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

tfl.lattice_layer.LaplacianRegularizer

View source on GitHub

Laplacian regularizer for tfl.layers.Lattice layer.

tfl.lattice_layer.LaplacianRegularizer(
    lattice_sizes, l1=0.0, l2=0.0
)

Laplacian regularizer penalizes the difference between adjacent vertices in multi-cell lattice (see publication).

Consider a 3 x 2 lattice with weights w:

w[3]-----w[4]-----w[5]
  |        |        |
  |        |        |
w[0]-----w[1]-----w[2]

where the number at each node represents the weight index. In this case, the laplacian regularizer is defined as:

l1[0] * (|w[1] - w[0]| + |w[2] - w[1]| +
         |w[4] - w[3]| + |w[5] - w[4]|) +
l1[1] * (|w[3] - w[0]| + |w[4] - w[1]| + |w[5] - w[2]|) +

l2[0] * ((w[1] - w[0])^2 + (w[2] - w[1])^2 +
         (w[4] - w[3])^2 + (w[5] - w[4])^2) +
l2[1] * ((w[3] - w[0])^2 + (w[4] - w[1])^2 + (w[5] - w[2])^2)

Args:

  • lattice_sizes: Lattice sizes of tfl.layers.Lattice to regularize.
  • l1: l1 regularization amount. Either single float or list or tuple of floats to specify different regularization amount per dimension.
  • l2: l2 regularization amount. Either single float or list or tuple of floats to specify different regularization amount per dimension.

Raises:

  • ValueError: If provided input does not correspond to lattice_sizes.

Methods

__call__

View source

__call__(
    x
)

Returns regularization loss for x.

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.