F_VN_FeatureTransform
Apply a feature transform to one or more sample(s).
Syntax
Definition:
FUNCTION F_VN_FeatureTransform : HRESULT
VAR_INPUT
ipFeatureTransform : ITcVnMlModel;
ipSamples : ITcUnknown;
pipTransformed : Pointer To ITcUnknown;
hrPrev : HRESULT;
END_VAR
Inputs
Name |
Type |
Description |
---|---|---|
ipFeatureTransform |
Feature transform instance to be used | |
ipSamples |
Container holding one or more of input sample(s) (ContainerType_Vector_REAL, ContainerType_Vector_LREAL, ContainerType_Vector_Vector_REAL, or ContainerType_Vector_Vector_LREAL) | |
pipTransformed |
Pointer To ITcUnknown |
Returns the transformed sample(s) using the same type like ipSamples |
hrPrev |
HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.) |
Further information
The function F_VN_FeatureTransform
transforms the features of one or more samples using a transformation model. An inverse transform can be carried out with the F_VN_InverseFeatureTransform function.
Parameter
Transformation model
A previously created model must be transferred to ipFeatureTransform
for feature transformation.
Samples
A container with the samples to be transformed is transferred to ipSamples
. The following container types are permitted:
ContainerType_Vector_REAL
orContainerType_Vector_LREAL
for a single sampleContainerType_Vector_Vector_REAL
orContainerType_Vector_Vector_LREAL
for a container with several samples.
Transformed samples
A container with the transformed samples is returned via the pointer pipTransformed
. The container type is taken from ipSamples
.
Application
For example, a feature transformation is carried out as follows:
hr := F_VN_FeatureTransform(
ipFeatureTransform := ipMlModel,
ipSamples := ipSamples,
pipTransformed := ADR(ipTransformed),
hrPrev := hr);
Related functions
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 |