tfl.pwl_calibration_layer.WrinkleRegularizer

Wrinkle regularizer for PWL calibration layer.

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

Calibrator wrinkle regularization penalizes the change in the second derivative. It is defined to be:

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

where third_derivative is:

`3 * output_keypoints[1:end-2] - 3 * output_keypoints[2:end-1]

  • output_keypoints[0:end-3] + output_keypoints[3:end]`.

This regularizer is zero when the output_keypoints form a 2nd order polynomial of the index (and not necessarily 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 TF-Keras model_to_estimator, saving and loading models to HDF5 formats, TF-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).