tf.keras.layers.GaussianNoise
Stay organized with collections
Save and categorize content based on your preferences.
Apply additive zero-centered Gaussian noise.
Inherits From: Layer, Module
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.
Args |
|---|
stddev
|
Float, standard deviation of the noise distribution.
|
seed
|
Integer, optional random seed to enable deterministic behavior.
|
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).
|
|
|---|
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.
|
Output shape |
|---|
|
Same shape as input.
|
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. Some content is licensed under the numpy license.
Last updated 2023-10-06 UTC.
[null,null,["Last updated 2023-10-06 UTC."],[],[],null,["# tf.keras.layers.GaussianNoise\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.14.0/keras/layers/regularization/gaussian_noise.py#L28-L81) |\n\nApply additive zero-centered Gaussian noise.\n\nInherits From: [`Layer`](../../../tf/keras/layers/Layer), [`Module`](../../../tf/Module) \n\n tf.keras.layers.GaussianNoise(\n stddev, seed=None, **kwargs\n )\n\nThis is useful to mitigate overfitting\n(you could see it as a form of random data augmentation).\nGaussian Noise (GS) is a natural choice as corruption process\nfor real valued inputs.\n\nAs it is a regularization layer, it is only active at training time.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------|-----------------------------------------------------------------|\n| `stddev` | Float, standard deviation of the noise distribution. |\n| `seed` | Integer, optional random seed to enable deterministic behavior. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Call arguments -------------- ||\n|------------|---------------------------------------------------------------------------------------------------------------------------------|\n| `inputs` | Input tensor (of any rank). |\n| `training` | Python boolean indicating whether the layer should behave in training mode (adding noise) or in inference mode (doing nothing). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Input shape ----------- ||\n|---|---|\n| 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. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Output shape ------------ ||\n|---|---|\n| Same shape as input. ||\n\n\u003cbr /\u003e"]]
View source on GitHub