# tfl.lattice_layer.TorsionRegularizer

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/lattice_layer.py#L938-L998) |

Torsion regularizer for [`tfl.layers.Lattice`](https://www.tensorflow.org/lattice/api_docs/python/tfl/layers/Lattice) layer.

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

Lattice torsion regularizer penalizes how much the lattice function twists
from side-to-side (see
[publication](http://jmlr.org/papers/v17/15-243.html)).

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)

<br />

<br />

<br />

| ## Args ||
|---|---|
| `lattice_sizes` | Lattice sizes of [`tfl.layers.Lattice`](https://www.tensorflow.org/lattice/api_docs/python/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. The amount of regularization for the interaction term between two dimensions is the product of the corresponding per dimension amounts. |
| `l2` | l2 regularization amount. Either single float or list or tuple of floats to specify different regularization amount per dimension. The amount of regularization for the interaction term between two dimensions is the product of the corresponding per dimension amounts. |

<br />

## 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.

<br />

<br />

<br />

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

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A regularizer instance. ||

<br />

### `get_config`

[View source](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/lattice_layer.py#L992-L998)

    get_config()

Standard Keras config for serialization.

### `__call__`

[View source](https://github.com/tensorflow/lattice/blob/v2.1.1/tensorflow_lattice/python/lattice_layer.py#L985-L990)

    __call__(
        x
    )

Returns regularization loss for `x`.