I think there may be an error in one of the examples.
In the section,
Convert Scikit-learn pipelines
you have:
pipeline = make_pipeline(normalizer, linear_svc)
...
pipeline_onnx = convert_sklearn(linear_svc, name='NormalizerLinearSVC',
input_features=[('input', FloatTensorType([1, 3]))])
Shouldn't this be:
pipeline_onnx = convert_sklearn(pipeline, name='NormalizerLinearSVC',
input_features=[('input', FloatTensorType([1, 3]))])
Document Details
⚠ Do not edit this section. It is required for docs.microsoft.com ➟ GitHub issue linking.
ID: e6bf772d-9f06-0114-305a-058c6bea5786
Version Independent ID: 297ca67d-9d10-eb87-f26e-4d72eefe252f
This repo has changed significantly since this issue was first raised, and further changes are upcoming. As such, I'm going through and closing many of these stale issues which sat unassigned for a long while.
I think there may be an error in one of the examples. In the section, Convert Scikit-learn pipelines you have: pipeline = make_pipeline(normalizer, linear_svc) ... pipeline_onnx = convert_sklearn(linear_svc, name='NormalizerLinearSVC', input_features=[('input', FloatTensorType([1, 3]))])
Shouldn't this be: pipeline_onnx = convert_sklearn(pipeline, name='NormalizerLinearSVC', input_features=[('input', FloatTensorType([1, 3]))])
Document Details
⚠ Do not edit this section. It is required for docs.microsoft.com ➟ GitHub issue linking.