/TensorFlow 2.3


View source on GitHub

A LearningRateSchedule that uses an inverse time decay schedule.

Inherits From: LearningRateSchedule

When training a model, it is often recommended to lower the learning rate as the training progresses. This schedule applies the inverse decay function to an optimizer step, given a provided initial learning rate. It requires a step value to compute the decayed learning rate. You can just pass a TensorFlow variable that you increment at each training step.

The schedule a 1-arg callable that produces a decayed learning rate when passed the current optimizer step. This can be useful for changing the learning rate value across different invocations of optimizer functions. It is computed as:

def decayed_learning_rate(step):
  return initial_learning_rate / (1 + decay_rate * step / decay_step)

or, if staircase is True, as:

def decayed_learning_rate(step):
  return initial_learning_rate / (1 + decay_rate * floor(step / decay_step))

You can pass this schedule directly into a tf.keras.optimizers.Optimizer as the learning rate. Example: Fit a Keras model when decaying 1/t with a rate of 0.5:

initial_learning_rate = 0.1
decay_steps = 1.0
decay_rate = 0.5
learning_rate_fn = keras.optimizers.schedules.InverseTimeDecay(
  initial_learning_rate, decay_steps, decay_rate)


model.fit(data, labels, epochs=5)
A 1-arg callable learning rate schedule that takes the current optimizer step and outputs the decayed learning rate, a scalar Tensor of the same type as initial_learning_rate.
initial_learning_rate A scalar float32 or float64 Tensor or a Python number. The initial learning rate.
decay_steps How often to apply decay.
decay_rate A Python number. The decay rate.
staircase Whether to apply decay in a discrete staircase, as opposed to continuous, fashion.
name String. Optional name of the operation. Defaults to 'InverseTimeDecay'.



View source

Instantiates a LearningRateSchedule from its config.

config Output of get_config().
A LearningRateSchedule instance.


View source


View source

Call self as a function.

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.