tf.keras.optimizers.schedules.deserialize

Instantiates a LearningRateSchedule object from a serialized form.

tf.keras.optimizers.schedules.deserialize(
    config, custom_objects=None
)

config The serialized form of the LearningRateSchedule. Dictionary of the form {'class_name': str, 'config': dict}.
custom_objects A dictionary mapping class names (or function names) of custom (non-Keras) objects to class/functions.

A LearningRateSchedule object.

Example:

# Configuration for PolynomialDecay
config = {
    'class_name': 'PolynomialDecay',
    'config': {'cycle': False,
        'decay_steps': 10000,
        'end_learning_rate': 0.01,
        'initial_learning_rate': 0.1,
        'name': None,
        'power': 0.5
    }
}
lr_schedule = keras.optimizers.schedules.deserialize(config)