W3cubDocs

/TensorFlow 2.9

Module: tf.keras.regularizers

Built-in regularizers.

Classes

class L1: A regularizer that applies a L1 regularization penalty.

class L1L2: A regularizer that applies both L1 and L2 regularization penalties.

class L2: A regularizer that applies a L2 regularization penalty.

class OrthogonalRegularizer: A regularizer that encourages input vectors to be orthogonal to each other.

class Regularizer: Regularizer base class.

class l1: A regularizer that applies a L1 regularization penalty.

class l2: A regularizer that applies a L2 regularization penalty.

class orthogonal_regularizer: A regularizer that encourages input vectors to be orthogonal to each other.

Functions

deserialize(...)

get(...): Retrieve a regularizer instance from a config or identifier.

l1_l2(...): Create a regularizer that applies both L1 and L2 penalties.

serialize(...)

© 2022 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 4.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.9/api_docs/python/tf/keras/regularizers