Users of machine learning frameworks must currently implement their own transforms for running ML inferences. The exception is the TensorFlow RunInference transform. However, this is hosted in its own repo, and has an API that is exclusively geared towards the TensorFlow TFX library. Our goal is to add new implementations of RunInference for the two other popular machine learning frameworks: scikit-learn and Pytorch.
Users of machine learning frameworks must currently implement their own transforms for running ML inferences. The exception is the TensorFlow RunInference transform. However, this is hosted in its own repo, and has an API that is exclusively geared towards the TensorFlow TFX library. Our goal is to add new implementations of RunInference for the two other popular machine learning frameworks: scikit-learn and Pytorch.
Please see main design document here.
Imported from Jira BEAM-13970. Original Jira may contain additional context. Reported by: yeandy.