# tf.keras.constraints.NonNeg

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.7.0/keras/constraints.py#L120-L128) |

Constrains the weights to be non-negative.

Inherits From: [`Constraint`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/keras/constraints/Constraint)

#### View aliases


**Main aliases**

[`tf.keras.constraints.non_neg`](https://www.tensorflow.org/api_docs/python/tf/keras/constraints/NonNeg)
**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

[`tf.compat.v1.keras.constraints.NonNeg`](https://www.tensorflow.org/api_docs/python/tf/keras/constraints/NonNeg), [`tf.compat.v1.keras.constraints.non_neg`](https://www.tensorflow.org/api_docs/python/tf/keras/constraints/NonNeg)

<br />

Also available via the shortcut function [`tf.keras.constraints.non_neg`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/keras/constraints/NonNeg).

## Methods

### `get_config`

[View source](https://github.com/keras-team/keras/tree/v2.7.0/keras/constraints.py#L67-L76)

    get_config()

Returns a Python dict of the object config.

A constraint config is a Python dictionary (JSON-serializable) that can
be used to reinstantiate the same object.

<br />

<br />

<br />

| Returns ||
|---|---|
| Python dict containing the configuration of the constraint object. ||

<br />

### `__call__`

[View source](https://github.com/keras-team/keras/tree/v2.7.0/keras/constraints.py#L127-L128)

    __call__(
        w
    )

Applies the constraint to the input weight variable.

By default, the inputs weight variable is not modified.
Users should override this method to implement their own projection
function.

<br />

<br />

<br />

| Args ||
|---|---|
| `w` | Input weight variable. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| Projected variable (by default, returns unmodified inputs). ||

<br />