TensorFlow 2.0 Beta is available Learn more

tf.keras.optimizers.schedules.LearningRateSchedule

Class LearningRateSchedule

A serializable learning rate decay schedule.

Aliases:

  • Class tf.compat.v1.keras.optimizers.schedules.LearningRateSchedule
  • Class tf.compat.v2.keras.optimizers.schedules.LearningRateSchedule
  • Class tf.compat.v2.optimizers.schedules.LearningRateSchedule
  • Class tf.keras.optimizers.schedules.LearningRateSchedule

Defined in python/keras/optimizer_v2/learning_rate_schedule.py.

LearningRateSchedules can be passed in as the learning rate of optimizers in tf.keras.optimizers. They can be serialized and deserialized using tf.keras.optimizers.schedules.serialize and tf.keras.optimizers.schedules.deserialize.

Methods

__call__

__call__(step)

from_config

@classmethod
from_config(
    cls,
    config
)

Instantiates a LearningRateSchedule from its config.

Args:

  • config: Output of get_config().

Returns:

A LearningRateSchedule instance.

get_config

get_config()