#include <itkMultiGradientOptimizerv4.h>

Inheritance diagram for itk::MultiGradientOptimizerv4:

Collaboration diagram for itk::MultiGradientOptimizerv4:

Detailed Description

Multiple gradient-based optimizers are combined in order to perform a multi-objective optimization.

This optimizer will do a combined gradient descent optimization using whatever metric/optimizer gradient sub-optimizers are passed to it by the user. The learning rate or scaleestimator for each sub-optimizer controls the relative weight of each metric in the optimization. Denote the weights as $ w_1 $ and $ w_2 $ then the MultiGradientOptimizer will optimize $\sum_i w_i Metric_i$ by using update rule:

$params_{new} = params_{old} + \frac{1}{N_{Metrics}} * ( \sum_i w_i Grad(Metric_i) )$

Note: The scales, learning rates and weights options must be set individually for each sub-optimizer, and have no effect when set on this class.

The test for this class illustrates the expected behavior.

Definition at line 45 of file itkMultiGradientOptimizerv4.h.

Public Types
typedef SmartPointer< const Self >	ConstPointer

typedef MetricType::DerivativeType	DerivativeType

typedef Superclass::InternalComputationValueType	InternalComputationValueType

typedef itk::GradientDescentOptimizerv4::Pointer	LocalOptimizerPointer

typedef itk::GradientDescentOptimizerv4	LocalOptimizerType

typedef Superclass::MeasureType	MeasureType

typedef Superclass::MetricType	MetricType

typedef MetricType::Pointer	MetricTypePointer

typedef std::vector< MeasureType >	MetricValuesListType

typedef OptimizerType::Pointer	OptimizerPointer

typedef OptimizersListType::size_type	OptimizersListSizeType

typedef std::vector < LocalOptimizerPointer >	OptimizersListType

typedef ObjectToObjectOptimizerBase	OptimizerType

typedef Superclass::ParametersType	ParametersType

typedef SmartPointer< Self >	Pointer

typedef MultiGradientOptimizerv4	Self

typedef std::ostringstream	StopConditionDescriptionType

typedef std::string	StopConditionReturnStringType

typedef GradientDescentOptimizerv4	Superclass

Public Types inherited from itk::GradientDescentOptimizerv4
typedef SmartPointer< const Self >	ConstPointer

typedef itk::Function::WindowConvergenceMonitoringFunction < double >	ConvergenceMonitoringType

typedef Superclass::DerivativeType	DerivativeType

typedef Superclass::InternalComputationValueType	InternalComputationValueType

typedef Superclass::MeasureType	MeasureType

typedef SmartPointer< Self >	Pointer

typedef GradientDescentOptimizerv4	Self

typedef GradientDescentOptimizerBasev4	Superclass

Public Types inherited from itk::GradientDescentOptimizerBasev4
typedef SmartPointer< const Self >	ConstPointer

typedef MetricType::DerivativeType	DerivativeType

typedef Superclass::InternalComputationValueType	InternalComputationValueType

typedef Superclass::MeasureType	MeasureType

typedef Superclass::MetricType	MetricType

typedef MetricType::Pointer	MetricTypePointer

typedef SmartPointer< Self >	Pointer

typedef GradientDescentOptimizerBasev4	Self

typedef std::ostringstream	StopConditionDescriptionType

typedef std::string	StopConditionReturnStringType

enum	StopConditionType { MAXIMUM_NUMBER_OF_ITERATIONS, COSTFUNCTION_ERROR, UPDATE_PARAMETERS_ERROR, STEP_TOO_SMALL, QUASI_NEWTON_STEP_ERROR, CONVERGENCE_CHECKER_PASSED, OTHER_ERROR }

typedef ObjectToObjectOptimizerBase	Superclass

Public Types inherited from itk::ObjectToObjectOptimizerBase
typedef SmartPointer< const Self >	ConstPointer

typedef MetricType::InternalComputationValueType	InternalComputationValueType

typedef MetricType::MeasureType	MeasureType

typedef ObjectToObjectMetricBase	MetricType

typedef MetricType::Pointer	MetricTypePointer

typedef MetricType::NumberOfParametersType	NumberOfParametersType

typedef OptimizerParameters < double >	ParametersType

typedef SmartPointer< Self >	Pointer

typedef OptimizerParameters < double >	ScalesType

typedef ObjectToObjectOptimizerBase	Self

typedef Object	Superclass

Public Types inherited from itk::Object
typedef SmartPointer< const Self >	ConstPointer

typedef SmartPointer< Self >	Pointer

typedef Object	Self

typedef LightObject	Superclass

Public Types inherited from itk::LightObject
typedef SmartPointer< const Self >	ConstPointer

typedef SmartPointer< Self >	Pointer

typedef LightObject	Self

Public Member Functions
virtual ::itk::LightObject::Pointer	CreateAnother (void) const

virtual SizeValueType	GetCurrentIteration () const

const MetricValuesListType &	GetMetricValuesList () const

virtual const char *	GetNameOfClass () const

virtual const SizeValueType &	GetNumberOfIterations ()

OptimizersListType &	GetOptimizersList ()

virtual const StopConditionType &	GetStopCondition ()

virtual const StopConditionReturnStringType	GetStopConditionDescription () const

virtual void	ResumeOptimization ()

virtual void	SetNumberOfIterations (SizeValueType _arg)

void	SetOptimizersList (OptimizersListType &p)

virtual void	StartOptimization (bool doOnlyInitialization=false)

virtual void	StopOptimization (void)

Public Member Functions inherited from itk::GradientDescentOptimizerv4
virtual void	EstimateLearningRate ()

virtual const InternalComputationValueType &	GetConvergenceValue ()

virtual const InternalComputationValueType &	GetLearningRate ()

virtual const InternalComputationValueType &	GetMaximumStepSizeInPhysicalUnits ()

virtual void	SetConvergenceWindowSize (SizeValueType _arg)

virtual void	SetLearningRate (InternalComputationValueType _arg)

virtual void	SetMaximumStepSizeInPhysicalUnits (InternalComputationValueType _arg)

virtual void	SetMinimumConvergenceValue (InternalComputationValueType _arg)

virtual void	SetScalesEstimator (OptimizerParameterScalesEstimator *_arg)

virtual void	SetDoEstimateScales (bool _arg)

virtual const bool &	GetDoEstimateScales ()

virtual void	DoEstimateScalesOn ()

virtual void	DoEstimateScalesOff ()

virtual void	SetDoEstimateLearningRateAtEachIteration (bool _arg)

virtual const bool &	GetDoEstimateLearningRateAtEachIteration ()

virtual void	DoEstimateLearningRateAtEachIterationOn ()

virtual void	DoEstimateLearningRateAtEachIterationOff ()

virtual void	SetDoEstimateLearningRateOnce (bool _arg)

virtual const bool &	GetDoEstimateLearningRateOnce ()

virtual void	DoEstimateLearningRateOnceOn ()

virtual void	DoEstimateLearningRateOnceOff ()

virtual void	SetReturnBestParametersAndValue (bool _arg)

virtual const bool &	GetReturnBestParametersAndValue ()

virtual void	ReturnBestParametersAndValueOn ()

virtual void	ReturnBestParametersAndValueOff ()

Public Member Functions inherited from itk::GradientDescentOptimizerBasev4
virtual const DerivativeType &	GetGradient ()

virtual void	ModifyGradientByScales ()

virtual void	ModifyGradientByLearningRate ()

Public Member Functions inherited from itk::ObjectToObjectOptimizerBase
virtual const MeasureType &	GetCurrentMetricValue ()

const ParametersType &	GetCurrentPosition ()

virtual const ThreadIdType &	GetNumberOfThreads ()

virtual const ScalesType &	GetScales ()

virtual const bool &	GetScalesAreIdentity ()

const MeasureType &	GetValue ()

virtual const ScalesType &	GetWeights ()

virtual const bool &	GetWeightsAreIdentity ()

virtual void	SetNumberOfThreads (ThreadIdType number)

virtual void	SetScales (ScalesType _arg)

virtual void	SetWeights (ScalesType _arg)

virtual void	SetMetric (MetricType *_arg)

virtual MetricType *	GetModifiableMetric ()

virtual const MetricType *	GetMetric () const

Public Member Functions inherited from itk::Object
unsigned long	AddObserver (const EventObject &event, Command *)

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

virtual void	DebugOff () const

virtual void	DebugOn () const

Command *	GetCommand (unsigned long tag)

bool	GetDebug () const

MetaDataDictionary &	GetMetaDataDictionary (void)

const MetaDataDictionary &	GetMetaDataDictionary (void) const

virtual ModifiedTimeType	GetMTime () const

virtual const TimeStamp &	GetTimeStamp () const

bool	HasObserver (const EventObject &event) const

void	InvokeEvent (const EventObject &)

void	InvokeEvent (const EventObject &) const

virtual void	Modified () const

virtual void	Register () const

void	RemoveAllObservers ()

void	RemoveObserver (unsigned long tag)

void	SetDebug (bool debugFlag) const

void	SetMetaDataDictionary (const MetaDataDictionary &rhs)

virtual void	SetReferenceCount (int)

virtual void	UnRegister () const

Public Member Functions inherited from itk::LightObject
virtual void	Delete ()

virtual int	GetReferenceCount () const

	itkCloneMacro (Self)

void	Print (std::ostream &os, Indent indent=0) const

Static Public Member Functions
static Pointer	New ()

Static Public Member Functions inherited from itk::GradientDescentOptimizerv4
static Pointer	New ()

Protected Member Functions
virtual void	PrintSelf (std::ostream &os, Indent indent) const


	MultiGradientOptimizerv4 ()

virtual	~MultiGradientOptimizerv4 ()

Protected Member Functions inherited from itk::GradientDescentOptimizerv4
virtual void	AdvanceOneStep (void)

	GradientDescentOptimizerv4 ()

virtual	~GradientDescentOptimizerv4 ()

virtual void	ModifyGradientByScalesOverSubRange (const IndexRangeType &subrange)

virtual void	ModifyGradientByLearningRateOverSubRange (const IndexRangeType &subrange)

Protected Member Functions inherited from itk::GradientDescentOptimizerBasev4
	GradientDescentOptimizerBasev4 ()

virtual	~GradientDescentOptimizerBasev4 ()

Protected Member Functions inherited from itk::ObjectToObjectOptimizerBase
	ObjectToObjectOptimizerBase ()

virtual	~ObjectToObjectOptimizerBase ()

Protected Member Functions inherited from itk::Object
	Object ()

bool	PrintObservers (std::ostream &os, Indent indent) const

virtual void	SetTimeStamp (const TimeStamp &time)

virtual	~Object ()

Protected Member Functions inherited from itk::LightObject
virtual LightObject::Pointer	InternalClone () const

	LightObject ()

virtual void	PrintHeader (std::ostream &os, Indent indent) const

virtual void	PrintTrailer (std::ostream &os, Indent indent) const

virtual	~LightObject ()

Protected Attributes
SizeValueType	m_CurrentIteration

MeasureType	m_MaximumMetricValue

MetricValuesListType	m_MetricValuesList

MeasureType	m_MinimumMetricValue

SizeValueType	m_NumberOfIterations

OptimizersListType	m_OptimizersList

bool	m_Stop

StopConditionType	m_StopCondition

StopConditionDescriptionType	m_StopConditionDescription

Protected Attributes inherited from itk::GradientDescentOptimizerv4
ParametersType	m_BestParameters

ConvergenceMonitoringType::Pointer	m_ConvergenceMonitoring

InternalComputationValueType	m_ConvergenceValue

SizeValueType	m_ConvergenceWindowSize

MeasureType	m_CurrentBestValue

InternalComputationValueType	m_LearningRate

InternalComputationValueType	m_MaximumStepSizeInPhysicalUnits

InternalComputationValueType	m_MinimumConvergenceValue

bool	m_ReturnBestParametersAndValue

OptimizerParameterScalesEstimator::Pointer	m_ScalesEstimator

Protected Attributes inherited from itk::GradientDescentOptimizerBasev4
SizeValueType	m_CurrentIteration

DerivativeType	m_Gradient

GradientDescentOptimizerBasev4ModifyGradientByLearningRateThreader::Pointer	m_ModifyGradientByLearningRateThreader

GradientDescentOptimizerBasev4ModifyGradientByScalesThreader::Pointer	m_ModifyGradientByScalesThreader

SizeValueType	m_NumberOfIterations

bool	m_Stop

StopConditionType	m_StopCondition

StopConditionDescriptionType	m_StopConditionDescription

Protected Attributes inherited from itk::ObjectToObjectOptimizerBase
MeasureType	m_CurrentMetricValue

MetricTypePointer	m_Metric

ThreadIdType	m_NumberOfThreads

ScalesType	m_Scales

bool	m_ScalesAreIdentity

ScalesType	m_Weights

bool	m_WeightsAreIdentity

Private Member Functions
	MultiGradientOptimizerv4 (const Self &)

void	operator= (const Self &)

Additional Inherited Members
Protected Types inherited from itk::GradientDescentOptimizerBasev4
typedef GradientDescentOptimizerBasev4ModifyGradientByScalesThreader::IndexRangeType	IndexRangeType

Member Typedef Documentation

typedef SmartPointer< const Self > itk::MultiGradientOptimizerv4::ConstPointer

Definition at line 53 of file itkMultiGradientOptimizerv4.h.

typedef MetricType::DerivativeType itk::MultiGradientOptimizerv4::DerivativeType

Derivative type

Definition at line 80 of file itkMultiGradientOptimizerv4.h.

typedef Superclass::InternalComputationValueType itk::MultiGradientOptimizerv4::InternalComputationValueType

Internal computation type, for maintaining a desired precision

Definition at line 87 of file itkMultiGradientOptimizerv4.h.

typedef itk::GradientDescentOptimizerv4::Pointer itk::MultiGradientOptimizerv4::LocalOptimizerPointer

Definition at line 62 of file itkMultiGradientOptimizerv4.h.

typedef itk::GradientDescentOptimizerv4 itk::MultiGradientOptimizerv4::LocalOptimizerType

Definition at line 59 of file itkMultiGradientOptimizerv4.h.

typedef Superclass::MeasureType itk::MultiGradientOptimizerv4::MeasureType

Measure type

Definition at line 83 of file itkMultiGradientOptimizerv4.h.

typedef Superclass::MetricType itk::MultiGradientOptimizerv4::MetricType

Metric type over which this class is templated

Definition at line 76 of file itkMultiGradientOptimizerv4.h.

typedef MetricType::Pointer itk::MultiGradientOptimizerv4::MetricTypePointer

Definition at line 77 of file itkMultiGradientOptimizerv4.h.

typedef std::vector< MeasureType > itk::MultiGradientOptimizerv4::MetricValuesListType

Definition at line 84 of file itkMultiGradientOptimizerv4.h.

typedef OptimizerType::Pointer itk::MultiGradientOptimizerv4::OptimizerPointer

Definition at line 65 of file itkMultiGradientOptimizerv4.h.

typedef OptimizersListType::size_type itk::MultiGradientOptimizerv4::OptimizersListSizeType

Definition at line 67 of file itkMultiGradientOptimizerv4.h.

typedef std::vector< LocalOptimizerPointer > itk::MultiGradientOptimizerv4::OptimizersListType

Definition at line 66 of file itkMultiGradientOptimizerv4.h.

typedef ObjectToObjectOptimizerBase itk::MultiGradientOptimizerv4::OptimizerType

Definition at line 64 of file itkMultiGradientOptimizerv4.h.

typedef Superclass::ParametersType itk::MultiGradientOptimizerv4::ParametersType

Definition at line 63 of file itkMultiGradientOptimizerv4.h.

typedef SmartPointer< Self > itk::MultiGradientOptimizerv4::Pointer

Definition at line 52 of file itkMultiGradientOptimizerv4.h.

typedef MultiGradientOptimizerv4 itk::MultiGradientOptimizerv4::Self

Standard class typedefs.

Definition at line 50 of file itkMultiGradientOptimizerv4.h.

typedef std::ostringstream itk::MultiGradientOptimizerv4::StopConditionDescriptionType

Stop condition internal string type

Definition at line 73 of file itkMultiGradientOptimizerv4.h.

typedef std::string itk::MultiGradientOptimizerv4::StopConditionReturnStringType

Stop condition return string type

Definition at line 70 of file itkMultiGradientOptimizerv4.h.

typedef GradientDescentOptimizerv4 itk::MultiGradientOptimizerv4::Superclass

Definition at line 51 of file itkMultiGradientOptimizerv4.h.

Constructor & Destructor Documentation

itk::MultiGradientOptimizerv4::MultiGradientOptimizerv4 ( )

protected

Default constructor

virtual itk::MultiGradientOptimizerv4::~MultiGradientOptimizerv4 ( )

protectedvirtual

Default constructor

itk::MultiGradientOptimizerv4::MultiGradientOptimizerv4 ( const Self & )

private

Member Function Documentation

virtual::itk::LightObject::Pointer itk::MultiGradientOptimizerv4::CreateAnother ( void ) const

virtual

Create an object from an instance, potentially deferring to a factory. This method allows you to create an instance of an object that is exactly the same type as the referring object. This is useful in cases where an object has been cast back to a base class.

Reimplemented from itk::GradientDescentOptimizerv4.

virtual SizeValueType itk::MultiGradientOptimizerv4::GetCurrentIteration ( ) const

virtual

Get the current iteration number.

Reimplemented from itk::GradientDescentOptimizerBasev4.

const MetricValuesListType& itk::MultiGradientOptimizerv4::GetMetricValuesList ( ) const

Get the list of metric values that we produced after the multi-objective search.

virtual const char* itk::MultiGradientOptimizerv4::GetNameOfClass ( ) const

virtual

Run-time type information (and related methods).

Reimplemented from itk::GradientDescentOptimizerv4.

virtual const SizeValueType& itk::MultiGradientOptimizerv4::GetNumberOfIterations ( )

virtual

Get the number of iterations.

Reimplemented from itk::GradientDescentOptimizerBasev4.

OptimizersListType& itk::MultiGradientOptimizerv4::GetOptimizersList ( )

Get the list of optimizers currently held.

virtual const StopConditionType& itk::MultiGradientOptimizerv4::GetStopCondition ( )

virtual

Get stop condition enum

Reimplemented from itk::GradientDescentOptimizerBasev4.

virtual const StopConditionReturnStringType itk::MultiGradientOptimizerv4::GetStopConditionDescription ( ) const

virtual

Get the reason for termination

Reimplemented from itk::GradientDescentOptimizerBasev4.

static Pointer itk::MultiGradientOptimizerv4::New ( )

static

Method for creation through the object factory.

void itk::MultiGradientOptimizerv4::operator= ( const Self & )

private

virtual void itk::MultiGradientOptimizerv4::PrintSelf	(	std::ostream &	os,
		Indent	indent
	)		const

protectedvirtual

Methods invoked by Print() to print information about the object including superclasses. Typically not called by the user (use Print() instead) but used in the hierarchical print process to combine the output of several classes.

Reimplemented from itk::GradientDescentOptimizerv4.

virtual void itk::MultiGradientOptimizerv4::ResumeOptimization ( )

virtual

Resume the optimization. Can be called after StopOptimization to resume. The bulk of the optimization work loop is here.

Reimplemented from itk::GradientDescentOptimizerv4.

virtual void itk::MultiGradientOptimizerv4::SetNumberOfIterations ( SizeValueType _arg )

virtual

Set the number of iterations.

Reimplemented from itk::GradientDescentOptimizerBasev4.

void itk::MultiGradientOptimizerv4::SetOptimizersList ( OptimizersListType & p )

Set the list of optimizers to combine

virtual void itk::MultiGradientOptimizerv4::StartOptimization ( bool doOnlyInitialization = false )