Module: tf.keras.optimizers.schedules  |  TensorFlow v2.16.1 (original) (raw)

Module: tf.keras.optimizers.schedules

Stay organized with collections Save and categorize content based on your preferences.

DO NOT EDIT.

This file was autogenerated. Do not edit it by hand, since your modifications would be overwritten.

Classes

class CosineDecay: A LearningRateSchedule that uses a cosine decay with optional warmup.

class CosineDecayRestarts: A LearningRateSchedule that uses a cosine decay schedule with restarts.

class ExponentialDecay: A LearningRateSchedule that uses an exponential decay schedule.

class InverseTimeDecay: A LearningRateSchedule that uses an inverse time decay schedule.

class LearningRateSchedule: The learning rate schedule base class.

class PiecewiseConstantDecay: A LearningRateSchedule that uses a piecewise constant decay schedule.

class PolynomialDecay: A LearningRateSchedule that uses a polynomial decay schedule.

Functions

deserialize(...): Instantiates a LearningRateSchedule object from a serialized form.

serialize(...): Serializes a LearningRateSchedule into a JSON-compatible dict.

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 2024-04-26 UTC.