LearningRateSchedule class


The learning rate schedule base class.

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 keras.optimizers.schedules.ExponentialDecay or keras.optimizers.schedules.PiecewiseConstantDecay:

lr_schedule = keras.optimizers.schedules.ExponentialDecay(
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.


class MyLRSchedule(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 = keras.optimizers.SGD(learning_rate=MyLRSchedule(0.1))