The structure stores the parameters for the classificationa nd must be initialized and passed to the training method pcl::SVMTrain. More...
#include <pcl/ml/svm_wrapper.h>
Inheritance diagram for pcl::SVMParam:
Collaboration diagram for pcl::SVMParam:
Public Member Functions | |
| SVMParam () | |
Additional Inherited Members | |
| Public Attributes inherited from svm_parameter | |
| int | svm_type |
| int | kernel_type |
| int | degree |
| double | gamma |
| double | coef0 |
| double | cache_size |
| double | eps |
| double | C |
| int | nr_weight |
| int * | weight_label |
| double * | weight |
| double | nu |
| double | p |
| int | shrinking |
| int | probability |
Detailed Description
The structure stores the parameters for the classificationa nd must be initialized and passed to the training method pcl::SVMTrain.
- Parameters
-
svm_type {C_SVC, NU_SVC, ONE_CLASS, EPSILON_SVR, NU_SVR} kernel_type {LINEAR, POLY, RBF, SIGMOID, PRECOMPUTED} probability sets the probability estimates
Definition at line 62 of file svm_wrapper.h.
Constructor & Destructor Documentation
◆ SVMParam()
|
inline |
Definition at line 63 of file svm_wrapper.h.
References svm_parameter::C, svm_parameter::cache_size, svm_parameter::coef0, svm_parameter::degree, svm_parameter::eps, svm_parameter::gamma, svm_parameter::kernel_type, svm_parameter::nr_weight, svm_parameter::nu, svm_parameter::p, svm_parameter::probability, svm_parameter::shrinking, svm_parameter::svm_type, svm_parameter::weight, and svm_parameter::weight_label.
The documentation for this struct was generated from the following file:
- pcl/ml/svm_wrapper.h