Module: tfl.categorical_calibration_layer

Categorical calibration layer with monotonicity and bound constraints.

Keras implementation of tensorflow lattice categorical calibration layer. This layer takes single or multi-dimensional input and transforms it using lookup tables satisfying monotonicity and bounds constraints if specified.


class CategoricalCalibrationConstraints: Monotonicity and bounds constraints for categorical calibration layer.

Other Members

  • CATEGORICAL_CALIBRATION_KERNEL_NAME = 'categorical_calibration_kernel'
  • DEFAULT_INPUT_VALUE_NAME = 'default_input_value'