ITK  5.2.0
Insight Toolkit
Public Types | Public Member Functions | Static Public Member Functions | List of all members
itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType > Class Template Reference

#include <itkRegularStepGradientDescentOptimizerv4.h>

+ Inheritance diagram for itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >:
+ Collaboration diagram for itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >:

Public Types

using CompensatedSummationType = CompensatedSummation< InternalComputationValueType >
 
using ConstPointer = SmartPointer< const Self >
 
using DerivativeType = typename Superclass::DerivativeType
 
using IndexRangeType = typename Superclass::IndexRangeType
 
using InternalComputationValueType = TInternalComputationValueType
 
using MeasureType = typename Superclass::MeasureType
 
using ParametersType = typename Superclass::ParametersType
 
using Pointer = SmartPointer< Self >
 
using ScalesType = typename Superclass::ScalesType
 
using Self = RegularStepGradientDescentOptimizerv4
 
using Superclass = GradientDescentOptimizerv4Template< TInternalComputationValueType >
 
- Public Types inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
using ConstPointer = SmartPointer< const Self >
 
using DerivativeType = typename Superclass::DerivativeType
 
using IndexRangeType = typename Superclass::IndexRangeType
 
using InternalComputationValueType = TInternalComputationValueType
 
using MeasureType = typename Superclass::MeasureType
 
using ParametersType = typename Superclass::ParametersType
 
using Pointer = SmartPointer< Self >
 
using ScalesType = typename Superclass::ScalesType
 
using Self = GradientDescentOptimizerv4Template
 
using Superclass = GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
 
- Public Types inherited from itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
using ConstPointer = SmartPointer< const Self >
 
using ConvergenceMonitoringType = itk::Function::WindowConvergenceMonitoringFunction< TInternalComputationValueType >
 
using DerivativeType = typename Superclass::DerivativeType
 
using InternalComputationValueType = TInternalComputationValueType
 
using MeasureType = typename Superclass::MeasureType
 
using MetricType = typename Superclass::MetricType
 
using MetricTypePointer = typename MetricType::Pointer
 
using ParametersType = typename Superclass::ParametersType
 
using Pointer = SmartPointer< Self >
 
using ScalesType = typename Superclass::ScalesType
 
using Self = GradientDescentOptimizerBasev4Template
 
using StopConditionDescriptionType = typename Superclass::StopConditionDescriptionType
 
using StopConditionReturnStringType = typename Superclass::StopConditionReturnStringType
 
using Superclass = ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
 
using IndexRangeType = ThreadedIndexedContainerPartitioner::IndexRangeType
 
- Public Types inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
using ConstPointer = SmartPointer< const Self >
 
using DerivativeType = typename MetricType::DerivativeType
 
using MeasureType = typename MetricType::MeasureType
 
using MetricType = ObjectToObjectMetricBaseTemplate< TInternalComputationValueType >
 
using MetricTypePointer = typename MetricType::Pointer
 
using NumberOfParametersType = typename MetricType::NumberOfParametersType
 
using ParametersType = OptimizerParameters< TInternalComputationValueType >
 
using Pointer = SmartPointer< Self >
 
using ScalesEstimatorType = OptimizerParameterScalesEstimatorTemplate< TInternalComputationValueType >
 
using ScalesType = OptimizerParameters< TInternalComputationValueType >
 
using Self = ObjectToObjectOptimizerBaseTemplate
 
using StopConditionDescriptionType = std::ostringstream
 
using StopConditionReturnStringType = std::string
 
using Superclass = Object
 
- Public Types inherited from itk::Object
using ConstPointer = SmartPointer< const Self >
 
using Pointer = SmartPointer< Self >
 
using Self = Object
 
using Superclass = LightObject
 
- Public Types inherited from itk::LightObject
using ConstPointer = SmartPointer< const Self >
 
using Pointer = SmartPointer< Self >
 
using Self = LightObject
 

Public Member Functions

virtual ::itk::LightObject::Pointer CreateAnother () const
 
virtual const char * GetNameOfClass () const
 
- Public Member Functions inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
virtual void SetLearningRate (TInternalComputationValueType _arg)
 
virtual const TInternalComputationValueType & GetLearningRate () const
 
virtual void SetMaximumStepSizeInPhysicalUnits (TInternalComputationValueType _arg)
 
virtual const TInternalComputationValueType & GetMaximumStepSizeInPhysicalUnits () const
 
virtual void SetDoEstimateLearningRateAtEachIteration (bool _arg)
 
virtual const bool & GetDoEstimateLearningRateAtEachIteration () const
 
virtual void DoEstimateLearningRateAtEachIterationOn ()
 
virtual void DoEstimateLearningRateAtEachIterationOff ()
 
virtual void SetDoEstimateLearningRateOnce (bool _arg)
 
virtual const bool & GetDoEstimateLearningRateOnce () const
 
virtual void DoEstimateLearningRateOnceOn ()
 
virtual void DoEstimateLearningRateOnceOff ()
 
virtual void SetMinimumConvergenceValue (TInternalComputationValueType _arg)
 
virtual void SetConvergenceWindowSize (SizeValueType _arg)
 
virtual const TInternalComputationValueType & GetConvergenceValue () const
 
virtual void SetReturnBestParametersAndValue (bool _arg)
 
virtual const bool & GetReturnBestParametersAndValue () const
 
virtual void ReturnBestParametersAndValueOn ()
 
virtual void ReturnBestParametersAndValueOff ()
 
void StopOptimization () override
 
void ResumeOptimization () override
 
- Public Member Functions inherited from itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
virtual const DerivativeTypeGetGradient () const
 
virtual const StopConditionObjectToObjectOptimizerEnumGetStopCondition () const
 
void SetNumberOfIterations (const SizeValueType numberOfIterations) override
 
SizeValueType GetNumberOfIterations () const override
 
SizeValueType GetCurrentIteration () const override
 
const StopConditionReturnStringType GetStopConditionDescription () const override
 
virtual void ModifyGradientByScales ()
 
virtual void ModifyGradientByLearningRate ()
 
- Public Member Functions inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
virtual void SetMetric (MetricType *_arg)
 
virtual MetricTypeGetModifiableMetric ()
 
virtual const MetricTypeGetMetric () const
 
virtual const MeasureTypeGetCurrentMetricValue () const
 
virtual const MeasureTypeGetValue () const
 
virtual void SetScales (const ScalesType &scales)
 
virtual const ScalesTypeGetScales () const
 
virtual const bool & GetScalesAreIdentity () const
 
virtual void SetWeights (ScalesType _arg)
 
virtual const ScalesTypeGetWeights () const
 
virtual const bool & GetWeightsAreIdentity () const
 
bool GetScalesInitialized () const
 
virtual void SetScalesEstimator (ScalesEstimatorType *_arg)
 
virtual void SetDoEstimateScales (bool _arg)
 
virtual const bool & GetDoEstimateScales () const
 
virtual void DoEstimateScalesOn ()
 
virtual void DoEstimateScalesOff ()
 
virtual void SetNumberOfWorkUnits (ThreadIdType number)
 
virtual const ThreadIdTypeGetNumberOfWorkUnits () const
 
virtual const ParametersTypeGetCurrentPosition () const
 
- Public Member Functions inherited from itk::Object
unsigned long AddObserver (const EventObject &event, Command *)
 
unsigned long AddObserver (const EventObject &event, Command *) const
 
unsigned long AddObserver (const EventObject &event, std::function< void(const EventObject &)> function) const
 
virtual void DebugOff () const
 
virtual void DebugOn () const
 
CommandGetCommand (unsigned long tag)
 
bool GetDebug () const
 
MetaDataDictionaryGetMetaDataDictionary ()
 
const MetaDataDictionaryGetMetaDataDictionary () const
 
virtual ModifiedTimeType GetMTime () const
 
virtual const TimeStampGetTimeStamp () const
 
bool HasObserver (const EventObject &event) const
 
void InvokeEvent (const EventObject &)
 
void InvokeEvent (const EventObject &) const
 
virtual void Modified () const
 
void Register () const override
 
void RemoveAllObservers ()
 
void RemoveObserver (unsigned long tag)
 
void SetDebug (bool debugFlag) const
 
void SetReferenceCount (int) override
 
void UnRegister () const noexcept override
 
void SetMetaDataDictionary (const MetaDataDictionary &rhs)
 
void SetMetaDataDictionary (MetaDataDictionary &&rrhs)
 
virtual void SetObjectName (std::string _arg)
 
virtual const std::string & GetObjectName () const
 
- Public Member Functions inherited from itk::LightObject
Pointer Clone () const
 
virtual void Delete ()
 
virtual int GetReferenceCount () const
 
void Print (std::ostream &os, Indent indent=0) const
 

Static Public Member Functions

static Pointer New ()
 
- Static Public Member Functions inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
static Pointer New ()
 
- Static Public Member Functions inherited from itk::Object
static bool GetGlobalWarningDisplay ()
 
static void GlobalWarningDisplayOff ()
 
static void GlobalWarningDisplayOn ()
 
static Pointer New ()
 
static void SetGlobalWarningDisplay (bool val)
 
- Static Public Member Functions inherited from itk::LightObject
static void BreakOnError ()
 
static Pointer New ()
 
TInternalComputationValueType m_RelaxationFactor
 
TInternalComputationValueType m_MinimumStepLength
 
TInternalComputationValueType m_GradientMagnitudeTolerance
 
MeasureType m_CurrentLearningRateRelaxation
 
virtual void SetMinimumStepLength (TInternalComputationValueType _arg)
 
virtual const TInternalComputationValueType & GetMinimumStepLength () const
 
virtual void SetRelaxationFactor (TInternalComputationValueType _arg)
 
virtual const TInternalComputationValueType & GetRelaxationFactor () const
 
virtual void SetGradientMagnitudeTolerance (TInternalComputationValueType _arg)
 
virtual const TInternalComputationValueType & GetGradientMagnitudeTolerance () const
 
virtual void SetCurrentLearningRateRelaxation (MeasureType _arg)
 
virtual const MeasureTypeGetCurrentLearningRateRelaxation () const
 
void StartOptimization (bool doOnlyInitialization=false) override
 
void EstimateLearningRate () override
 
double GetCurrentStepLength () const
 
void AdvanceOneStep () override
 
void ModifyGradientByScalesOverSubRange (const IndexRangeType &subrange) override
 
void ModifyGradientByLearningRateOverSubRange (const IndexRangeType &subrange) override
 
 RegularStepGradientDescentOptimizerv4 ()
 
 ~RegularStepGradientDescentOptimizerv4 () override=default
 
void PrintSelf (std::ostream &os, Indent indent) const override
 

Additional Inherited Members

- Protected Member Functions inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
 GradientDescentOptimizerv4Template ()
 
 ~GradientDescentOptimizerv4Template () override=default
 
- Protected Member Functions inherited from itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
 GradientDescentOptimizerBasev4Template ()
 
 ~GradientDescentOptimizerBasev4Template () override=default
 
- Protected Member Functions inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
 ObjectToObjectOptimizerBaseTemplate ()
 
 ~ObjectToObjectOptimizerBaseTemplate () override
 
- Protected Member Functions inherited from itk::Object
 Object ()
 
 ~Object () override
 
bool PrintObservers (std::ostream &os, Indent indent) const
 
virtual void SetTimeStamp (const TimeStamp &timeStamp)
 
- 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 inherited from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >
TInternalComputationValueType m_LearningRate
 
TInternalComputationValueType m_MinimumConvergenceValue
 
TInternalComputationValueType m_ConvergenceValue
 
MeasureType m_CurrentBestValue
 
ParametersType m_BestParameters
 
bool m_ReturnBestParametersAndValue { false }
 
DerivativeType m_PreviousGradient
 
- Protected Attributes inherited from itk::GradientDescentOptimizerBasev4Template< TInternalComputationValueType >
bool m_DoEstimateLearningRateAtEachIteration
 
bool m_DoEstimateLearningRateOnce
 
TInternalComputationValueType m_MaximumStepSizeInPhysicalUnits
 
bool m_UseConvergenceMonitoring
 
SizeValueType m_ConvergenceWindowSize
 
ConvergenceMonitoringType::Pointer m_ConvergenceMonitoring
 
DomainThreader< ThreadedIndexedContainerPartitioner, Self >::Pointer m_ModifyGradientByScalesThreader
 
DomainThreader< ThreadedIndexedContainerPartitioner, Self >::Pointer m_ModifyGradientByLearningRateThreader
 
bool m_Stop { false }
 
StopConditionObjectToObjectOptimizerEnum m_StopCondition
 
StopConditionDescriptionType m_StopConditionDescription
 
DerivativeType m_Gradient
 
- Protected Attributes inherited from itk::ObjectToObjectOptimizerBaseTemplate< TInternalComputationValueType >
MetricTypePointer m_Metric
 
ThreadIdType m_NumberOfWorkUnits
 
SizeValueType m_CurrentIteration
 
SizeValueType m_NumberOfIterations
 
MeasureType m_CurrentMetricValue
 
ScalesType m_Scales
 
ScalesType m_Weights
 
bool m_ScalesAreIdentity
 
ScalesEstimatorType::Pointer m_ScalesEstimator
 
bool m_WeightsAreIdentity
 
bool m_DoEstimateScales
 
- Protected Attributes inherited from itk::LightObject
std::atomic< int > m_ReferenceCount
 

Detailed Description

template<typename TInternalComputationValueType = double>
class itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >

Regular Step Gradient descent optimizer.

This optimizer is a variant of gradient descent that attempts to prevent it from taking steps that are too large. At each iteration, this optimizer will take a step along the direction of the metric derivative. Each time the direction of the derivative abruptly changes, the optimizer assumes that a local extrema has been passed and reacts by reducing the step length by a relaxation factor that is set to 0.5 by default. The default value for the initial step length is 1, and this value can only be changed manually via SetLearningRate() since this optimizer does not use the ScaleEstimator to automatically estimate the learning rate. Also note that unlike the previous version of ReuglarStepGradientDescentOptimizer, ITKv4 does not have a "maximize/minimize" option to modify the effect of the metric derivative. The assigned metric is assumed to return a parameter derivative result that "improves" the optimization.

Examples
Examples/RegistrationITKv4/ImageRegistration1.cxx, Examples/RegistrationITKv4/ImageRegistration12.cxx, Examples/RegistrationITKv4/ImageRegistration13.cxx, Examples/RegistrationITKv4/ImageRegistration3.cxx, Examples/RegistrationITKv4/ImageRegistration4.cxx, Examples/RegistrationITKv4/ImageRegistration5.cxx, Examples/RegistrationITKv4/ImageRegistration6.cxx, Examples/RegistrationITKv4/ImageRegistration7.cxx, Examples/RegistrationITKv4/ImageRegistration8.cxx, Examples/RegistrationITKv4/ImageRegistration9.cxx, Examples/RegistrationITKv4/MultiResImageRegistration1.cxx, Examples/RegistrationITKv4/MultiStageImageRegistration1.cxx, Examples/RegistrationITKv4/MultiStageImageRegistration2.cxx, and SphinxExamples/src/Registration/Common/Perform2DTranslationRegistrationWithMeanSquares/Code.cxx.

Definition at line 47 of file itkRegularStepGradientDescentOptimizerv4.h.

Member Typedef Documentation

◆ CompensatedSummationType

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::CompensatedSummationType = CompensatedSummation<InternalComputationValueType>

Compensated summation type.

Definition at line 79 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ ConstPointer

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::ConstPointer = SmartPointer<const Self>

Definition at line 57 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ DerivativeType

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::DerivativeType = typename Superclass::DerivativeType

Derivative type.

Definition at line 70 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ IndexRangeType

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::IndexRangeType = typename Superclass::IndexRangeType

Definition at line 74 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ InternalComputationValueType

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::InternalComputationValueType = TInternalComputationValueType

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

Definition at line 67 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ MeasureType

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::MeasureType = typename Superclass::MeasureType

Metric type over which this class is templated.

Definition at line 73 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ ParametersType

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::ParametersType = typename Superclass::ParametersType

Definition at line 76 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ Pointer

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::Pointer = SmartPointer<Self>

Definition at line 56 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ ScalesType

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::ScalesType = typename Superclass::ScalesType

Definition at line 75 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ Self

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::Self = RegularStepGradientDescentOptimizerv4

Standard class type aliases.

Definition at line 54 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ Superclass

template<typename TInternalComputationValueType = double>
using itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::Superclass = GradientDescentOptimizerv4Template<TInternalComputationValueType>

Definition at line 55 of file itkRegularStepGradientDescentOptimizerv4.h.

Constructor & Destructor Documentation

◆ RegularStepGradientDescentOptimizerv4()

template<typename TInternalComputationValueType = double>
itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::RegularStepGradientDescentOptimizerv4 ( )
protected

Default constructor.

◆ ~RegularStepGradientDescentOptimizerv4()

template<typename TInternalComputationValueType = double>
itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::~RegularStepGradientDescentOptimizerv4 ( )
overrideprotecteddefault

Destructor.

Member Function Documentation

◆ AdvanceOneStep()

template<typename TInternalComputationValueType = double>
void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::AdvanceOneStep ( )
overrideprotectedvirtual

Advance one Step following the gradient direction. Includes transform update.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

◆ CreateAnother()

template<typename TInternalComputationValueType = double>
virtual::itk::LightObject::Pointer itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::CreateAnother ( ) 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::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

◆ EstimateLearningRate()

template<typename TInternalComputationValueType = double>
void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::EstimateLearningRate ( )
overridevirtual

Estimate the learning rate based on the current gradient.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

◆ GetCurrentLearningRateRelaxation()

template<typename TInternalComputationValueType = double>
virtual const MeasureType& itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::GetCurrentLearningRateRelaxation ( ) const
virtual

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

◆ GetCurrentStepLength()

template<typename TInternalComputationValueType = double>
double itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::GetCurrentStepLength ( ) const

Get current gradient step value.

◆ GetGradientMagnitudeTolerance()

template<typename TInternalComputationValueType = double>
virtual const TInternalComputationValueType& itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::GetGradientMagnitudeTolerance ( ) const
virtual

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

◆ GetMinimumStepLength()

template<typename TInternalComputationValueType = double>
virtual const TInternalComputationValueType& itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::GetMinimumStepLength ( ) const
virtual

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

◆ GetNameOfClass()

template<typename TInternalComputationValueType = double>
virtual const char* itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::GetNameOfClass ( ) const
virtual

Run-time type information (and related methods).

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

◆ GetRelaxationFactor()

template<typename TInternalComputationValueType = double>
virtual const TInternalComputationValueType& itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::GetRelaxationFactor ( ) const
virtual

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

◆ ModifyGradientByLearningRateOverSubRange()

template<typename TInternalComputationValueType = double>
void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::ModifyGradientByLearningRateOverSubRange ( const IndexRangeType subrange)
overrideprotectedvirtual

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

◆ ModifyGradientByScalesOverSubRange()

template<typename TInternalComputationValueType = double>
void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::ModifyGradientByScalesOverSubRange ( const IndexRangeType subrange)
overrideprotectedvirtual

Modify the input gradient over a given index range.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

◆ New()

template<typename TInternalComputationValueType = double>
static Pointer itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::New ( )
static

New macro for creation of through a Smart Pointer.

◆ PrintSelf()

template<typename TInternalComputationValueType = double>
void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::PrintSelf ( std::ostream &  os,
Indent  indent 
) const
overrideprotectedvirtual

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

◆ SetCurrentLearningRateRelaxation()

template<typename TInternalComputationValueType = double>
virtual void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::SetCurrentLearningRateRelaxation ( MeasureType  _arg)
virtual

Set/Get current scale for learning rate.

◆ SetGradientMagnitudeTolerance()

template<typename TInternalComputationValueType = double>
virtual void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::SetGradientMagnitudeTolerance ( TInternalComputationValueType  _arg)
virtual

Set/Get gradient magnitude tolerance value for convergence checking.

◆ SetMinimumStepLength()

template<typename TInternalComputationValueType = double>
virtual void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::SetMinimumStepLength ( TInternalComputationValueType  _arg)
virtual

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

◆ SetRelaxationFactor()

template<typename TInternalComputationValueType = double>
virtual void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::SetRelaxationFactor ( TInternalComputationValueType  _arg)
virtual

Set/Get relaxation factor value.

◆ StartOptimization()

template<typename TInternalComputationValueType = double>
void itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::StartOptimization ( bool  doOnlyInitialization = false)
overridevirtual

Start and run the optimization.

Reimplemented from itk::GradientDescentOptimizerv4Template< TInternalComputationValueType >.

Member Data Documentation

◆ m_CurrentLearningRateRelaxation

template<typename TInternalComputationValueType = double>
MeasureType itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::m_CurrentLearningRateRelaxation
private

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

Definition at line 152 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ m_GradientMagnitudeTolerance

template<typename TInternalComputationValueType = double>
TInternalComputationValueType itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::m_GradientMagnitudeTolerance
private

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

Definition at line 150 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ m_MinimumStepLength

template<typename TInternalComputationValueType = double>
TInternalComputationValueType itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::m_MinimumStepLength
private

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

Definition at line 148 of file itkRegularStepGradientDescentOptimizerv4.h.

◆ m_RelaxationFactor

template<typename TInternalComputationValueType = double>
TInternalComputationValueType itk::RegularStepGradientDescentOptimizerv4< TInternalComputationValueType >::m_RelaxationFactor
private

Minimum step length (learning rate) value for convergence checking. When the local minima is passed by taking a large step, the step length is adjusted (decreased) by the relaxation factor, so that smaller steps are taken towards the minimum point (convergence). When the step length value reaches a small value, it would be treated as converged.

The default value is set to 1e-4 to pass all tests.

Definition at line 146 of file itkRegularStepGradientDescentOptimizerv4.h.


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