctionAdaptor::NegateCostFunctionOn ( )

inline

Definition at line 113 of file itkSingleValuedVnlCostFunctionAdaptor.h.

References m_NegateCostFunction.

ReportIteration()

void itk::SingleValuedVnlCostFunctionAdaptor::ReportIteration ( const EventObject & event ) const

protected

This method is intended to be called by the derived classes in order to notify of an iteration event to any Command/Observers

SetCostFunction()

void itk::SingleValuedVnlCostFunctionAdaptor::SetCostFunction ( SingleValuedCostFunction * costFunction )

inline

Set the CostFunction deriving from SingleValuedCostFunction

Definition at line 66 of file itkSingleValuedVnlCostFunctionAdaptor.h.

References m_CostFunction.

SetNegateCostFunction()

void itk::SingleValuedVnlCostFunctionAdaptor::SetNegateCostFunction

(

bool

flag

)

Set/Get Negate cost function. The purpose of this boolean flag is to make possible to take certain VNL optimizers that are only minimizers, and use them for maximizing functions. When the boolean flag is set to true, the values returned by GetValue in the internal ITK cost function will be multiplied by -1 before returning it in the f() function. Similar operations will be done for the gradf() and compute() methods. When the boolean flag is set to false, then the values returned by the ITK cost function will be passed unchanged to the VNL optimizers.

SetScales()

void itk::SingleValuedVnlCostFunctionAdaptor::SetScales

(

const ScalesType &

scales

)

Set current parameters scaling.

Member Data Documentation

m_CachedCurrentParameters

ParametersType itk::SingleValuedVnlCostFunctionAdaptor::m_CachedCurrentParameters {}

mutableprivate

Definition at line 161 of file itkSingleValuedVnlCostFunctionAdaptor.h.

m_CachedDerivative

DerivativeType itk::SingleValuedVnlCostFunctionAdaptor::m_CachedDerivative {}

mutableprivate

Definition at line 160 of file itkSingleValuedVnlCostFunctionAdaptor.h.

m_CachedValue

MeasureType itk::SingleValuedVnlCostFunctionAdaptor::m_CachedValue {}

mutableprivate

Definition at line 159 of file itkSingleValuedVnlCostFunctionAdaptor.h.

m_CostFunction

SingleValuedCostFunction::Pointer itk::SingleValuedVnlCostFunctionAdaptor::m_CostFunction {}

private

Definition at line 153 of file itkSingleValuedVnlCostFunctionAdaptor.h.

Referenced by GetCostFunction(), and SetCostFunction().

m_InverseScales

ScalesType itk::SingleValuedVnlCostFunctionAdaptor::m_InverseScales {}

private

Definition at line 155 of file itkSingleValuedVnlCostFunctionAdaptor.h.

m_NegateCostFunction

bool itk::SingleValuedVnlCostFunctionAdaptor::m_NegateCostFunction {}

private

Definition at line 156 of file itkSingleValuedVnlCostFunctionAdaptor.h.

Referenced by NegateCostFunctionOff(), and NegateCostFunctionOn().

m_Reporter

Object::Pointer itk::SingleValuedVnlCostFunctionAdaptor::m_Reporter {}

private

Definition at line 157 of file itkSingleValuedVnlCostFunctionAdaptor.h.

m_ScalesInitialized

bool itk::SingleValuedVnlCostFunctionAdaptor::m_ScalesInitialized {}

private

Definition at line 154 of file itkSingleValuedVnlCostFunctionAdaptor.h.

---

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

• itkSingleValuedVnlCostFunctionAdaptor.h