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

tfl.pwl_calibration_layer.LaplacianRegularizer

View source on GitHub

Laplacian regularizer for PWL calibration layer.

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

Calibrator Laplacian regularization penalizes the change in the calibration output. It is defined to be:

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

where delta is:

output_keypoints[1:end] - output_keypoints[0:end-1].

Args:

  • 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

__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).

from_config

@classmethod
from_config(
    cls, 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.

Arguments:

  • 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.