- ONNX Support
- Format Conversion
- Automatic data type conversion
- Creating a Model
- Running a model
- Validation in the Strategy Tester
- OnnxCreate
- OnnxCreateFromBuffer
- OnnxRelease
- OnnxRun
- OnnxGetInputCount
- OnnxGetOutputCount
- OnnxGetInputName
- OnnxGetOutputName
- OnnxGetInputTypeInfo
- OnnxGetOutputTypeInfo
- OnnxSetInputShape
- OnnxSetOutputShape
- Data structures
Format Conversion
ONNX is an open format, which allows using models from different machine learning toolkits. This format is supported by many frameworks, including Chainer, Caffee2 and PyTorch.
One of the most popular tools for converting models to the ONNX format is Microsoft's ONNXMLTools.
ONNXMLTools installation and use instructions are available at the GitHub repo. The following toolkits are currently supported:
- Keras (a wrapper of keras2onnx converter)
- Tensorflow (a wrapper of tf2onnx converter)
- scikit-learn (a wrapper of skl2onnx converter)
- Apple Core ML
- Spark ML (experimental)
- LightGBM
- libscm;
- XGBoost;
- H2O
- CatBoost
ONNXMLTools can be easily installed. For installation details and model conversion examples, please see the project page at https://github.com/onnx/onnxmltools#install.