Xavier Dupré

Whatever the option, there will be two versions, one for scikit learn, one for onnx. The numpy api is a way to have the same code produce the two versions....

Thanks, I'll write the example today.

I created a PR with an example similar to yours. Feel free to add comment wherever it needs more explanations from me.

You can look into https://onnx.ai/onnx/operators/ or https://github.com/onnx/onnx/blob/main/docs/Operators.md. The first page contains some explaination about onnx, opset, domain, operators, ...

They are dynamically created by the package based on the operator schema. They have the same signature as the operators. Operator Slice becomes class OnnxSlice. When I created this API,...

Yes.

I see they already added float 8 types. The documentation is better than onnx.

I'm in favor, same reasons.

Is it possible to know the value for the attributes of the operator Resize you defined and the input size as well?

Should we add the operator converting an int/double into a string?