Join us at TensorFlow World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tfma.default_eval_shared_model

tfma.default_eval_shared_model(
    eval_saved_model_path,
    add_metrics_callbacks=None,
    include_default_metrics=True,
    example_weight_key=None,
    additional_fetches=None
)

Defined in api/model_eval_lib.py.

Returns default EvalSharedModel.

Args:

  • eval_saved_model_path: Path to EvalSavedModel.
  • add_metrics_callbacks: Optional list of callbacks for adding additional metrics to the graph (see EvalSharedModel for more information on how to configure additional metrics). Metrics for example counts and example weight will be added automatically.
  • include_default_metrics: True to include the default metrics that are part of the saved model graph during evaluation.
  • example_weight_key: Deprecated.
  • additional_fetches: Prefixes of additional tensors stored in signature_def.inputs that should be fetched at prediction time. The "features" and "labels" tensors are handled automatically and should not be included.