Module: tf.keras.layers.experimental

Public API for tf.keras.layers.experimental namespace.

Modules

preprocessing module: Public API for tf.keras.layers.experimental.preprocessing namespace.

class EinsumDense: A layer that uses tf.einsum as the backing computation.

class RandomFourierFeatures: Layer that projects its inputs into a random feature space.

class SyncBatchNormalization: Normalize and scale inputs or activations synchronously across replicas.

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 2022-05-17 UTC.