2019-06-15 ONNX, runtime, converters

I have been recently working on sklearn-onnx to write converter from scikit-learn operators to ONNX serialization format. I was talking about that a month ago and somebody asked me if there was a runtime implemented in RUST. Not that I know of but I said it would not be too complex to implement one.

That’s what I did in Python. There are two components for the runtime. An ONNX model is a series of mathematical functions chained in a graph. A runtime must implement each component and the sequence of operators to compute predictions.