Back to Aurora Vision Library website

You are here: Start » Function Reference » Data Classification » Nearest Neighbors » KNN_Train

KNN_Train


Header: AVL.h
Namespace: avl
Module: FoundationPro

Trains KNN classifier using sample data.

Syntax

C++
C#
 
void avl::KNN_Train
(
	const avl::KNNModel& inKNNModel,
	const atl::Array<atl::Array<float> >& inFeatures,
	const atl::Array< int >& inClasses,
	avl::KNNModel& outKNNModel
)

Parameters

Name Type Default Description
Input value inKNNModel const KNNModel& Initialized KNN model
Input value inFeatures const Array<Array<float> >& Array of features array
Input value inClasses const Array< int >& Array of classes corresponding to feature array elements
Output value outKNNModel KNNModel& Trained KNN model

Errors

List of possible exceptions:

Error type Description
DomainError Array inClasses contains negative values in KNN_Train.
DomainError Array inClasses contains values grater than maximal class value in KNN_Train.
DomainError Input array inClasses is empty in KNN_Train.
DomainError Input array inFeatures is empty in KNN_Train.
DomainError Input inFeatures contains array of different sizes in KNN_Train.
DomainError The inFeatures size is different than inClasses size in KNN_Train.
DomainError Using uninitialized classifier in KNN_Train.