Skip to content

NVIDIA-RTX/NNE-TensorRT-Sample

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Style Transfer Sample Project for NNE TensorRT for RTX plugin

The NVIDIA TensorRT™ for RTX plugin is a runtime for Unreal Engine's Neural Network Engine (NNE). This repository contains UE5_NNETRT_Sample, a sample Unreal Engine project for demonstrating NNE running with the TensorRT for RTX runtime.

Project Overview

The sample project is configured to use the following Unreal Engine plugins:

  • NNERuntimeTRT
  • NNERuntimeRDG
  • NeuralRendering

Requirements

To use this sample project, ensure the following are available:

  • Unreal Engine 5.7 with support for the required plugins
  • NVIDIA TensorRT for RTX plugin for Unreal Engine NNE
  • An NVIDIA RTX GPU
  • A Windows system with DirectX 12 support

Setup Instructions

  1. Clone the repository
  2. Get UE5.7 source.
  3. Add TensorRT runtime support to the Neural Post-processing as follows:
    1. Modify neuralprofile.h/cpp under this folder Engine\Source\Runtime\Engine\Classes\Engine\
    2. In the header file add: UNNERuntimeRDGTensorRT UMETA(DisplayName = "NNERuntimeTRT"), to the ENeuralProfileRuntimeType. The full enum class should look like this:
    UNNERuntimeRDGTensorRT UMETA(DisplayName = "NNERuntimeTRT"), UENUM(BlueprintType)
    enum class ENeuralProfileRuntimeType : uint8
    {
    	NNERuntimeORTDml UMETA(DisplayName = "NNERuntimeORTDml"),
    
    	/** Does not have full operator support*/
    	NNERuntimeRDGHlsl UMETA(DisplayName = "NNERuntimeRDGHlsl"),
    	UNNERuntimeRDGTensorRT UMETA(DisplayName = "NNERuntimeTRT"),
    	MAX	UMETA(Hidden)
    };
    1. In the CPP file add: ,TEXT("NNERuntimeTRT") to the kRuntimeNames The full kRuntimeNames array should be:
    static const TCHAR* const kRuntimeNames[] = {
    	TEXT("NNERuntimeORTDml"),
    	TEXT("NNERuntimeRDGHlsl"),
    	TEXT("NNERuntimeTRT")
    };
  4. Compile the engine.

Running the Sample

  1. Launch the project in the compiled Unreal Editor.
  2. Open the sample level LVL_PPVStyleTest included with the project content.
  3. Play in Standalone.
  4. Press S to show performance stats.
  5. Press T to toggle between DirectML and TensorRT for RTX.

License

This project is licensed under the MIT License. See LICENSE.txt for details.

Third-Party Community Consideration

The Candy style transfer model is not owned or developed by NVIDIA. See the link to the non-NVIDIA model card. License: BSD-3-Clause.

About

No description, website, or topics provided.

Resources

License

Security policy

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages