onnxcustom 0.2.122

onnxcustom: custom ONNX

documentation

Tutorial on how to convert machine learned models into ONNX, implement your own converter or runtime. The module must be compiled to be used inplace:

python setup.py build_ext --inplace

Generate the setup in subfolder dist:

python setup.py sdist

Generate the documentation in folder dist/html:

python setup.py build_sphinx

Run the unit tests:

python setup.py unittests

To check style:

python -m flake8 onnxcustom tests examples

The function check or the command line python -m onnxcustom check checks the module is properly installed and returns processing time for a couple of functions or simply:

import onnxcustom
onnxcustom.check()

This tutorial has been merged into sklearn-onnx documentation.