Create a model
Create a runtime model by importing an ONNX model file or using the Sentis model API.
Page | Description |
---|---|
Understand models in Sentis | How Sentis optimizes models, and information about fixed and dynamic input dimensions. |
Export an ONNX file from a machine learning framework | Export a model from a machine learning framework in the ONNX format Sentis needs. |
Convert a file to ONNX | Convert a neural network file to the ONNX format |
Import an ONNX file | Import an ONNX file and create a runtime model. |
Serialize a model | Create a serialized model (*.sentis file) in the StreamingAssets folder. |
Inspect a model | Check the inputs, outputs and layers of a model. |
Create a new model | Create a new runtime model with the Sentis model API. |
Edit a model | Make changes to an existing runtime model. |
Encrypt a model | Encrypt and decrypt a Sentis model. |
Supported ONNX operators | Which ONNX operators Sentis supports. |
Model Asset Import Settings reference | Understand the settings and properties of an imported model in the Unity Inspector. |