RSVP for your your local TensorFlow Everywhere event today!


Creates an Evaluator for evaluating metrics and plots.

eval_shared_model Shared model parameters for EvalSavedModel.
desired_batch_size Optional batch size for batching in Aggregate.
metrics_key Name to use for metrics key in Evaluation output.
plots_key Name to use for plots key in Evaluation output.
run_after Extractor to run after (None means before any extractors).
compute_confidence_intervals Whether or not to compute confidence intervals.
min_slice_size If the number of examples in a specific slice is less than min_slice_size, then an error will be returned for that slice. This will be useful to ensure privacy by not displaying the aggregated data for smaller number of examples.
serialize If true, serialize the metrics to protos as part of the evaluation as well.
random_seed_for_testing Provide for deterministic tests only.

Evaluator for evaluating metrics and plots. The output will be stored under 'metrics' and 'plots' keys.