Execute_MultiLayerOutput
Execute a neural network using the provided image as input and provide the output from the specified output layers. If sLayerNames is empty, the method returns the output of the unconnected output layers. The method doesn't perform any pre-processing or transformation.
Syntax
Definition:
HRESULT Execute_MultiLayerOutput(
ITcVnImage* ipSrcImage,
ITcVnContainer** pipDestImages,
ITcVnContainer* ipLayerNames
)Parameters
|
Name |
Type |
Description |
|---|---|---|
|
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.) | |
|
pipDestImages |
Container of images containing the output from the specified layers | |
|
ipLayerNames |
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. |