Join the SIG TFX-Addons community and help make TFX even better!

tfx.components.InfraValidator

A TFX component to validate the model against the serving infrastructure.

Inherits From: BaseComponent, BaseNode

An infra validation is done by loading the model to the exactly same serving binary that is used in production, and additionaly sending some requests to the model server. Such requests can be specified from Examples artifact.

Examples

Full example using TensorFlowServing binary running on local docker.

infra_validator = InfraValidator(
    model=trainer.outputs['model'],
    examples=test_example_gen.outputs['examples'],
    serving_spec=ServingSpec(
        tensorflow_serving=TensorFlowServing(  # Using TF Serving.
            tags=['latest']
        ),
        local_docker=LocalDockerConfig(),  # Running on local docker.
    ),
    validation_spec=ValidationSpec(
        max_loading_time_seconds=60,
        num_tries=5,
    ),
    request_spec=RequestSpec(
        tensorflow_serving=TensorFlowServingRequestSpec(),
        num_examples=1,
    )
)

Minimal example when running on Kubernetes.

infra_validator = InfraValidator(
    model=trainer.outputs['model'],
    examples=test_example_gen.outputs['examples'],
    serving_spec=ServingSpec(
        tensorflow_serving=TensorFlowServing(
            tags=['latest']
        ),
        kubernetes=KubernetesConfig(),  # Running on Kubernetes.
    ),
)

Component outputs contains:

model A Channel of ModelExportPath type, usually produced by Trainer component. required
serving_spec A ServingSpec configuration about serving binary and test platform config to launch model server for validation. required
examples A Channel of ExamplesPath type, usually produced by ExampleGen component. If not specified, InfraValidator does not issue requests for validation.
request_spec Optional RequestSpec configuration about making requests from examples input. If not specified, InfraValidator does not issue requests for validation.
validation_spec Optional ValidationSpec configuration.

outputs Component's output channel dict.