Open NonaryR opened 5 years ago
@xadupre @prabhat00155
I'm not sure where the errror comes from. If it is a bad conversion, we made many fixes over the past two weeks to fix the conversion of pipelines in sklearn-onnx. If it is a runtime issue, graphpipe says it is using caffe2 as a runtime. Is it possible to check the onnx model with a different runtime (such as onnxruntime) and let us know the outcome?
@xadupre I got same building error.
Hello! I'm trying to use onnx model from sklearn with graphpipe
Save an onnx model which contains
Pipeline
withStandartScaler + LogisticRegression
Also, I should providevalue-inputs.json
, with inputs specification In my data i have 44 float features, so myvalue-inputs
looks like this:Then I run docker container and have this validation error
In my onnx model I have two outputs --
label
andprobabilties
:How can I resolve this?