#include <itkRSGDEachParameterApartOptimizer.h>

Detailed Description

An optimizer based on gradient descent.

This class is almost a copy of the normal itk::RegularStepGradientDescentOptimizer. The difference is that each parameter has its own step length, whereas the normal RSGD has one step length that is used for all parameters.

This could cause inaccuracies, if, for example, parameter 1, 2 and 3 are already close to the optimum, but parameter 4 not yet. The average stepsize is halved then, so parameter 4 will not have time to reach its optimum (in a worst case scenario).

The RSGDEachParameterApart stops only if ALL steplenghts are smaller than the MinimumStepSize given in the parameter file!

Note that this is a quite experimental optimizer, currently only used for some specific tests.

See also: RSGDEachParameterApart

Definition at line 53 of file itkRSGDEachParameterApartOptimizer.h.

Inheritance diagram for itk::RSGDEachParameterApartOptimizer:

[legend]

Public Types
using	ConstPointer = SmartPointer<const Self>

using	CostFunctionPointer = CostFunctionType::Pointer

using	Pointer = SmartPointer<Self>

using	Self = RSGDEachParameterApartOptimizer

using	Superclass = RSGDEachParameterApartBaseOptimizer

Public Types inherited from itk::RSGDEachParameterApartBaseOptimizer
using	ConstPointer = SmartPointer<const Self>

using	Pointer = SmartPointer<Self>

using	Self = RSGDEachParameterApartBaseOptimizer

enum	StopConditionType { GradientMagnitudeTolerance = 1 , StepTooSmall , ImageNotAvailable , SamplesNotAvailable , MaximumNumberOfIterations , MetricError }

using	Superclass = SingleValuedNonLinearOptimizer

Public Member Functions
virtual const char *	GetClassName () const

	ITK_DISALLOW_COPY_AND_MOVE (RSGDEachParameterApartOptimizer)

Public Member Functions inherited from itk::RSGDEachParameterApartBaseOptimizer
virtual unsigned long	GetCurrentIteration () const

virtual double	GetCurrentStepLength () const

virtual const DerivativeType &	GetCurrentStepLengths ()

virtual const DerivativeType &	GetGradient ()

virtual double	GetGradientMagnitude () const

virtual double	GetGradientMagnitudeTolerance () const

virtual bool	GetMaximize () const

virtual double	GetMaximumStepLength () const

bool	GetMinimize () const

virtual double	GetMinimumStepLength () const

virtual unsigned long	GetNumberOfIterations () const

virtual StopConditionType	GetStopCondition () const

virtual MeasureType	GetValue () const

	ITK_DISALLOW_COPY_AND_MOVE (RSGDEachParameterApartBaseOptimizer)

virtual void	MaximizeOff ()

virtual void	MaximizeOn ()

void	MinimizeOff ()

void	MinimizeOn ()

void	ResumeOptimization ()

virtual void	SetGradientMagnitudeTolerance (double _arg)

virtual void	SetMaximize (bool _arg)

virtual void	SetMaximumStepLength (double _arg)

void	SetMinimize (bool v)

virtual void	SetMinimumStepLength (double _arg)

virtual void	SetNumberOfIterations (unsigned long _arg)

void	StartOptimization () override

void	StopOptimization ()

Static Public Member Functions
static Pointer	New ()

Static Public Member Functions inherited from itk::RSGDEachParameterApartBaseOptimizer
static Pointer	New ()

Protected Member Functions
	RSGDEachParameterApartOptimizer ()=default

void	StepAlongGradient (const DerivativeType &factor, const DerivativeType &transformedGradient) override

	~RSGDEachParameterApartOptimizer () override=default

Protected Member Functions inherited from itk::RSGDEachParameterApartBaseOptimizer
virtual void	AdvanceOneStep ()

void	PrintSelf (std::ostream &os, Indent indent) const override

	RSGDEachParameterApartBaseOptimizer ()

	~RSGDEachParameterApartBaseOptimizer () override=default

Member Typedef Documentation

◆ ConstPointer

using itk::RSGDEachParameterApartOptimizer::ConstPointer = SmartPointer<const Self>

Definition at line 62 of file itkRSGDEachParameterApartOptimizer.h.

◆ CostFunctionPointer

using itk::RSGDEachParameterApartOptimizer::CostFunctionPointer = CostFunctionType::Pointer

Definition at line 72 of file itkRSGDEachParameterApartOptimizer.h.

◆ Pointer

using itk::RSGDEachParameterApartOptimizer::Pointer = SmartPointer<Self>

Definition at line 61 of file itkRSGDEachParameterApartOptimizer.h.

◆ Self

using itk::RSGDEachParameterApartOptimizer::Self = RSGDEachParameterApartOptimizer

Standard class typedefs.

Definition at line 59 of file itkRSGDEachParameterApartOptimizer.h.

◆ Superclass

using itk::RSGDEachParameterApartOptimizer::Superclass = RSGDEachParameterApartBaseOptimizer

Definition at line 60 of file itkRSGDEachParameterApartOptimizer.h.

Constructor & Destructor Documentation

◆ RSGDEachParameterApartOptimizer()

itk::RSGDEachParameterApartOptimizer::RSGDEachParameterApartOptimizer ( )

protecteddefault

◆ ~RSGDEachParameterApartOptimizer()

itk::RSGDEachParameterApartOptimizer::~RSGDEachParameterApartOptimizer ( )

overrideprotecteddefault

Member Function Documentation

◆ GetClassName()

virtual const char * itk::RSGDEachParameterApartOptimizer::GetClassName ( ) const

virtual

Run-time type information (and related methods).

Reimplemented from itk::RSGDEachParameterApartBaseOptimizer.

Reimplemented in elastix::RSGDEachParameterApart< TElastix >.

◆ ITK_DISALLOW_COPY_AND_MOVE()

itk::RSGDEachParameterApartOptimizer::ITK_DISALLOW_COPY_AND_MOVE ( RSGDEachParameterApartOptimizer )

◆ New()

static Pointer itk::RSGDEachParameterApartOptimizer::New ( )

static

Method for creation through the object factory.

◆ StepAlongGradient()

void itk::RSGDEachParameterApartOptimizer::StepAlongGradient	(	const DerivativeType &	factor,
		const DerivativeType &	transformedGradient )

overrideprotectedvirtual

Advance one step along the corrected gradient taking into account the steplengths represented by the factor array. This method is invoked by AdvanceOneStep. It is expected to be overrided by optimization methods in non-vector spaces

See also: AdvanceOneStep