Sentis overview
This package is available as an experimental package, so it is not ready for production use. The features and documentation in this package might change before it is verified for release.
The Sentis package is a neural network inference library for Unity.
You can use Sentis to import trained neural network models into Unity, then run them in real time locally on any platform Unity supports and in the Editor. You can run models on the GPU or the CPU.
To use Sentis, it helps if you have some experience in using machine learning models, for example in a framework like TensorFlow or PyTorch.
Note: You can only get access to Sentis if you've been invited to the private beta by Unity. You can sign up for the closed beta. If you’re already in the closed beta, visit the Unity Discussions group for the Sentis beta for updates and resources, including a full sample project.
| Section | Description |
|---|---|
| Get started | Install Sentis, find and use the sample projects, and get started. |
| Import a model | Import an Open Neural Network Exchange (ONNX) model into Sentis and inspect it. |
| Run an imported model | Create input data for a model, create an engine to run the model, and get output. |
| Use Tensors | Get, set and modify input and output data. |
| Profile a model | Use Unity tools to profile the speed and performance of a model. |
Supported platforms
Sentis supports all the platforms Unity supports.
How long a model takes to run depends on the complexity of the model, the platform, and the engine type you use. Refer to Models and Create an engine for more information.
Supported model types
Sentis supports most models in ONNX format with an opset version between 7 and 15. Refer to Supported ONNX operators for more information.