tfl.pwl_calibration_layer.HessianRegularizer

Stay organized with collections Save and categorize content based on your preferences.

Hessian regularizer for PWL calibration layer.

tfl.pwl_calibration_layer.HessianRegularizer(
    l1=0.0, l2=0.0, is_cyclic=False
)

Calibrator hessian regularizer penalizes the change in slopes of linear pieces. It is define to be:

l1 * ||nonlinearity||_1 + l2 * ||nonlinearity||_2^2

where nonlinearity is:

`2 * output_keypoints[1:end-1] - output_keypoints[0:end-2]

  • output_keypoints[2:end]`.

This regularizer is zero when the output_keypoints form a linear function of the index (and not necessarily linear in input values, e.g. when using non-uniform input keypoints).

l1 l1 regularization amount as float.
l2 l2 regularization amount as float.
is_cyclic Whether the first and last keypoints should take the same output value.

Methods

from_config

@classmethod
from_config(
    config
)

Creates a regularizer from its config.

This method is the reverse of get_config, capable of instantiating the same regularizer from the config dictionary.

This method is used by Keras model_to_estimator, saving and loading models to HDF5 formats, Keras model cloning, some visualization utilities, and exporting models to and from JSON.

Args
config A Python dictionary, typically the output of get_config.

Returns
A regularizer instance.

get_config

View source

get_config()

Standard Keras config for serialization.

__call__

View source

__call__(
    x
)

Returns regularization loss.

Args
x Tensor of shape: (k, units) which represents weights of PWL calibration layer. First row of weights is bias term. All remaining represent delta in y-value compare to previous point (segment heights).