Concatenated edge training class. More...

#include <TrainEdgeConcat.h>

Inheritance diagram for DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >:

Collaboration diagram for DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >:

[legend]

Public Member Functions
	CTrainEdgeConcat (byte nStates, word nFeatures)
	Constructor. More...

template<class TrainerParams >
	CTrainEdgeConcat (byte nStates, word nFeatures, TrainerParams params)
	Constructor. More...

virtual	~CTrainEdgeConcat (void)=default

virtual void	reset (void)
	Resets class variables. More...

void	save (const std::string &path, const std::string &name=std::string(), short idx=-1) const
	Saves the training data. More...

void	load (const std::string &path, const std::string &name=std::string(), short idx=-1)
	Loads the training data. More...

virtual void	addFeatureVecs (const Mat &featureVector1, byte gt1, const Mat &featureVector2, byte gt2)
	Adds a pair of feature vectors. More...

virtual void	train (bool doClean=false)
	Random model training. More...

Public Member Functions inherited from DirectGraphicalModels::CTrainEdge
	CTrainEdge (byte nStates, word nFeatures)
	Constructor. More...

virtual	~CTrainEdge (void)=default

Mat	getEdgePotentials (const Mat &featureVector1, const Mat &featureVector2, const vec_float_t &vParams, float weight=1.0f) const
	Returns the edge potential, based on the feature vectors. More...

Public Member Functions inherited from DirectGraphicalModels::ITrain
	ITrain (byte nStates, word nFeatures)
	Constructor. More...

virtual	~ITrain (void)=default

word	getNumFeatures (void) const
	Returns number of features. More...

Public Member Functions inherited from DirectGraphicalModels::CBaseRandomModel
	CBaseRandomModel (byte nStates)
	Constructor. More...

virtual	~CBaseRandomModel (void)

byte	getNumStates (void) const
	Returns number of states (classes) More...

Protected Member Functions
virtual void	saveFile (FILE *pFile) const
	Saves the random model into the file. More...

virtual void	loadFile (FILE *pFile)
	Loads the random model from the file. More...

virtual Mat	calculateEdgePotentials (const Mat &featureVector1, const Mat &featureVector2, const vec_float_t &vParams) const
	Returns the data-dependent edge potentials. More...

Protected Member Functions inherited from DirectGraphicalModels::CBaseRandomModel
std::string	generateFileName (const std::string &path, const std::string &name, short idx) const
	Generates name of the data file for storing random model parameters. More...

Private Attributes
std::unique_ptr< CPriorNode >	m_pPrior
	Node prior poobability More...

std::unique_ptr< CTrainNode >	m_pTrainer
	Node trainer More...

std::unique_ptr< CFeaturesConcatenator >	m_pConcatenator
	Feature concatenator. More...

Mat	m_featureVector
	Feature vector. More...

Additional Inherited Members
Static Public Member Functions inherited from DirectGraphicalModels::CTrainEdge
static std::shared_ptr< CTrainEdge >	create (byte edgeRandomModel, byte nStates, word nFeatures)
	Factory method returning edge trainer object. More...

static Mat	getDefaultEdgePotentials (float val, byte nStates)
	Returns the data-independent edge potentials. More...

static Mat	getDefaultEdgePotentials (const vec_float_t &values)
	Returns the data-independent edge potentials. More...

Protected Attributes inherited from DirectGraphicalModels::CBaseRandomModel
byte	m_nStates
	The number of states (classes) More...

Detailed Description

template<class Trainer, class Concatenator>
class DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >

Concatenated edge training class.

This class in order to estimate edge potentials, uses an unary potential trainer, which is learned for $nStates^2$ states (classes). Both edge feature vectors are concatenated in one feature vector, which in its turn, is used for the unary potential trainer. The feature concatenation is performed by the CFeaturesConcatenator class.

Template Parameters

Trainer	The nested node potential trainer, derived from the CTrainNode class
Concatenator	The feature concatenator, derived from the CFeaturesConcatenator class

Author: Sergey G. Kosov, serge.nosp@m.y.ko.nosp@m.sov@p.nosp@m.roje.nosp@m.ct-10.nosp@m..de

Definition at line 25 of file TrainEdgeConcat.h.

Constructor & Destructor Documentation

◆ CTrainEdgeConcat() [1/2]

template<class Trainer , class Concatenator >

DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::CTrainEdgeConcat	(	byte	nStates,
		word	nFeatures
	)

inline

Constructor.

Parameters

nStates	Number of states (classes) Must be less then 16
nFeatures	Number of features

Definition at line 34 of file TrainEdgeConcat.h.

◆ CTrainEdgeConcat() [2/2]

template<class Trainer , class Concatenator >

template<class TrainerParams >

DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::CTrainEdgeConcat	(	byte	nStates,
		word	nFeatures,
		TrainerParams	params
	)

inline

Constructor.

Template Parameters

TrainerParams Type of the parameters to the nested node potential trainer

Parameters

nStates	Number of states (classes) Must be less then 16
nFeatures	Number of features
params	Parameters of the nested node potential trainer

Definition at line 52 of file TrainEdgeConcat.h.

◆ ~CTrainEdgeConcat()

template<class Trainer , class Concatenator >

virtual DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::~CTrainEdgeConcat ( void )

virtualdefault

Member Function Documentation

◆ addFeatureVecs()

template<class Trainer , class Concatenator >

virtual void DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::addFeatureVecs	(	const Mat &	featureVector1,
		byte	gt1,
		const Mat &	featureVector2,
		byte	gt2
	)

inlinevirtual

Adds a pair of feature vectors.

Used to add featureVector1 and featureVector2, corresponding to the ground-truth states (classes) gt1 and gt2 for training. Here the couple {featureVector1, gt1} corresponds to the first node of the edge, and the couple {featureVector2, gt2} - to the second node.

Parameters

featureVector1	Multi-dimensinal point: Mat(size: nFeatures x 1; type: CV_8UC1), corresponding to the first node of the edge.
gt1	The ground-truth state (class) of the first node of the edge, given by featureVector1
featureVector2	Multi-dimensinal point: Mat(size: nFeatures x 1; type: CV_8UC1), corresponding to the second node of the edge.
gt2	The ground-truth state (class) of the second node of the edge, given by featureVector2

Implements DirectGraphicalModels::CTrainEdge.

Definition at line 69 of file TrainEdgeConcat.h.

◆ calculateEdgePotentials()

template<class Trainer , class Concatenator >

virtual Mat DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::calculateEdgePotentials	(	const Mat &	featureVector1,
		const Mat &	featureVector2,
		const vec_float_t &	vParams
	)		const

inlineprotectedvirtual

Returns the data-dependent edge potentials.

This function returns edge potential matrix, which elements are obrained from the unary potential vector:

\[ edgePot[nStates][nStates] = nodePot[nStates^2] = f(concat(\textbf{f}_1[nFeatures],\textbf{f}_2[nFeatures])). \]

The resulting edge potential matrix is normalized such that its largest element is equal to paramter $\theta$, and then regularized as follows:

\[ edgePot_{s,s} = \left\{\begin{array}{ll} 1 &\mbox{ if $edgePot_{s,s}<1$} \\ edgePot_{s,s} &\mbox{ otherwise}\end{array} \right.\;\;\;\forall s\in\mathbb{S}.\]

Todo:: : Incorporate the node potential weight into the model parameters

Parameters

featureVector1	Multi-dimensinal point $\textbf{f}_1$: Mat(size: nFeatures x 1; type: CV_8UC1), corresponding to the first node of the edge
featureVector2	Multi-dimensinal point $\textbf{f}_2$: Mat(size: nFeatures x 1; type: CV_8UC1), corresponding to the second node of the edge
vParams	Array of control parameters $\vec{\theta}$, which must consist from one parameter, specifying the largest value in the resulting edge potential.

Returns: The edge potential matrix: Mat(size: nStates x nStates; type: CV_32FC1)

Implements DirectGraphicalModels::CTrainEdge.

Definition at line 94 of file TrainEdgeConcat.h.

◆ load()

template<class Trainer , class Concatenator >

void DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::load	(	const std::string &	path,
		const std::string &	name = `std::string()`,
		short	idx = `-1`
	)

inlinevirtual

Loads the training data.

Allows to re-use the class. Loads data to the file: "<path><name>_<idx>.dat".

Parameters

path	Path to the folder, containing the data file.
name	Name of data file. If empty, will be generated automatically from the class name.
idx	Index of the data file. Negative value means no index.

Reimplemented from DirectGraphicalModels::CBaseRandomModel.

Definition at line 67 of file TrainEdgeConcat.h.

◆ loadFile()

template<class Trainer , class Concatenator >

virtual void DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::loadFile ( FILE * pFile )

inlineprotectedvirtual

Loads the random model from the file.

Allows to re-use the class.

Parameters

pFile Pointer to the file, opened for reading.

Implements DirectGraphicalModels::CBaseRandomModel.

Definition at line 81 of file TrainEdgeConcat.h.

◆ reset()

template<class Trainer , class Concatenator >

virtual void DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::reset ( void )

inlinevirtual

Resets class variables.

Allows to re-use the class.

Implements DirectGraphicalModels::CBaseRandomModel.

Definition at line 65 of file TrainEdgeConcat.h.

◆ save()

template<class Trainer , class Concatenator >

void DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::save	(	const std::string &	path,
		const std::string &	name = `std::string()`,
		short	idx = `-1`
	)		const

inlinevirtual

Saves the training data.

Allows to re-use the class. Stores data to the file: "<path><name>_<idx>.dat".

Parameters

path	Path to the destination folder.
name	Name of data file. If empty, will be generated automatically from the class name.
idx	Index of the destination file. Negative value means no index.

Reimplemented from DirectGraphicalModels::CBaseRandomModel.

Definition at line 66 of file TrainEdgeConcat.h.

◆ saveFile()

template<class Trainer , class Concatenator >

virtual void DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::saveFile ( FILE * pFile ) const

inlineprotectedvirtual

Saves the random model into the file.

Allows to re-use the class.

Parameters

pFile Pointer to the file, opened for writing.

Implements DirectGraphicalModels::CBaseRandomModel.

Definition at line 80 of file TrainEdgeConcat.h.

◆ train()

template<class Trainer , class Concatenator >

virtual void DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::train ( bool doClean = false )

inlinevirtual

Random model training.

Auxilary function for training - some derived classes may use this function inbetween training and classification phases

Note: This function must be called inbetween the training and classification phases

Parameters

doClean Flag indicating if the memory, keeping the trining data should be released after training

Reimplemented from DirectGraphicalModels::CTrainEdge.

Definition at line 76 of file TrainEdgeConcat.h.

Member Data Documentation

◆ m_featureVector

template<class Trainer , class Concatenator >

Mat DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::m_featureVector

private

Feature vector.

Definition at line 121 of file TrainEdgeConcat.h.

◆ m_pConcatenator

template<class Trainer , class Concatenator >

std::unique_ptr<CFeaturesConcatenator> DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::m_pConcatenator

private

Feature concatenator.

Definition at line 120 of file TrainEdgeConcat.h.

◆ m_pPrior

template<class Trainer , class Concatenator >

std::unique_ptr<CPriorNode> DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::m_pPrior

private

Node prior poobability

Definition at line 118 of file TrainEdgeConcat.h.

◆ m_pTrainer

template<class Trainer , class Concatenator >

std::unique_ptr<CTrainNode> DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >::m_pTrainer

private

Node trainer

Definition at line 119 of file TrainEdgeConcat.h.

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

D:/Projects/DGM/modules/DGM/TrainEdgeConcat.h

featureVector1	Multi-dimensinal point \(\textbf{f}_1\): Mat(size: nFeatures x 1; type: CV_8UC1), corresponding to the first node of the edge
featureVector2	Multi-dimensinal point \(\textbf{f}_2\): Mat(size: nFeatures x 1; type: CV_8UC1), corresponding to the second node of the edge
vParams	Array of control parameters \(\vec{\theta}\), which must consist from one parameter, specifying the largest value in the resulting edge potential.

Public Member Functions

Protected Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

template<class Trainer, class Concatenator> class DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >

Constructor & Destructor Documentation

◆ CTrainEdgeConcat() [1/2]

◆ CTrainEdgeConcat() [2/2]

◆ ~CTrainEdgeConcat()

Member Function Documentation

◆ addFeatureVecs()

◆ calculateEdgePotentials()

◆ load()

◆ loadFile()

◆ reset()

◆ save()

◆ saveFile()

◆ train()

Member Data Documentation

◆ m_featureVector

◆ m_pConcatenator

◆ m_pPrior

◆ m_pTrainer

template<class Trainer, class Concatenator>
class DirectGraphicalModels::CTrainEdgeConcat< Trainer, Concatenator >