Navigation
API > API/Runtime > API/Runtime/NNE > API/Runtime/NNE/IModelInstanceRunSync
Description
Prepare the model to be run with the given input shape.
The call is mandatory before a model can be run. The function will run shape inference and resolve, if possible, the output shapes which can then be accessed by calling GetOutputTensorShapes(). This is a potentially expensive call and should be called lazily if possible.
| Name | SetInputTensorShapes |
| Type | function |
| Header File | /Engine/Source/Runtime/NNE/Public/NNERuntimeRunSync.h |
| Include Path | #include "NNERuntimeRunSync.h" |
ESetInputTensorShapesStatus SetInputTensorShapes
(
TConstArrayView< FTensorShape > InInputShapes
)
Status indicating success or failure.
Parameters
| Name | Remarks |
|---|---|
| InInputShapes | The input shapes to prepare the model with. |