ag-tcm

@xadupre Thanks for the links. I'm brand new to onnx but recently rewrote the QuantileTransformer from Python into Java, so I have decent knowledge of that code. Would you be...

Or even more beneficial might be if you could please point me to an existing converter that might closely resemble the one that would need to be created for QuantileTransformer?

No problem, I put my modified code here: https://github.com/ag-tcm/annoy-java.

I also got these exceptions under the same circumstances. However, it wasn't consistent. Sometimes I start a worker after the chief and other workers are already running and it starts...

I tried moving the CastTransformer to be after SimpleImputer, but it results in this error: `onnxruntime.capi.onnxruntime_pybind11_state.NotImplemented: [ONNXRuntimeError] : 9 : NOT_IMPLEMENTED : Could not find an implementation for Imputer(1) node...

Yes, thank you! It works for me. With that change, if I put the `cast32` transformer in front of the `SimpleImputer` the the latter will have float32 as its input...