Closed
Description
openedon Jul 15, 2019
When exporting a NimbusML pipeline which contains a predictor to ONNX, a TypeConvertingTransformer is sometimes inserted in the pipeline. The TypeConvertingTransformer currently requires the Experimental ONNX flag to be set in order for it to be converted to ONNX (see line 390 in src\Microsoft.ML.Data\Transforms\TypeConverting.cs). Can this be updated to no longer require the Experimental flag?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
