itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType > Class Template Reference

#include <itkGradientDescentOptimizerBasev4.h>

Inheritance diagram for itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >:

Collaboration diagram for itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >:

Detailed Description

template<typename TInternalComputationValueType>
class itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >

Definition at line 39 of file itkGradientDescentOptimizerBasev4.h.

Public Types
typedef SmartPointer< const Self >	ConstPointer
typedef itk::Function::WindowConvergenceMonitoringFunction < TInternalComputationValueType >	ConvergenceMonitoringType
typedef Superclass::DerivativeType	DerivativeType
typedef ThreadedIndexedContainerPartitioner::IndexRangeType	IndexRangeType
typedef TInternalComputationValueType	InternalComputationValueType
typedef Superclass::MeasureType	MeasureType
typedef Superclass::MetricType	MetricType
typedef MetricType::Pointer	MetricTypePointer
typedef Superclass::ParametersType	ParametersType
typedef SmartPointer< Self >	Pointer
typedef Superclass::ScalesType	ScalesType
typedef GradientDescentOptimizerBasev4Template	Self
typedef Superclass::StopConditionDescriptionType	StopConditionDescriptionType
typedef Superclass::StopConditionReturnStringType	StopConditionReturnStringType
enum	StopConditionType {   MAXIMUM_NUMBER_OF_ITERATIONS,   COSTFUNCTION_ERROR,   UPDATE_PARAMETERS_ERROR,   STEP_TOO_SMALL,   CONVERGENCE_CHECKER_PASSED,   GRADIENT_MAGNITUDE_TOLEARANCE,   OTHER_ERROR }
typedef ObjectToObjectOptimizerBaseTemplate < TInternalComputationValueType >	Superclass
Public Types inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
typedef SmartPointer< const Self >	ConstPointer
typedef MetricType::DerivativeType	DerivativeType
typedef MetricType::MeasureType	MeasureType
typedef ObjectToObjectMetricBaseTemplate < TInternalComputationValueType >	MetricType
typedef MetricType::Pointer	MetricTypePointer
typedef MetricType::NumberOfParametersType	NumberOfParametersType
typedef OptimizerParameters < TInternalComputationValueType >	ParametersType
typedef SmartPointer< Self >	Pointer
typedef OptimizerParameterScalesEstimatorTemplate < TInternalComputationValueType >	ScalesEstimatorType
typedef OptimizerParameters < TInternalComputationValueType >	ScalesType
typedef ObjectToObjectOptimizerBaseTemplate	Self
typedef std::ostringstream	StopConditionDescriptionType
typedef std::string	StopConditionReturnStringType
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 SizeValueType	GetCurrentIteration () const override
virtual const DerivativeType &	GetGradient () const
virtual const char *	GetNameOfClass () const
virtual SizeValueType	GetNumberOfIterations () const override
virtual const StopConditionType &	GetStopCondition () const
virtual const StopConditionReturnStringType	GetStopConditionDescription () const override
virtual void	ModifyGradientByLearningRateOverSubRange (const IndexRangeType &subrange)=0
virtual void	ModifyGradientByScalesOverSubRange (const IndexRangeType &subrange)=0
virtual void	ResumeOptimization ()=0
virtual void	StartOptimization (bool doOnlyInitialization=false) override
virtual void	StopOptimization ()
virtual void	SetNumberOfIterations (const SizeValueType numberOfIterations) override
virtual void	ModifyGradientByScales ()
virtual void	ModifyGradientByLearningRate ()
Public Member Functions inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
virtual const MeasureType &	GetCurrentMetricValue () const
virtual const ParametersType &	GetCurrentPosition () const
virtual const ThreadIdType &	GetNumberOfThreads () const
virtual const ScalesType &	GetScales () const
virtual const bool &	GetScalesAreIdentity () const
bool	GetScalesInitialized () const
virtual const MeasureType &	GetValue () const
virtual const ScalesType &	GetWeights () const
virtual const bool &	GetWeightsAreIdentity () const
virtual void	SetNumberOfThreads (ThreadIdType number)
virtual void	SetScalesEstimator (ScalesEstimatorType *_arg)
virtual void	SetWeights (ScalesType _arg)
virtual void	SetMetric (MetricType *_arg)
virtual MetricType *	GetModifiableMetric ()
virtual const MetricType *	GetMetric () const
virtual void	SetScales (const ScalesType &scales)
virtual void	SetDoEstimateScales (bool _arg)
virtual const bool &	GetDoEstimateScales () const
virtual void	DoEstimateScalesOn ()
virtual void	DoEstimateScalesOff ()
Public Member Functions inherited from itk::Object
unsigned long	AddObserver (const EventObject &event, Command *)
unsigned long	AddObserver (const EventObject &event, Command *) const
virtual LightObject::Pointer	CreateAnother () const override
virtual void	DebugOff () const
virtual void	DebugOn () const
Command *	GetCommand (unsigned long tag)
bool	GetDebug () const
MetaDataDictionary &	GetMetaDataDictionary ()
const MetaDataDictionary &	GetMetaDataDictionary () 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 override
void	RemoveAllObservers ()
void	RemoveObserver (unsigned long tag)
void	SetDebug (bool debugFlag) const
void	SetMetaDataDictionary (const MetaDataDictionary &rhs)
virtual void	SetReferenceCount (int) override
virtual void	UnRegister () const noexceptoverride
virtual void	SetObjectName (std::string _arg)
virtual const std::string &	GetObjectName () 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

Protected Member Functions
virtual void	PrintSelf (std::ostream &os, Indent indent) const override
	GradientDescentOptimizerBasev4Template ()
virtual	~GradientDescentOptimizerBasev4Template ()
Protected Member Functions inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
	ObjectToObjectOptimizerBaseTemplate ()
virtual	~ObjectToObjectOptimizerBaseTemplate ()
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
ConvergenceMonitoringType::Pointer	m_ConvergenceMonitoring
SizeValueType	m_ConvergenceWindowSize
bool	m_DoEstimateLearningRateAtEachIteration
bool	m_DoEstimateLearningRateOnce
DerivativeType	m_Gradient
TInternalComputationValueType	m_MaximumStepSizeInPhysicalUnits
DomainThreader < ThreadedIndexedContainerPartitioner, Self >::Pointer	m_ModifyGradientByLearningRateThreader
DomainThreader < ThreadedIndexedContainerPartitioner, Self >::Pointer	m_ModifyGradientByScalesThreader
bool	m_Stop
StopConditionType	m_StopCondition
StopConditionDescriptionType	m_StopConditionDescription
bool	m_UseConvergenceMonitoring
Protected Attributes inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
SizeValueType	m_CurrentIteration
MeasureType	m_CurrentMetricValue
bool	m_DoEstimateScales
MetricTypePointer	m_Metric
SizeValueType	m_NumberOfIterations
ThreadIdType	m_NumberOfThreads
ScalesType	m_Scales
bool	m_ScalesAreIdentity
ScalesEstimatorType::Pointer	m_ScalesEstimator
ScalesType	m_Weights
bool	m_WeightsAreIdentity
Protected Attributes inherited from itk::LightObject
AtomicInt< int >	m_ReferenceCount

Private Member Functions
	GradientDescentOptimizerBasev4Template (const Self &)
void	operator= (const Self &)

Additional Inherited Members
Static Public Member Functions inherited from itk::Object
static bool	GetGlobalWarningDisplay ()
static void	GlobalWarningDisplayOff ()
static void	GlobalWarningDisplayOn ()
static Pointer	New ()
static void	SetGlobalWarningDisplay (bool flag)
Static Public Member Functions inherited from itk::LightObject
static void	BreakOnError ()
static Pointer	New ()

Member Typedef Documentation

template<typename TInternalComputationValueType >

typedef SmartPointer< const Self > itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ConstPointer

Definition at line 47 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef itk::Function::WindowConvergenceMonitoringFunction<TInternalComputationValueType> itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ConvergenceMonitoringType

Type for the convergence checker

Definition at line 88 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef Superclass::DerivativeType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::DerivativeType

Derivative type

Definition at line 77 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef ThreadedIndexedContainerPartitioner::IndexRangeType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::IndexRangeType

Definition at line 151 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef TInternalComputationValueType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::InternalComputationValueType

It should be possible to derive the internal computation type from the class object.

Definition at line 70 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef Superclass::MeasureType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::MeasureType

Measure type

Definition at line 80 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef Superclass::MetricType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::MetricType

Metric type over which this class is templated

Definition at line 73 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef MetricType::Pointer itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::MetricTypePointer

Definition at line 74 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef Superclass::ParametersType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ParametersType

Definition at line 84 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef SmartPointer< Self > itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::Pointer

Definition at line 46 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef Superclass::ScalesType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ScalesType

Definition at line 82 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef GradientDescentOptimizerBasev4Template itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::Self

Standard class typedefs.

Definition at line 44 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef Superclass::StopConditionDescriptionType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::StopConditionDescriptionType

Stop condition internal string type

Definition at line 67 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef Superclass::StopConditionReturnStringType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::StopConditionReturnStringType

Stop condition return string type

Definition at line 64 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

typedef ObjectToObjectOptimizerBaseTemplate<TInternalComputationValueType> itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::Superclass

Definition at line 45 of file itkGradientDescentOptimizerBasev4.h.

Member Enumeration Documentation

template<typename TInternalComputationValueType >

enum itk::GradientDescentOptimizerBasev4Template::StopConditionType

Codes of stopping conditions.

Enumerator
MAXIMUM_NUMBER_OF_ITERATIONS
COSTFUNCTION_ERROR
UPDATE_PARAMETERS_ERROR
STEP_TOO_SMALL
CONVERGENCE_CHECKER_PASSED
GRADIENT_MAGNITUDE_TOLEARANCE
OTHER_ERROR

Definition at line 53 of file itkGradientDescentOptimizerBasev4.h.

Constructor & Destructor Documentation

template<typename TInternalComputationValueType >

itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::GradientDescentOptimizerBasev4Template ( )

protected

Default constructor

template<typename TInternalComputationValueType >

virtual itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::~GradientDescentOptimizerBasev4Template ( )

protectedvirtual

Default constructor

template<typename TInternalComputationValueType >

itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::GradientDescentOptimizerBasev4Template ( const Self &  )

private

Member Function Documentation

template<typename TInternalComputationValueType >

virtual SizeValueType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::GetCurrentIteration ( ) const

inlineoverridevirtual

Get the current iteration number.

Reimplemented from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >.

Definition at line 115 of file itkGradientDescentOptimizerBasev4.h.

References itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >::m_CurrentIteration.

template<typename TInternalComputationValueType >

virtual const DerivativeType& itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::GetGradient ( ) const

virtual

Get the most recent gradient values.

template<typename TInternalComputationValueType >

virtual const char* itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::GetNameOfClass ( ) const

virtual

Run-time type information (and related methods).

Reimplemented from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >.

Reimplemented in itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >, itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >, itk::GradientDescentLineSearchOptimizerv4Template< TInternalComputationValueType >, itk::ConjugateGradientLineSearchOptimizerv4Template< TInternalComputationValueType >, itk::MultiGradientOptimizerv4Template< TInternalComputationValueType >, and itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual SizeValueType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::GetNumberOfIterations ( ) const

inlineoverridevirtual

Get the number of iterations.

Reimplemented from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >.

Definition at line 109 of file itkGradientDescentOptimizerBasev4.h.

References itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >::m_NumberOfIterations.

template<typename TInternalComputationValueType >

virtual const StopConditionType& itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::GetStopCondition ( ) const

virtual

Get stop condition enum

Reimplemented in itk::MultiGradientOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual const StopConditionReturnStringType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::GetStopConditionDescription ( ) const

overridevirtual

Get the reason for termination

Implements itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >.

Reimplemented in itk::MultiGradientOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ModifyGradientByLearningRate ( )

virtual

Modify the gradient in place, to advance the optimization. This call performs a threaded modification for transforms with local support (assumed to be dense). Otherwise the modification is performed w/out threading. See EstimateLearningRate() to perform optionaly learning rate estimation. At completion, m_Gradient can be used to update the transform parameters. Derived classes may hold additional results in other member variables.

See Also

EstimateLearningRate()

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ModifyGradientByLearningRateOverSubRange ( const IndexRangeType &  subrange )

pure virtual

Derived classes define this worker method to modify the gradient by learning rates. Modifications must be performed over the index range defined in subrange. Called from ModifyGradientByLearningRate(), either directly or via threaded operation. This function is used in GradientDescentOptimizerBasev4ModifyGradientByScalesThreaderTemplate and GradientDescentOptimizerBasev4ModifyGradientByLearningRateThreaderTemplate classes.

Implemented in itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >, and itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ModifyGradientByScales ( )

virtual

Modify the gradient in place, to advance the optimization. This call performs a threaded modification for transforms with local support (assumed to be dense). Otherwise the modification is performed w/out threading. See EstimateLearningRate() to perform optionaly learning rate estimation. At completion, m_Gradient can be used to update the transform parameters. Derived classes may hold additional results in other member variables.

See Also

EstimateLearningRate()

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ModifyGradientByScalesOverSubRange ( const IndexRangeType &  subrange )

pure virtual

Derived classes define this worker method to modify the gradient by scales. Modifications must be performed over the index range defined in subrange. Called from ModifyGradientByScales(), either directly or via threaded operation.

Implemented in itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >, and itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::operator= ( const Self &  )

private

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::PrintSelf ( std::ostream &  os, Indent  indent  ) const

overrideprotectedvirtual

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::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >.

Reimplemented in itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >, itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >, itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >, itk::MultiGradientOptimizerv4Template< TInternalComputationValueType >, itk::GradientDescentLineSearchOptimizerv4Template< TInternalComputationValueType >, and itk::ConjugateGradientLineSearchOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::ResumeOptimization ( )

pure virtual

Resume optimization. This runs the optimization loop, and allows continuation of stopped optimization

Implemented in itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >, and itk::MultiGradientOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::SetNumberOfIterations ( const SizeValueType  numberOfIterations )

inlineoverridevirtual

Set the number of iterations.

Reimplemented from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >.

Definition at line 97 of file itkGradientDescentOptimizerBasev4.h.

References itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >::m_NumberOfIterations, and itk::Object::Modified().

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::StartOptimization ( bool  doOnlyInitialization = false )

overridevirtual

Start and run the optimization

Reimplemented from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >.

Reimplemented in itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >, itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >, itk::MultiGradientOptimizerv4Template< TInternalComputationValueType >, itk::QuasiNewtonOptimizerv4Template< TInternalComputationValueType >, and itk::ConjugateGradientLineSearchOptimizerv4Template< TInternalComputationValueType >.

template<typename TInternalComputationValueType >

virtual void itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::StopOptimization ( )

virtual

Stop optimization. The object is left in a state so the optimization can be resumed by calling ResumeOptimization.

Reimplemented in itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >, and itk::MultiGradientOptimizerv4Template< TInternalComputationValueType >.

Member Data Documentation

template<typename TInternalComputationValueType >

ConvergenceMonitoringType::Pointer itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_ConvergenceMonitoring

protected

The convergence checker.

Definition at line 208 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

SizeValueType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_ConvergenceWindowSize

protected

Window size for the convergence checker. The convergence checker calculates convergence value by fitting to a window of the energy (metric value) profile.

Definition at line 205 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

bool itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_DoEstimateLearningRateAtEachIteration

protected

Flag to control use of the ScalesEstimator (if set) for automatic learning step estimation at each iteration.

Definition at line 180 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

bool itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_DoEstimateLearningRateOnce

protected

Flag to control use of the ScalesEstimator (if set) for automatic learning step estimation only once, during first iteration.

Definition at line 185 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

DerivativeType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_Gradient

protected

Current gradient

Definition at line 219 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

TInternalComputationValueType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_MaximumStepSizeInPhysicalUnits

protected

The maximum step size in physical units, to restrict learning rates. Only used with automatic learning rate estimation. It may be initialized either by calling SetMaximumStepSizeInPhysicalUnits manually or by using m_ScalesEstimator automatically, and the former has higher priority than the latter. See main documentation.

Definition at line 193 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

DomainThreader<ThreadedIndexedContainerPartitioner, Self>::Pointer itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_ModifyGradientByLearningRateThreader

protected

Definition at line 211 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

DomainThreader<ThreadedIndexedContainerPartitioner, Self>::Pointer itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_ModifyGradientByScalesThreader

protected

Definition at line 210 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

bool itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_Stop

protected

Definition at line 214 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

StopConditionType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_StopCondition

protected

Definition at line 215 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

StopConditionDescriptionType itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_StopConditionDescription

protected

Definition at line 216 of file itkGradientDescentOptimizerBasev4.h.

template<typename TInternalComputationValueType >

bool itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >::m_UseConvergenceMonitoring

protected

Flag to control using the convergence monitoring for stop condition. This flag should be always set to true except for regular step gradient descent optimizer that uses minimum step length to check the convergence.

Definition at line 199 of file itkGradientDescentOptimizerBasev4.h.

---

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

• itkGradientDescentOptimizerBasev4.h