F_VN_GetBatchNovelties

Get the degree of novelty of multiple samples.
Can use available TwinCAT Job Tasks for executing parallel code regions.

Syntax

Definition:

FUNCTION F_VN_GetBatchNovelties : HRESULT
VAR_INPUT
    ipNoveltyDetector : ITcVnMlModel;
    ipSamples         : ITcUnknown;
    ipNovelties       : Reference To  ITcVnContainer;
    hrPrev            : HRESULT;
END_VAR

Inputs

Name	Type	Description
ipNoveltyDetector	ITcVnMlModel	Novelty detector to be used
ipSamples	ITcUnknown	Container holding a batch of input samples (ContainerType_Vector_Vector_REAL or ContainerType_Vector_Vector_LREAL)
ipNovelties	Reference To ITcVnContainer	Returns the degree of novelty (0.0 if a sample is completely known; > 0.0 otherwise) of each sample (ContainerType_Vector_REAL)
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_GetBatchNovelties determines the degree of novelty for all samples in a container.

Parameter

Anomaly model

To calculate the degree of novelty, the previously trained model must be transferred to ipNoveltyDetector.

Samples

A container with the samples is transferred to ipSamples.

Degrees of novelty

A container with the calculated degrees of novelty is returned via the reference ipNovelties.

Application

The degree of novelty of several samples can be calculated as follows:

hr := F_VN_GetBatchNovelties(
    ipNoveltyDetector   := ipNoveltyDetector,
    ipSamples           := ipSamples,
    ipNovelties         := ipNovelties,
    hrPrev              := hr);

Related functions

F_VN_GetSampleNovelty

Required License

TC3 Vision Machine Learning

System Requirements

Development environment	Target platform	PLC libraries to include
TwinCAT V3.1.4024.54 or later	PC or CX (x64) with PL50, e.g. Intel 4-core Atom CPU	Tc3_Vision