Module core.components.bulk_inferrer.executor

ZenML bulk inferrer executor.


BulkInferrerExecutor(context: Union[tfx.dsl.components.base.base_executor.BaseExecutor.Context, NoneType] = None) : TFX bulk inferrer executor.

Constructs a beam based executor.

### Ancestors (in MRO)

* tfx.dsl.components.base.base_executor.BaseExecutor

### Methods

`Do(self, input_dict: Dict[str, List[tfx.types.artifact.Artifact]], output_dict: Dict[str, List[tfx.types.artifact.Artifact]], exec_properties: Dict[str, Any]) ‑> NoneType`
:   Runs batch inference on a given model with given input examples.
      input_dict: Input dict from input key to a list of Artifacts.
        - examples: examples for inference.
        - model: exported model.
        - model_blessing: model blessing result, optional.
      output_dict: Output dict from output key to a list of Artifacts.
        - output: bulk inference results.
      exec_properties: A dict of execution properties.
        - model_spec: JSON string of bulk_inferrer_pb2.ModelSpec instance.
        - data_spec: JSON string of bulk_inferrer_pb2.DataSpec instance.