tf.keras.experimental.CosineDecayRestarts

TensorFlow 1 version View source on GitHub

A LearningRateSchedule that uses a cosine decay schedule with restarts.

Inherits From: LearningRateSchedule

tf.keras.experimental.CosineDecayRestarts(
    initial_learning_rate, first_decay_steps, t_mul=2.0, m_mul=1.0, alpha=0.0,
    name=None
)

Args:

  • initial_learning_rate: A scalar float32 or float64 Tensor or a Python number. The initial learning rate.
  • first_decay_steps: A scalar int32 or int64 Tensor or a Python number. Number of steps to decay over.
  • t_mul: A scalar float32 or float64 Tensor or a Python number. Used to derive the number of iterations in the i-th period
  • m_mul: A scalar float32 or float64 Tensor or a Python number. Used to derive the initial learning rate of the i-th period:
  • alpha: A scalar float32 or float64 Tensor or a Python number. Minimum learning rate value as a fraction of the initial_learning_rate.
  • name: String. Optional name of the operation. Defaults to 'SGDRDecay'.

Methods

__call__

View source

__call__(
    step
)

Call self as a function.

from_config

View source

@classmethod
from_config(
    config
)

Instantiates a LearningRateSchedule from its config.

Args:

  • config: Output of get_config().

Returns:

A LearningRateSchedule instance.

get_config

View source

get_config()