tfl.categorical_calibration_layer.CategoricalCalibrationConstraints

Monotonicity and bounds constraints for categorical calibration layer.

tfl.categorical_calibration_layer.CategoricalCalibrationConstraints(
    output_min=None, output_max=None, monotonicities=None
)

Updates the weights of CategoricalCalibration layer to satify bound and monotonicity constraints. The update is an approximate L2 projection into the constrained parameter space.

output_min Minimum possible output of categorical function.
output_max Maximum possible output of categorical function.
monotonicities Monotonicities of CategoricalCalibration layer.

Methods

from_config

@classmethod
from_config(
    config
)

Instantiates a weight constraint from a configuration dictionary.

Example:

constraint = UnitNorm()
config = constraint.get_config()
constraint = UnitNorm.from_config(config)

Args
config A Python dictionary, the output of get_config.

Returns
A tf.keras.constraints.Constraint instance.

get_config

View source

get_config()

Standard Keras config for serialization.

__call__

View source

__call__(
    w
)

Applies constraints to w.