Module: tf.keras.optimizers

DO NOT EDIT.

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

Modules

legacy module: DO NOT EDIT.

schedules module: DO NOT EDIT.

Classes

class Adadelta: Optimizer that implements the Adadelta algorithm.

class Adafactor: Optimizer that implements the Adafactor algorithm.

class Adagrad: Optimizer that implements the Adagrad algorithm.

class Adam: Optimizer that implements the Adam algorithm.

class AdamW: Optimizer that implements the AdamW algorithm.

class Adamax: Optimizer that implements the Adamax algorithm.

class Ftrl: Optimizer that implements the FTRL algorithm.

class Lion: Optimizer that implements the Lion algorithm.

class LossScaleOptimizer: An optimizer that dynamically scales the loss to prevent underflow.

class Nadam: Optimizer that implements the Nadam algorithm.

class Optimizer: A class for Tensorflow specific optimizer logic.

class RMSprop: Optimizer that implements the RMSprop algorithm.

class SGD: Gradient descent (with momentum) optimizer.

Functions

deserialize(...): Returns a Keras optimizer object via its configuration.

get(...): Retrieves a Keras Optimizer instance.

serialize(...): Returns the optimizer configuration as a Python 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.