Navigation
API > API/Plugins > API/Plugins/NNE > API/Plugins/NNE/IModelGPU
References
| Module | NNE |
| Header | /Engine/Plugins/Experimental/NNE/Source/NNE/Public/NNERuntimeGPU.h |
| Include | #include "NNERuntimeGPU.h" |
TUniquePtr< UE::NNE::IModelInstanceGPU > CreateModelInstance&40;&41;
Remarks
Create a model instance for inference
The runtime have the opportunity to share the model weights among multiple IModelInstanceGPU created from an IModelGPU instance, however this is not mandatory. The caller can decide to convert the result into a shared pointer if required (e.g. if the model needs to be shared with an async task for evaluation). A caller owned model representing the neural network instance created.