TensorFlow 2.0 RC is available Learn more

tfma.make_eval_results

tfma.make_eval_results(
    results,
    mode
)

Defined in api/model_eval_lib.py.

Run model analysis for a single model on multiple data sets.

Args:

  • results: A list of TFMA evaluation results.
  • mode: The mode of the evaluation. Currently, tfma.DATA_CENTRIC_MODE and tfma.MODEL_CENTRIC_MODE are supported.

Returns:

An EvalResults containing all evaluation results. This can be used to construct a time series view.