Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tf.keras.experimental.CosineDecay

TensorFlow 1 version View source on GitHub

A LearningRateSchedule that uses a cosine decay schedule.

Inherits From: LearningRateSchedule

tf.keras.experimental.CosineDecay(
    initial_learning_rate, decay_steps, alpha=0.0, name=None
)

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.
  • alpha: A scalar float32 or float64 Tensor or a Python number. Minimum learning rate value as a fraction of initial_learning_rate.
  • name: String. Optional name of the operation. Defaults to 'CosineDecay'.

Methods

__call__

View source

__call__(
    step
)

Call self as a function.

from_config

View source

@classmethod
from_config(
    cls, config
)

Instantiates a LearningRateSchedule from its config.

Args:

  • config: Output of get_config().

Returns:

A LearningRateSchedule instance.

get_config

View source

get_config()