F_VN_FeatureScaling
Apply a feature scaling to one or more sample(s).
Syntax
Definition:
FUNCTION F_VN_FeatureScaling : HRESULT
VAR_INPUT
ipSamples : ITcVnContainer;
ipScales : ITcVnContainer;
ipScaledSamples : Reference To ITcVnContainer;
hrPrev : HRESULT;
END_VAR
Inputs
|
Name |
Type |
Description |
|---|---|---|
|
ipSamples |
Container holding one or more input sample(s) (ContainerType_Vector_REAL, ContainerType_Vector_LREAL, ContainerType_Vector_Vector_REAL, or ContainerType_Vector_Vector_LREAL) | |
|
ipScales |
Container with the scaling parameters of each feature (type ContainerType_Vector_REAL or ContainerType_Vector_LREAL). | |
|
ipScaledSamples |
Reference To ITcVnContainer |
Returns the scaled sample(s) using the same type like ipSamples. If the same container ipSamples is uesd, the source data will be replaced. |
|
hrPrev |
HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.) |
Return valueFurther information
The function F_VN_FeatureScaling scales features from several samples. The function F_VN_InverseFeatureScaling can be used for inverse scaling.
Parameter
Samples
One or more samples must be transferred as a container to ipSamples.
Scaling
A container with the scaling type and the corresponding scaling parameters must be transferred to ipScales. The container can be calculated using the function F_VN_GetFeatureScales or created using the structure described there.
Scaled samples
The scaled samples are returned via the reference ipScaledSamples.
Expert parameters
The expert variant F_VN_FeatureScalingExp contains additional parameters.
Application
For example, a feature scaling in which the scaling parameters are calculated beforehand by F_VN_GetFeatureScales using the MINMAX method looks like this:
hr := F_VN_GetFeatureScales(ipSamples, ipScales, TCVN_FST_MINMAX, hr);
hr := F_VN_FeatureScaling(
ipSamples := ipSamples,
ipScales := ipScales,
ipScaledSamples := ipScaledSamples,
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 |