tfx_bsl.public.beam.RunInference

View source on GitHub

Run inference with a model.

View aliases

Main aliases

tfx_bsl.public.beam.run_inference.RunInference

tfx_bsl.public.beam.RunInference(
    examples: beam.pvalue.PCollection,
    inference_spec_type: tfx_bsl.public.proto.model_spec_pb2.InferenceSpecType
) -> beam.pvalue.PCollection

There are two types of inference you can perform using this PTransform:

1. In-process inference from a SavedModel instance. Used when saved_model_spec field is set in inference_spec_type.

2. Remote inference by using a service endpoint. Used when ai_platform_prediction_model_spec field is set in inference_spec_type.

3. Bytes as Input.

4. PTable Input.

5. Models as SideInput.

Args
examples	A PCollection containing examples.
inference_spec_type	Model inference endpoint.

Returns
A PCollection containing prediction logs.