ExecuteNeuralNetwork (MO)
Execute a neural network using the provided image as input and provide the output of the specified output layers. The function doesn't perform any pre-processing or transformation.
Can use available TwinCAT Job Tasks for executing parallel code regions.
Syntax
Definition:
HRESULT ExecuteNeuralNetwork(
HRESULT hrPrev,
ITcVnNeuralNetwork* ipNeuralNetwork,
ITcVnImage* ipSrcImage,
ITcVnContainer*& ipDestImages,
ITcVnContainer* ipOutputNames
)Parameters
|
Name |
Type |
Description |
|---|---|---|
|
hrPrev |
HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.) | |
|
ipNeuralNetwork |
Neural network model | |
|
ipSrcImage |
Source image (The image layout must be adapted to match the model's expected input format using e.g. F_VN_ConvertDataLayout or F_VN_ReshapeImage functions if necessary.) | |
|
ipDestImages |
Container of images containing the output from the specified layers. | |
|
ipOutputNames |
Container of layer names whose outputs to be returned (ContainerType_Vector_String_SINT). If set to zero, the outputs of all unconnected output layers will be returned.. |
Required License
TC3 Neural Network 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 |