tfma.load_eval_results

tfma.load_eval_results(
    output_paths,
    mode
)

Defined in api/model_eval_lib.py.

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

Args:

  • output_paths: A list of output paths of completed tfma runs.
  • mode: The mode of the evaluation. Currently, tfma.DATA_CENTRIC_MODE and tfma.MODEL_CENTRIC_MODE are supported.

Returns:

An EvalResults containing the evaluation results serialized at output_paths. This can be used to construct a time series view.