tf.keras.experimental.CosineDecay

A LearningRateSchedule that uses a cosine decay schedule.

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.experimental.CosineDecay, `tf.compat.v2.keras.experimental.CosineDecay`

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

@classmethod
from_config(
    config
)

Instantiates a LearningRateSchedule from its config.

Args
`config`	Output of `get_config()`.

Returns
A `LearningRateSchedule` instance.

get_config()

__call__(
    step
)

Call self as a function.