CreateKnnModel
Create a k-nearest neighbors model of the specified type. The initial reference count is set to one if a new model is created and kept, otherwise. Models of this type support on-line training (sample by sample) and retraining. Predictions can only be scalar.
Syntax
Definition:
HRESULT CreateKnnModel(
HRESULT hrPrev,
ITcVnMlModel*& ipMlModel,
ETcVnKnn eKnnType,
ULONG nK
)Parameters
|
Name |
Type |
Description |
|---|---|---|
|
hrPrev |
HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.) | |
|
ipMlModel |
Returns the created model (Non-zero interface pointers are reused.) | |
|
eKnnType |
k-nearest neighbors model type | |
|
nK |
ULONG |
Parameter k used for prediction (number of considered neighbors) |
Return valueRequired 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 |