Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tfl.categorical_calibration_lib.verify_hyperparameters

View source on GitHub

Verifies that all given hyperparameters are consistent.

tfl.categorical_calibration_lib.verify_hyperparameters(
    num_buckets=None, output_min=None, output_max=None, monotonicities=None
)

See tfl.layers.CategoricalCalibration class level comment for detailes.

Args:

  • num_buckets: num_buckets of CategoricalCalibration layer.
  • output_min: smallest output of CategoricalCalibration layer.
  • output_max: largest output of CategoricalCalibration layer.
  • monotonicities: monotonicities of CategoricalCalibration layer.

Raises:

  • ValueError: If parameters are incorrect or inconsistent.