Save the date! Google I/O returns May 18-20 Register now

tf.keras.experimental.LinearCosineDecay

TensorFlow 2 version View source on GitHub

A LearningRateSchedule that uses a linear cosine decay schedule.

Inherits From: LearningRateSchedule

initial_learning_rate A scalar float32 or float64 Tensor or a Python number. The initial learning rate.
decay_steps A scalar int32 or int64 Tensor or a Python number. Number of steps to decay over.
num_periods Number of periods in the cosine part of the decay. See computation above.
alpha See computation above.
beta See computation above.
name String. Optional name of the operation. Defaults to 'LinearCosineDecay'.

Methods

from_config

View source

Instantiates a LearningRateSchedule from its config.

Args
config Output of get_config().

Returns
A LearningRateSchedule instance.

get_config

View source

__call__

View source

Call self as a function.