tfma.multiple_model_analysis

tfma.multiple_model_analysis(
    model_locations,
    data_location,
    **kwargs
)

Defined in api/model_eval_lib.py.

Run model analysis for multiple models on the same data set.

Args:

  • model_locations: A list of paths to the export eval saved model.
  • data_location: The location of the data files.
  • **kwargs: The args used for evaluation. See tfma.run_model_analysis() for details.

Returns:

A tfma.EvalResults containing all the evaluation results with the same order as model_locations.