Module core.components.pusher.cortex_executor¶
Cortex pusher executor.
Classes¶
Executor(context: Union[tfx.dsl.components.base.base_executor.BaseExecutor.Context, NoneType] = None)
: Deploy a model to Cortex serving.
Constructs a beam based executor.
### Ancestors (in MRO)
* tfx.components.pusher.executor.Executor
* 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])`
: Overrides the tfx_pusher_executor.
Args:
input_dict: Input dict from input key to a list of artifacts,
including:
- model_export: exported model from trainer.
- model_blessing: model blessing path from evaluator.
output_dict: Output dict from key to a list of artifacts, including:
- model_push: A list of 'ModelPushPath' artifact of size one. It
will
include the model in this push execution if the model was pushed.
exec_properties: Mostly a passthrough input dict for
tfx.components.Pusher.executor.custom_config
Raises:
ValueError: if custom config not present or not a dict.
RuntimeError: if