tf.keras.layers.GaussianNoise

TensorFlow 1 version View source on GitHub

Apply additive zero-centered Gaussian noise.

Inherits From: Layer

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.

stddev Float, standard deviation of the noise distribution.

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).

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.

Output shape:

Same shape as input.