Main Page   Groups   Namespace List   Class Hierarchy   Alphabetical List   Compound List   File List   Namespace Members   Compound Members   File Members   Concepts
itk::NeuralNetworkFileWriter

itk::NeuralNetworkFileWriter< TNetwork > Class Template Reference

#include <itkNeuralNetworkFileWriter.h>

Inheritance diagram for itk::NeuralNetworkFileWriter< TNetwork >:

Inheritance graph
[legend]
Collaboration diagram for itk::NeuralNetworkFileWriter< TNetwork >:

Collaboration graph
[legend]
List of all members.

Detailed Description

template<class TNetwork>
class itk::NeuralNetworkFileWriter< TNetwork >

Writer for Neural Network.

This class will enable a user to save a trained neural network to a text file. The user can also change the network topology by editing the network configuration file.

This class was contributed to the Insight Journal by Raghu Venkatram The original paper can be found at http://insight-journal.org/midas/handle.php?handle=1926/203

Author:
Raghu Venkatram
See also:
NeuralNetworkFileReader

MultilayerNeuralNetworkBase

IOFilter

Definition at line 66 of file itkNeuralNetworkFileWriter.h.

Public Types

typedef SmartPointer< const
Self > 		ConstPointer
typedef LayerBaseType::ConstPointer LayerBaseConstPointer
typedef LayerBaseType::Pointer LayerBasePointer
typedef Statistics::LayerBase<
MeasurementVectorType, TargetVectorType > 		LayerBaseType
typedef TNetwork::MeasurementVectorType MeasurementVectorType
enum  NetworkWriteWeightsType {
  IGNORE = 0,
  ASCII = 1,
  BINARY = 2
}
typedef SmartPointer< Self > Pointer
typedef NeuralNetworkFileWriter Self
typedef Object Superclass
typedef TNetwork::TargetVectorType TargetVectorType

Public Member Functions

virtual LightObject::Pointer CreateAnother () const
virtual void DebugOff () const
virtual void DebugOn () const
virtual void Delete ()
Command * GetCommand (unsigned long tag)
bool GetDebug () const
virtual const char * GetFileName () const
const MetaDataDictionary & GetMetaDataDictionary (void) const
MetaDataDictionary & GetMetaDataDictionary (void)
virtual unsigned long GetMTime () const
virtual const char * GetNameOfClass () const
virtual int GetReferenceCount () const
bool HasObserver (const EventObject &event) const
void InvokeEvent (const EventObject &) const
void InvokeEvent (const EventObject &)
 itkGetEnumMacro (WriteWeightValuesType, NetworkWriteWeightsType)
 itkSetEnumMacro (WriteWeightValuesType, NetworkWriteWeightsType)
virtual void Modified () const
void Print (std::ostream &os, Indent indent=0) const
virtual void Register () const
void RemoveAllObservers ()
void RemoveObserver (unsigned long tag)
void SetDebug (bool debugFlag) const
virtual void SetFileName (const char *_arg)
void SetMetaDataDictionary (const MetaDataDictionary &rhs)
virtual void SetReferenceCount (int)
virtual void UnRegister () const
void Update (void)
unsigned long AddObserver (const EventObject &event, Command *) const
unsigned long AddObserver (const EventObject &event, Command *)
const TNetwork * GetInput () const
void SetInput (TNetwork *network)

Static Public Member Functions

static void BreakOnError ()
static Pointer New ()
static bool GetGlobalWarningDisplay ()
static void GlobalWarningDisplayOff ()
static void GlobalWarningDisplayOn ()
static void SetGlobalWarningDisplay (bool flag)

Protected Types

typedef int InternalReferenceCountType

Protected Member Functions

 NeuralNetworkFileWriter ()
bool PrintObservers (std::ostream &os, Indent indent) const
virtual void PrintSelf (std::ostream &os, Indent indent) const
 ~NeuralNetworkFileWriter ()
virtual void PrintHeader (std::ostream &os, Indent indent) const
virtual void PrintTrailer (std::ostream &os, Indent indent) const

Protected Attributes

InternalReferenceCountType m_ReferenceCount
SimpleFastMutexLock m_ReferenceCountLock

Member Typedef Documentation

template<class TNetwork>
typedef SmartPointer<const Self> itk::NeuralNetworkFileWriter< TNetwork >::ConstPointer

Reimplemented from itk::Object.

Definition at line 74 of file itkNeuralNetworkFileWriter.h.

typedef int itk::LightObject::InternalReferenceCountType [protected, inherited]

Define the type of the reference count according to the target. This allows the use of atomic operations

Definition at line 139 of file itkLightObject.h.

template<class TNetwork>
typedef LayerBaseType::ConstPointer itk::NeuralNetworkFileWriter< TNetwork >::LayerBaseConstPointer

Definition at line 88 of file itkNeuralNetworkFileWriter.h.

template<class TNetwork>
typedef LayerBaseType::Pointer itk::NeuralNetworkFileWriter< TNetwork >::LayerBasePointer

Definition at line 87 of file itkNeuralNetworkFileWriter.h.

template<class TNetwork>
typedef Statistics::LayerBase< MeasurementVectorType, TargetVectorType > itk::NeuralNetworkFileWriter< TNetwork >::LayerBaseType

Definition at line 86 of file itkNeuralNetworkFileWriter.h.

template<class TNetwork>
typedef TNetwork::MeasurementVectorType itk::NeuralNetworkFileWriter< TNetwork >::MeasurementVectorType

Definition at line 80 of file itkNeuralNetworkFileWriter.h.

template<class TNetwork>
typedef SmartPointer<Self> itk::NeuralNetworkFileWriter< TNetwork >::Pointer

Reimplemented from itk::Object.

Definition at line 73 of file itkNeuralNetworkFileWriter.h.

template<class TNetwork>
typedef NeuralNetworkFileWriter itk::NeuralNetworkFileWriter< TNetwork >::Self

SmartPointer typedef support

Reimplemented from itk::Object.

Definition at line 71 of file itkNeuralNetworkFileWriter.h.

template<class TNetwork>
typedef Object itk::NeuralNetworkFileWriter< TNetwork >::Superclass

Reimplemented from itk::Object.

Definition at line 72 of file itkNeuralNetworkFileWriter.h.

template<class TNetwork>
typedef TNetwork::TargetVectorType itk::NeuralNetworkFileWriter< TNetwork >::TargetVectorType

Definition at line 83 of file itkNeuralNetworkFileWriter.h.

Member Enumeration Documentation

template<class TNetwork>
enum itk::NeuralNetworkFileWriter::NetworkWriteWeightsType

Enumerator:
IGNORE 
ASCII 
BINARY 

Definition at line 129 of file itkNeuralNetworkFileWriter.h.

Constructor & Destructor Documentation

template<class TNetwork>
itk::NeuralNetworkFileWriter< TNetwork >::NeuralNetworkFileWriter (  )  [protected]

template<class TNetwork>
itk::NeuralNetworkFileWriter< TNetwork >::~NeuralNetworkFileWriter (  )  [protected]

Member Function Documentation

unsigned long itk::Object::AddObserver ( const EventObject &  event,
Command *   
) const [inherited]

unsigned long itk::Object::AddObserver ( const EventObject &  event,
Command *   
) [inherited]

Allow people to add/remove/invoke observers (callbacks) to any ITK object. This is an implementation of the subject/observer design pattern. An observer is added by specifying an event to respond to and an itk::Command to execute. It returns an unsigned long tag which can be used later to remove the event or retrieve the command. The memory for the Command becomes the responsibility of this object, so don't pass the same instance of a command to two different objects

static void itk::LightObject::BreakOnError (  )  [static, inherited]

This method is called when itkExceptionMacro executes. It allows the debugger to break on error.

virtual LightObject::Pointer itk::Object::CreateAnother (  )  const [virtual, inherited]

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::LightObject.

virtual void itk::Object::DebugOff (  )  const [virtual, inherited]

Turn debugging output off.

virtual void itk::Object::DebugOn (  )  const [virtual, inherited]

Turn debugging output on.

virtual void itk::LightObject::Delete (  )  [virtual, inherited]

Delete an itk object. This method should always be used to delete an object when the new operator was used to create it. Using the C delete method will not work with reference counting.

Command* itk::Object::GetCommand ( unsigned long  tag  )  [inherited]

Get the command associated with the given tag. NOTE: This returns a pointer to a Command, but it is safe to asign this to a Command::Pointer. Since Command inherits from LightObject, at this point in the code, only a pointer or a reference to the Command can be used.

bool itk::Object::GetDebug (  )  const [inherited]

Get the value of the debug flag.

template<class TNetwork>
virtual const char* itk::NeuralNetworkFileWriter< TNetwork >::GetFileName (  )  const [virtual]

Get the filename

static bool itk::Object::GetGlobalWarningDisplay (  )  [static, inherited]

template<class TNetwork>
const TNetwork* itk::NeuralNetworkFileWriter< TNetwork >::GetInput (  )  const

const MetaDataDictionary& itk::Object::GetMetaDataDictionary ( void   )  const [inherited]

Returns:
A constant reference to this objects MetaDataDictionary.

MetaDataDictionary& itk::Object::GetMetaDataDictionary ( void   )  [inherited]

Returns:
A reference to this objects MetaDataDictionary.
Warning:
This reference may be changed.

virtual unsigned long itk::Object::GetMTime (  )  const [virtual, inherited]

Return this objects modified time.

Reimplemented in itk::ImageRegistrationMethod< TFixedImage, TMovingImage >, itk::ImageToSpatialObjectRegistrationMethod< TFixedImage, TMovingSpatialObject >, itk::MultiResolutionImageRegistrationMethod< TFixedImage, TMovingImage >, itk::PointSetToImageRegistrationMethod< TFixedPointSet, TMovingImage >, itk::PointSetToPointSetRegistrationMethod< TFixedPointSet, TMovingPointSet >, itk::DeformationFieldSource< TOutputImage >, itk::InverseDeformationFieldImageFilter< TInputImage, TOutputImage >, itk::ResampleImageFilter< TInputImage, TOutputImage, TInterpolatorPrecisionType >, itk::VectorResampleImageFilter< TInputImage, TOutputImage, TInterpolatorPrecisionType >, itk::BoundingBox< TPointIdentifier, VPointDimension, TCoordRep, TPointsContainer >, itk::ImageAdaptor< TImage, TAccessor >, itk::ResampleImageFilter< TInputImage, TOutputImage, TInterpolatorPrecisionType >, itk::TransformToDeformationFieldSource< TOutputImage, TTransformPrecisionType >, itk::ImageSpatialObject< TDimension, TPixelType >, itk::MeshSpatialObject< TMesh >, itk::SceneSpatialObject< TSpaceDimension >, itk::SpatialObject< TDimension >, itk::ImageAdaptor< TImage, itk::Accessor::AsinPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::AbsPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::LogPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ComplexToPhasePixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::Log10PixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ExpPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::AddPixelAccessor< TImage::PixelType > >, itk::ImageAdaptor< itk::VectorImage< TPixelType, Dimension >, itk::Accessor::VectorImageToImagePixelAccessor< TPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::RGBToVectorPixelAccessor< TImage::PixelType::ComponentType > >, itk::ImageAdaptor< TImage, itk::PixelAccessor< TInternalType, TExternalType > >, itk::ImageAdaptor< TImage, itk::Accessor::SqrtPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::AcosPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ComplexToModulusPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ExpNegativePixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::VectorToRGBPixelAccessor< TImage::PixelType::ValueType > >, itk::ImageAdaptor< TImage, itk::Accessor::TanPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ComplexToRealPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::RGBToLuminancePixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::AtanPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::SinPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ComplexToImaginaryPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::CosPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageSpatialObject< TDimension, unsigned char >, itk::SpatialObject< 3 >, and itk::SpatialObject< ::itk::GetMeshDimension< TMesh >::PointDimension >.

Referenced by itk::SpatialObject< ::itk::GetMeshDimension< TMesh >::PointDimension >::GetObjectMTime().

template<class TNetwork>
virtual const char* itk::NeuralNetworkFileWriter< TNetwork >::GetNameOfClass (  )  const [virtual]

Run-time type information (and related methods).

Reimplemented from itk::Object.

virtual int itk::LightObject::GetReferenceCount (  )  const [inline, virtual, inherited]

Gets the reference count on this object.

Definition at line 106 of file itkLightObject.h.

static void itk::Object::GlobalWarningDisplayOff (  )  [inline, static, inherited]

Definition at line 100 of file itkObject.h.

References itk::Object::SetGlobalWarningDisplay().

static void itk::Object::GlobalWarningDisplayOn (  )  [inline, static, inherited]

Definition at line 98 of file itkObject.h.

References itk::Object::SetGlobalWarningDisplay().

bool itk::Object::HasObserver ( const EventObject &  event  )  const [inherited]

Return true if an observer is registered for this event.

void itk::Object::InvokeEvent ( const EventObject &   )  const [inherited]

Call Execute on all the Commands observing this event id. The actions triggered by this call doesn't modify this object.

void itk::Object::InvokeEvent ( const EventObject &   )  [inherited]

Call Execute on all the Commands observing this event id.

template<class TNetwork>
itk::NeuralNetworkFileWriter< TNetwork >::itkGetEnumMacro ( WriteWeightValuesType  ,
NetworkWriteWeightsType   
)

template<class TNetwork>
itk::NeuralNetworkFileWriter< TNetwork >::itkSetEnumMacro ( WriteWeightValuesType  ,
NetworkWriteWeightsType   
)

virtual void itk::Object::Modified (  )  const [virtual, inherited]

Update the modification time for this object. Many filters rely on the modification time to determine if they need to recompute their data.

Reimplemented in itk::NormalizeImageFilter< TInputImage, TOutputImage >, itk::ImageAdaptor< TImage, TAccessor >, itk::MiniPipelineSeparableImageFilter< TInputImage, TOutputImage, TFilter >, itk::GrayscaleDilateImageFilter< TInputImage, TOutputImage, TKernel >, itk::GrayscaleErodeImageFilter< TInputImage, TOutputImage, TKernel >, itk::GrayscaleMorphologicalClosingImageFilter< TInputImage, TOutputImage, TKernel >, itk::GrayscaleMorphologicalOpeningImageFilter< TInputImage, TOutputImage, TKernel >, itk::MorphologicalGradientImageFilter< TInputImage, TOutputImage, TKernel >, itk::ImageAdaptor< TImage, itk::Accessor::AsinPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::AbsPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::LogPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ComplexToPhasePixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::Log10PixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ExpPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::AddPixelAccessor< TImage::PixelType > >, itk::ImageAdaptor< itk::VectorImage< TPixelType, Dimension >, itk::Accessor::VectorImageToImagePixelAccessor< TPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::RGBToVectorPixelAccessor< TImage::PixelType::ComponentType > >, itk::ImageAdaptor< TImage, itk::PixelAccessor< TInternalType, TExternalType > >, itk::ImageAdaptor< TImage, itk::Accessor::SqrtPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::AcosPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ComplexToModulusPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ExpNegativePixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::VectorToRGBPixelAccessor< TImage::PixelType::ValueType > >, itk::ImageAdaptor< TImage, itk::Accessor::TanPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ComplexToRealPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::RGBToLuminancePixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::AtanPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::SinPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::ComplexToImaginaryPixelAccessor< TImage::PixelType, TOutputPixelType > >, itk::ImageAdaptor< TImage, itk::Accessor::CosPixelAccessor< TImage::PixelType, TOutputPixelType > >, and itk::MiniPipelineSeparableImageFilter< TInputImage, TOutputImage, itk::RankImageFilter< TInputImage, TInputImage, itk::FlatStructuringElement< ::itk::GetImageDimension< TInputImage >::ImageDimension > > >.

Referenced by itk::NarrowBandImageFilterBase< TInputImage, itk::Image< TOutputPixelType,::itk::GetImageDimension< TInputImage >::ImageDimension > >::InsertNarrowBandNode(), itk::MatrixOffsetTransformBase< TScalarType, 3, 3 >::SetCenter(), itk::HistogramAlgorithmBase< TInputHistogram >::SetInputHistogram(), itk::MatrixOffsetTransformBase< TScalarType, 3, 3 >::SetMatrix(), itk::NarrowBandImageFilterBase< TInputImage, itk::Image< TOutputPixelType,::itk::GetImageDimension< TInputImage >::ImageDimension > >::SetNarrowBand(), itk::NarrowBandImageFilterBase< TInputImage, itk::Image< TOutputPixelType,::itk::GetImageDimension< TInputImage >::ImageDimension > >::SetNarrowBandInnerRadius(), itk::NarrowBandImageFilterBase< TInputImage, itk::Image< TOutputPixelType,::itk::GetImageDimension< TInputImage >::ImageDimension > >::SetNarrowBandTotalRadius(), itk::MatrixOffsetTransformBase< TScalarType, 3, 3 >::SetOffset(), itk::ThresholdLabelerImageFilter< TInputImage, TOutputImage >::SetRealThresholds(), itk::CollidingFrontsImageFilter< TInputImage, TOutputImage >::SetSeedPoints1(), itk::CollidingFrontsImageFilter< TInputImage, TOutputImage >::SetSeedPoints2(), itk::NonUniformBSpline< TDimension >::SetSplineOrder(), itk::ThresholdLabelerImageFilter< TInputImage, TOutputImage >::SetThresholds(), itk::Statistics::GoodnessOfFitFunctionBase< TInputHistogram >::SetTotalObservedScale(), and itk::MatrixOffsetTransformBase< TScalarType, 3, 3 >::SetTranslation().

template<class TNetwork>
static Pointer itk::NeuralNetworkFileWriter< TNetwork >::New (  )  [static]

Method for creation through the object factory

Reimplemented from itk::Object.

void itk::LightObject::Print ( std::ostream &  os,
Indent  indent = 0 
) const [inherited]

Cause the object to print itself out.

Referenced by itk::WeakPointer< itk::ProcessObject >::Print().

virtual void itk::LightObject::PrintHeader ( std::ostream &  os,
Indent  indent 
) const [protected, virtual, inherited]

bool itk::Object::PrintObservers ( std::ostream &  os,
Indent  indent 
) const [protected, inherited]

template<class TNetwork>
virtual void itk::NeuralNetworkFileWriter< TNetwork >::PrintSelf ( std::ostream &  os,
Indent  indent 
) const [protected, virtual]

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::Object.

virtual void itk::LightObject::PrintTrailer ( std::ostream &  os,
Indent  indent 
) const [protected, virtual, inherited]

virtual void itk::Object::Register (  )  const [virtual, inherited]

Increase the reference count (mark as used by another object).

Reimplemented from itk::LightObject.

void itk::Object::RemoveAllObservers (  )  [inherited]

Remove all observers .

void itk::Object::RemoveObserver ( unsigned long  tag  )  [inherited]

Remove the observer with this tag value.

void itk::Object::SetDebug ( bool  debugFlag  )  const [inherited]

Set the value of the debug flag. A non-zero value turns debugging on.

template<class TNetwork>
virtual void itk::NeuralNetworkFileWriter< TNetwork >::SetFileName ( const char *  _arg  )  [virtual]

Set the filename

static void itk::Object::SetGlobalWarningDisplay ( bool  flag  )  [static, inherited]

This is a global flag that controls whether any debug, warning or error messages are displayed.

Referenced by itk::Object::GlobalWarningDisplayOff(), and itk::Object::GlobalWarningDisplayOn().

template<class TNetwork>
void itk::NeuralNetworkFileWriter< TNetwork >::SetInput ( TNetwork *  network  ) 

Set/Get the input transform to write

void itk::Object::SetMetaDataDictionary ( const MetaDataDictionary &  rhs  )  [inherited]

Returns:
Set the MetaDataDictionary

virtual void itk::Object::SetReferenceCount ( int   )  [virtual, inherited]

Sets the reference count (use with care)

Reimplemented from itk::LightObject.

virtual void itk::Object::UnRegister (  )  const [virtual, inherited]

Decrease the reference count (release by another object).

Reimplemented from itk::LightObject.

template<class TNetwork>
void itk::NeuralNetworkFileWriter< TNetwork >::Update ( void   ) 

Read NeuralNetwork

Member Data Documentation

InternalReferenceCountType itk::LightObject::m_ReferenceCount [mutable, protected, inherited]

Number of uses of this object by other objects.

Definition at line 144 of file itkLightObject.h.

SimpleFastMutexLock itk::LightObject::m_ReferenceCountLock [mutable, protected, inherited]

Mutex lock to protect modification to the reference count

Definition at line 147 of file itkLightObject.h.

The documentation for this class was generated from the following file:
Generated at Thu Nov 6 09:11:01 2008 for ITK by doxygen 1.5.1 written by Dimitri van Heesch, © 1997-2000