Direct Graphical Models  v.1.7.0
DirectGraphicalModels::TrainNodeGMMParams Struct Reference

Gaussian Mixture Model parameters. More...

#include <TrainNodeGMM.h>

Public Member Functions

 TrainNodeGMMParams ()
 
 TrainNodeGMMParams (word _maxGausses, size_t _minSamples, double _dist_Etreshold, double _dist_Mtreshold, double _div_KLtreshold)
 

Public Attributes

word maxGausses
 The maximal number of Gauss functions for approximation. More...
 
size_t minSamples
 Minimum number of sapmles to approximate a Gauss function. More...
 
double dist_Etreshold
 Minimum Euclidean distance between Gauss functions. More...
 
double dist_Mtreshold
 Minimum Mahalanobis distance between Gauss functions. If this parameter is negative, the Euclidean distance is used. More...
 
double div_KLtreshold
 Minimum Kullback-Leiber divergence between Gauss functions. If this parameter is negative, the merging of Gaussians in addFeatureVec() function will be disabled. More...
 

Detailed Description

Gaussian Mixture Model parameters.

Definition at line 12 of file TrainNodeGMM.h.

Constructor & Destructor Documentation

◆ TrainNodeGMMParams() [1/2]

DirectGraphicalModels::TrainNodeGMMParams::TrainNodeGMMParams ( )
inline

Definition at line 19 of file TrainNodeGMM.h.

◆ TrainNodeGMMParams() [2/2]

DirectGraphicalModels::TrainNodeGMMParams::TrainNodeGMMParams ( word  _maxGausses,
size_t  _minSamples,
double  _dist_Etreshold,
double  _dist_Mtreshold,
double  _div_KLtreshold 
)
inline

Definition at line 20 of file TrainNodeGMM.h.

Member Data Documentation

◆ dist_Etreshold

double DirectGraphicalModels::TrainNodeGMMParams::dist_Etreshold

Minimum Euclidean distance between Gauss functions.

Definition at line 15 of file TrainNodeGMM.h.

◆ dist_Mtreshold

double DirectGraphicalModels::TrainNodeGMMParams::dist_Mtreshold

Minimum Mahalanobis distance between Gauss functions. If this parameter is negative, the Euclidean distance is used.

Definition at line 16 of file TrainNodeGMM.h.

◆ div_KLtreshold

double DirectGraphicalModels::TrainNodeGMMParams::div_KLtreshold

Minimum Kullback-Leiber divergence between Gauss functions. If this parameter is negative, the merging of Gaussians in addFeatureVec() function will be disabled.

Definition at line 17 of file TrainNodeGMM.h.

◆ maxGausses

word DirectGraphicalModels::TrainNodeGMMParams::maxGausses

The maximal number of Gauss functions for approximation.

Definition at line 13 of file TrainNodeGMM.h.

◆ minSamples

size_t DirectGraphicalModels::TrainNodeGMMParams::minSamples

Minimum number of sapmles to approximate a Gauss function.

Definition at line 14 of file TrainNodeGMM.h.


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