Bayes training class. More...

#include <TrainNodeNaiveBayes.h>

Inheritance diagram for DirectGraphicalModels::CTrainNodeBayes:

[legend]

Collaboration diagram for DirectGraphicalModels::CTrainNodeBayes:

[legend]

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

virtual	~CTrainNodeBayes (void)

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

virtual void	addFeatureVec (const Mat &featureVector, byte gt)
	Adds new feature vector. More...

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

IPDF *	getPDF (byte state, word feature) const
	Returns the normalized probability density function (PDF) for specific state (class) and feature. More...

IPDF *	getPDF2D (byte state) const
	Returns the 2D normalized probability density function (PDF) for specific state (class) More...

void	smooth (int nIt=1)
	Smothes the underlying Probability Density Functions (PDFs) More...

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

virtual	~CTrainNode (void)=default

void	addFeatureVecs (const Mat &featureVectors, const Mat &gt)
	Adds a block of new feature vectors. More...

void	addFeatureVecs (const vec_mat_t &featureVectors, const Mat &gt)
	Adds a block of new feature vectors. More...

Mat	getNodePotentials (const Mat &featureVectors, const Mat &weights=Mat(), float Z=0.0f) const
	Returns a block of node potentials, based on the block of feature vector. More...

Mat	getNodePotentials (const vec_mat_t &featureVectors, const Mat &weights=Mat(), float Z=0.0f) const
	Returns a block of node potentials, based on the block of feature vector. More...

Mat	getNodePotentials (const Mat &featureVector, float weight, float Z=0.0f) const
	Returns the node potential, based on the feature vector. 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)

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

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

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...

void	calculateNodePotentials (const Mat &featureVector, Mat &potential, Mat &mask) const
	Calculates the node potential, based on the feature vector. 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
IPDF ***	m_pPDF
	The 1D PDF for node potentials [state][feature]. More...

IPDF **	m_pPDF2D
	The 2D data histogram for node potentials and 2 features[state]. More...

Mat	m_prior
	The class prior probability vector. More...

Private Attributes inherited from DirectGraphicalModels::CPrior
Mat	m_histogramPrior
	The class cooccurance histogram. More...

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

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

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

Private Member Functions inherited from DirectGraphicalModels::CPriorNode
	CPriorNode (byte nStates)
	Constructor. More...

	~CPriorNode (void)

void	addNodeGroundTruth (const Mat &gt)
	Adds ground truth values to the co-occurance histogram vector. More...

void	addNodeGroundTruth (byte gt)
	Adds a ground truth value to the co-occurance histogram vector. More...

Mat	calculatePrior (void) const
	Calculates the prior probabilies. More...

Private Member Functions inherited from DirectGraphicalModels::CPrior
	CPrior (byte nStates, RandomModelType type)
	Constructor. More...

	~CPrior (void)

Mat	getPrior (float weight=1.0f) const
	Returns the prior probabilies. More...

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

virtual	~CBaseRandomModel (void)

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

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

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

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...

Detailed Description

Bayes training class.

This class implements the naive Bayes classifier, which is based on strong (naive) independence assumptions between the features.

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 20 of file TrainNodeNaiveBayes.h.

Constructor & Destructor Documentation

◆ CTrainNodeBayes()

DirectGraphicalModels::CTrainNodeBayes::CTrainNodeBayes	(	byte	nStates,
		word	nFeatures
	)

Constructor.

Parameters

nStates	Number of states (classes)
nFeatures	Number of features

Definition at line 10 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

◆ ~CTrainNodeBayes()

DirectGraphicalModels::CTrainNodeBayes::~CTrainNodeBayes ( void )

virtual

Definition at line 32 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

Member Function Documentation

◆ addFeatureVec()

void DirectGraphicalModels::CTrainNodeBayes::addFeatureVec	(	const Mat &	featureVector,
		byte	gt
	)

virtual

Adds new feature vector.

Used to add a featureVector, corresponding to the ground-truth state (class) gt for training

Parameters

featureVector	Multi-dimensinal point: Mat(size: nFeatures x 1; type: CV_8UC1)
gt	Corresponding ground-truth state (class)

Implements DirectGraphicalModels::CTrainNode.

Definition at line 63 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

◆ calculateNodePotentials()

void DirectGraphicalModels::CTrainNodeBayes::calculateNodePotentials	(	const Mat &	featureVector,
		Mat &	potential,
		Mat &	mask
	)		const

protectedvirtual

Calculates the node potential, based on the feature vector.

This function calculates the potentials of the node, described with the sample featureVector ( \( \textbf{f} \)):

\[ nodePot_s = prior_s\cdot\prod_{f\in\mathbb{F}} (H_{s,f}.data[\textbf{f}_f] / H_{s,f}.n); \forall s\in\mathbb{S}, \]

where \(\mathbb{S}\) and \(\mathbb{F}\) are sets of all states (classes) and features correspondently. In other words, the indexes: \( s \in [0; nStates) \) and \( f \in [0; nFeatures) \). Here \( H.data[256] \) is a 1D histogram, \( H.n \) is the number of entries in histogram, i.e. \( H.n = \sum^{255}_{i = 0} H.data[i] \). And \( \textbf{f}_f \in [0; 255], \forall f \in [0; nFeatures) \), i.e. has (type: CV_8UC1).

Parameters

[in]	featureVector	Multi-dimensinal point \(\textbf{f}\): Mat(size: nFeatures x 1; type: CV_{XX}C1)
[in,out]	potential	Node potentials: Mat(size: nStates x 1; type: CV_32FC1). This parameter should be preinitialized and set to value 0.
[in,out]	mask	Relevant Node potentials: Mat(size: nStates x 1; type: CV_8UC1). This parameter should be preinitialized and set to value 1 (all potentials are relevant).

Implements DirectGraphicalModels::CTrainNode.

Definition at line 125 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

◆ getPDF()

IPDF* DirectGraphicalModels::CTrainNodeBayes::getPDF	(	byte	state,
		word	feature
	)		const

inline

Returns the normalized probability density function (PDF) for specific state (class) and feature.

Parameters

state	The state (class)
feature	The feature

Returns: The probability density function

Definition at line 42 of file TrainNodeNaiveBayes.h.

◆ getPDF2D()

IPDF* DirectGraphicalModels::CTrainNodeBayes::getPDF2D ( byte state ) const

inline

Returns the 2D normalized probability density function (PDF) for specific state (class)

Note: Used for test purposes. Use this function when only 2 features are in use.

Parameters

state The state (class)

Returns: The probability density function for 2 features

Definition at line 49 of file TrainNodeNaiveBayes.h.

◆ loadFile()

void DirectGraphicalModels::CTrainNodeBayes::loadFile ( FILE * pFile )

protectedvirtual

Loads the random model from the file.

Allows to re-use the class.

Parameters

pFile Pointer to the file, opened for reading.

Reimplemented from DirectGraphicalModels::CPrior.

Definition at line 112 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

◆ reset()

void DirectGraphicalModels::CTrainNodeBayes::reset ( void )

virtual

Resets class variables.

Allows to re-use the class.

Reimplemented from DirectGraphicalModels::CPrior.

Definition at line 49 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

◆ saveFile()

void DirectGraphicalModels::CTrainNodeBayes::saveFile ( FILE * pFile ) const

protectedvirtual

Saves the random model into the file.

Allows to re-use the class.

Parameters

pFile Pointer to the file, opened for writing.

Reimplemented from DirectGraphicalModels::CPrior.

Definition at line 100 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

◆ smooth()

void DirectGraphicalModels::CTrainNodeBayes::smooth ( int nIt = 1 )

Smothes the underlying Probability Density Functions (PDFs)

Parameters

nIt	Number of smooth iterations

Definition at line 89 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

◆ train()

void DirectGraphicalModels::CTrainNodeBayes::train ( bool doClean = false )

virtual

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::CTrainNode.

Definition at line 84 of file TrainNodeNaiveBayes.cpp.

Here is the call graph for this function:

Member Data Documentation

◆ m_pPDF

IPDF*** DirectGraphicalModels::CTrainNodeBayes::m_pPDF

private

The 1D PDF for node potentials [state][feature].

Definition at line 75 of file TrainNodeNaiveBayes.h.

◆ m_pPDF2D

IPDF** DirectGraphicalModels::CTrainNodeBayes::m_pPDF2D

private

The 2D data histogram for node potentials and 2 features[state].

Definition at line 76 of file TrainNodeNaiveBayes.h.

◆ m_prior

Mat DirectGraphicalModels::CTrainNodeBayes::m_prior

private

The class prior probability vector.

Definition at line 77 of file TrainNodeNaiveBayes.h.

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

D:/Projects/DGM/modules/DGM/TrainNodeNaiveBayes.h
D:/Projects/DGM/modules/DGM/TrainNodeNaiveBayes.cpp

Public Member Functions

Protected Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ CTrainNodeBayes()

◆ ~CTrainNodeBayes()

Member Function Documentation

◆ addFeatureVec()

◆ calculateNodePotentials()

◆ getPDF()

◆ getPDF2D()

◆ loadFile()

◆ reset()

◆ saveFile()

◆ smooth()

◆ train()

Member Data Documentation

◆ m_pPDF

◆ m_pPDF2D

◆ m_prior