tf.keras.optimizers.schedules.LearningRateSchedule

View source on GitHub

The learning rate schedule base class.

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.optimizers.schedules.LearningRateSchedule

You can use a learning rate schedule to modulate how the learning rate of your optimizer changes over time.

Several built-in learning rate schedules are available, such as tf.keras.optimizers.schedules.ExponentialDecay or tf.keras.optimizers.schedules.PiecewiseConstantDecay:

lr_schedule = keras.optimizers.schedules.ExponentialDecay(
    initial_learning_rate=1e-2,
    decay_steps=10000,
    decay_rate=0.9)
optimizer = keras.optimizers.SGD(learning_rate=lr_schedule)

A LearningRateSchedule instance can be passed in as the learning_rate argument of any optimizer.

To implement your own schedule object, you should implement the __call__ method, which takes a step argument (scalar integer tensor, the current training step count). Like for any other Keras object, you can also optionally make your object serializable by implementing the get_config and from_config methods.

Example:

class MyLRSchedule(tf.keras.optimizers.schedules.LearningRateSchedule):

  def __init__(self, initial_learning_rate):
    self.initial_learning_rate = initial_learning_rate

  def __call__(self, step):
     return self.initial_learning_rate / (step + 1)

optimizer = tf.keras.optimizers.SGD(learning_rate=MyLRSchedule(0.1))

Methods

from_config

View source

@classmethod
from_config(
    config
)

Instantiates a LearningRateSchedule from its config.

Args
config	Output of get_config().

Returns
A LearningRateSchedule instance.

get_config

View source

@abc.abstractmethod
get_config()

__call__

View source

@abc.abstractmethod
__call__(
    step
)

Call self as a function.