tfl.lattice_lib.torsion_regularizer
Returns Torsion regularization loss for Lattice
layer.
tfl.lattice_lib.torsion_regularizer(
weights, lattice_sizes, l1=0.0, l2=0.0
)
Lattice torsion regularizer penalizes how much the lattice function twists
from side-to-side (see
publication).
Consider a 3 x 2 lattice with weights w
:
w[3]-----w[4]-----w[5]
| | |
| | |
w[0]-----w[1]-----w[2]
In this case, the torsion regularizer is defined as:
l1 * (|w[4] + w[0] - w[3] - w[1]| + |w[5] + w[1] - w[4] - w[2]|) +
l2 * ((w[4] + w[0] - w[3] - w[1])^2 + (w[5] + w[1] - w[4] - w[2])^2)
Arguments |
weights
|
Lattice weights tensor of shape: (prod(lattice_sizes), units) .
|
lattice_sizes
|
List or tuple of integers which represents lattice sizes.
|
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. The amount for
the interaction term between i and j is the corresponding product of each
per feature amount.
|
Returns |
Laplacian regularization loss.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2024-08-02 UTC.
[null,null,["Last updated 2024-08-02 UTC."],[],[]]