W3cubDocs

/TensorFlow 2.3

tf.keras.experimental.NoisyLinearCosineDecay

View source on GitHub

A LearningRateSchedule that uses a noisy linear cosine decay schedule.

Inherits From: LearningRateSchedule

See [Bello et al., ICML2017] Neural Optimizer Search with RL. https://arxiv.org/abs/1709.07417

For the idea of warm starts here controlled by num_periods, see [Loshchilov & Hutter, ICLR2016] SGDR: Stochastic Gradient Descent with Warm Restarts. https://arxiv.org/abs/1608.03983

Note that linear cosine decay is more aggressive than cosine decay and larger initial learning rates can typically be used.

When training a model, it is often recommended to lower the learning rate as the training progresses. This schedule applies a noisy linear cosine 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):
  step = min(step, decay_steps)
  linear_decay = (decay_steps - step) / decay_steps)
  cosine_decay = 0.5 * (
      1 + cos(pi * 2 * num_periods * step / decay_steps))
  decayed = (alpha + linear_decay + eps_t) * cosine_decay + beta
  return initial_learning_rate * decayed

where eps_t is 0-centered gaussian noise with variance initial_variance / (1 + global_step) ** variance_decay

Example usage:

decay_steps = 1000
lr_decayed_fn = (
  tf.keras.experimental.NoisyLinearCosineDecay(
    initial_learning_rate, decay_steps))

You can pass this schedule directly into a tf.keras.optimizers.Optimizer as the learning rate. The learning rate schedule is also serializable and deserializable using tf.keras.optimizers.schedules.serialize and tf.keras.optimizers.schedules.deserialize.

Returns
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.
Args
initial_learning_rate A scalar float32 or float64 Tensor or a Python number. The initial learning rate.
decay_steps A scalar int32 or int64 Tensor or a Python number. Number of steps to decay over.
initial_variance initial variance for the noise. See computation above.
variance_decay decay for the noise's variance. See computation above.
num_periods Number of periods in the cosine part of the decay. See computation above.
alpha See computation above.
beta See computation above.
name String. Optional name of the operation. Defaults to 'NoisyLinearCosineDecay'.

Methods

from_config

View source

Instantiates a LearningRateSchedule from its config.

Args
config Output of get_config().
Returns
A LearningRateSchedule instance.

get_config

View source

__call__

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.
https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/keras/experimental/NoisyLinearCosineDecay