Missed TensorFlow World? Check out the recap. Learn more

tfma.default_evaluators

tfma.default_evaluators(
    eval_shared_model,
    desired_batch_size=None,
    num_bootstrap_samples=None
)

Defined in api/model_eval_lib.py.

Returns the default evaluators for use in ExtractAndEvaluate.

Args:

  • eval_shared_model: Shared model parameters for EvalSavedModel.
  • desired_batch_size: Optional batch size for batching in Aggregate.
  • num_bootstrap_samples: Number of bootstrap samples to draw. If more than 1, confidence intervals will be computed for metrics. Suggested value is at least 20.