F_VN_TrainSampleClass

Syntax

Definition:

FUNCTION F_VN_TrainSampleClass : HRESULT
VAR_INPUT
    ipClassifier : ITcVnMlModel;
    ipSample     : ITcUnknown;
    nClass       : DINT;
    hrPrev       : HRESULT;
END_VAR

Inputs

Name	Type	Description
ipClassifier	ITcVnMlModel	Classifier to be used
ipSample	ITcUnknown	Container holding a single input sample (ContainerType_Vector_REAL or ContainerType_Vector_LREAL)
nClass	DINT	Class label to be learnt
hrPrev	HRESULT	HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.)

Return value

HRESULT

Further information

The function F_VN_TrainSampleClass trains a classifier model with a sample.

Parameter

Classifier model

The previously created classifier model must be transferred to ipClassifier.

Sample

The sample container is transferred to ipSample. The type of container must be ContainerType_Vector_REAL or ContainerType_Vector_LREAL.

Class

The target class for the sample is transferred as nClass.

Application

For example, a classifier model can be trained with single samples as follows:

hr := F_VN_TrainSampleClass(
    ipClassifier    := ipMlModel,
    ipSample        := ipSample,
    nClass          := nClass,
    hrPrev          := hr);

Related functions

Required License

TC3 Machine Learning Realtime Inference

System Requirements

Development environment	Target platform	PLC libraries to include
TwinCAT V3.1.4024.59 or later	PC or CX (x64) with min. PL50, e.g. Intel 4-core Atom CPU	Tc3_Vision