F_VN_ExecuteNeuralNetwork_MultiLayerOutput

Execute a neural network using the provided image as input and provide the output from the specified output layers. The function doesn't perform any pre-processing or transformation.

Syntax

Definition:

FUNCTION F_VN_ExecuteNeuralNetwork_MultiLayerOutput : HRESULT
VAR_INPUT
    ipNeuralNetwork : ITcVnNeuralNetwork;
    ipSrcImage      : ITcVnImage;
    ipDestImages    : Reference To  ITcVnContainer;
    ipLayerNames    : ITcVnContainer;
    hrPrev          : HRESULT;
END_VAR

Inputs

Name	Type	Description
ipNeuralNetwork	ITcVnNeuralNetwork	Neural network model
ipSrcImage	ITcVnImage	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	Reference To ITcVnContainer	Container of images containing the output from the specified layers.
ipLayerNames	ITcVnContainer	Container of layer names whose outputs are required (ContainerType_Vector_String_SINT). If set to zero, the container ipDestImages holds the outputs of all the unconnected output layers.
hrPrev	HRESULT	HRESULT indicating the result of previous operations (If SUCCEEDED(hrPrev) equals false, no operation is executed.)

Return value

HRESULT

Required License

TC3 Vision Neural Network

System Requirements

Development environment	Target platform	PLC libraries to include
TwinCAT V3.1.4024.59 or later	PC or CX (x64) with PL50, e.g. Intel 4-core Atom CPU	Tc3_Vision