Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 

2.0 KiB

Unity Inference Engine

The ML-Agents toolkit allows you to use pre-trained neural network models inside your Unity games. This support is possible thanks to the Unity Inference Engine. The Unity Inference Engine is using compute shaders to run the neural network within Unity.

Note: The ML-Agents toolkit only supports the models created with our trainers.

Supported devices

Scripting Backends : The Unity Inference Engine is generally faster with IL2CPP than with Mono for Standalone builds. In the Editor, It is not possible to use the Unity Inference Engine with GPU device selected when Editor Graphics Emulation is set to OpenGL(ES) 3.0 or 2.0 emulation. Also there might be non-fatal build time errors when target platform includes Graphics API that does not support Unity Compute Shaders. The Unity Inference Engine supposedly works on any Unity supported platform but we only tested for the following platforms :

  • Linux 64 bits
  • Mac OS X 64 bits (OpenGLCore Graphics API is not supported)
  • Windows 64 bits
  • iOS
  • Android

Supported formats

There are currently two supported model formats:

Export to ONNX is currently considered beta. To enable it, make sure tf2onnx>=1.5.5 is installed in pip. tf2onnx does not currently support tensorflow 2.0.0 or later.

Using the Unity Inference Engine

When using a model, drag the model file into the Model field in the Inspector of the Agent. Select the Inference Device : CPU or GPU you want to use for Inference.

Note: For most of the models generated with the ML-Agents toolkit, CPU will be faster than GPU. You should use the GPU only if you use the ResNet visual encoder or have a large number of agents with visual observations.