Xavier Dupré

A pipeline may only contains one operator from ai.onnx.ml. In that case, there is no obvious value for opset ai.onnx and it is missing from the ONNX graph. But some...

This table [Compatibility](https://github.com/microsoft/onnxruntime/blob/master/docs/Versioning.md#version-matrix) is more explicit about which version is supported at which version of onnxruntime or onnx. The dictionaries you mention above are just a way to guess an...

Booster should be now supported. You would probably need to install the library from master branch. See PR #385 for more details.

Many changes have been brought to the converter. Did you try recently?

ONNX only supports a specific set of operators which you can found at: https://github.com/onnx/onnx/blob/master/docs/Operators.md and https://github.com/onnx/onnx/blob/master/docs/Operators-ml.md. The final graph is a combination of them in a graph. You can look...

If you need a complete new converter, you need to define three elemens : a parser which defines the number of input and output of your model, the shape calculator...

You may look at http://onnx.ai/sklearn-onnx/auto_tutorial/plot_icustom_converter.html to see how to implement a custom converter. However, the support for strings is very limited in standard ONNX. It only supports tokenization with regular...

sklearn-onnx only supports model from scikit-learn. The documentation gives example on how to implement a new converter: https://onnx.ai/sklearn-onnx/tutorial_2_new_converter.html. The error does not seem related to pickle, am I missing something?

This is related to this issue: https://github.com/scikit-learn/scikit-learn/issues/13733.

You are using a custom operator and sklearn-onnx needs to know how to convert every piece of a pipeline to convert the whole pipeline. This error message tells that there...