PredictBatch
Compute predictions for a batch of samples.
Can use available TwinCAT Job Tasks for executing parallel code regions.
Syntax
Definition:
HRESULT PredictBatch(
HRESULT hrPrev,
ITcVnMlModel* ipMlModel,
ITcUnknown* ipSamples,
ITcVnContainer*& ipPredictions,
ITcVnContainer** pipNovelties = nullptr
)Parameters
|
Name |
Type |
Default |
Description |
|---|---|---|---|
|
hrPrev |
|
HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.) | |
|
ipMlModel |
|
Classifier or regressor to be used | |
|
ipSamples |
|
Container holding a batch of input samples (ContainerType_Vector_Vector_REAL or ContainerType_Vector_Vector_LREAL) | |
|
ipPredictions |
|
Returns the predicted outputs (depending on ipSamples; class labels (for classification, ContainerType_Vector_DINT) or real-valued predictions (for regression with scalar output, ContainerType_Vector_REAL or ContainerType_Vector_LREAL; for regression with vectorial output, ContainerType_Vector_Vector_REAL or ContainerType_Vector_Vector_LREAL)) | |
|
pipNovelties |
nullptr |
Returns the degree of novelty (0.0 if a sample is completely known; > 0.0 otherwise) of each sample (ContainerType_Vector_REAL; optional, set to 0 if not required) |
Return valueRequired License
TC3 Machine Learning Realtime Inference