![]() |
Run inference with a model.
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:
- In-process inference from a SavedModel instance. Used when
saved_model_spec
field is set ininference_spec_type
. Remote inference by using a service endpoint. Used when
ai_platform_prediction_model_spec
field is set ininference_spec_type
.tf.train.SequenceExample as Input for RemotePredict.
beam.Shared() initialization via Fingerprint for models CSE.
Models as SideInput.
TPU models.
Args | |
---|---|
examples
|
A PCollection containing examples of the following possible kinds,
each with their corresponding return type.
|
inference_spec_type
|
Model inference endpoint. |
Returns | |
---|---|
A PCollection (possibly keyed) containing prediction logs. |