# tf.keras.layers.GaussianNoise

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/layers/regularization/gaussian_noise.py#L28-L81) |

Apply additive zero-centered Gaussian noise.

Inherits From: [`Layer`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/keras/layers/Layer), [`Module`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/Module)

#### View aliases


**Compat aliases for migration**

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

\`tf.compat.v1.keras.layers.GaussianNoise\`

<br />

    tf.keras.layers.GaussianNoise(
        stddev, seed=None, **kwargs
    )

This is useful to mitigate overfitting
(you could see it as a form of random data augmentation).
Gaussian Noise (GS) is a natural choice as corruption process
for real valued inputs.

As it is a regularization layer, it is only active at training time.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `stddev` | Float, standard deviation of the noise distribution. |
| `seed` | Integer, optional random seed to enable deterministic behavior. |

<br />

<br />

<br />

<br />

| ## Call arguments ||
|---|---|
| `inputs` | Input tensor (of any rank). |
| `training` | Python boolean indicating whether the layer should behave in training mode (adding noise) or in inference mode (doing nothing). |

<br />

<br />

<br />

<br />

| ## Input shape ||
|---|---|
| Arbitrary. Use the keyword argument `input_shape` (tuple of integers, does not include the samples axis) when using this layer as the first layer in a model. ||

<br />

<br />

<br />

<br />

| ## Output shape ||
|---|---|
| Same shape as input. ||

<br />