<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.15.0/keras/optimizers/schedules/learning_rate_schedule.py#L770-L911) |

A LearningRateSchedule that uses a cosine decay schedule with restarts.

Inherits From: [`LearningRateSchedule`](https://www.tensorflow.org/versions/r2.15/api_docs/python/tf/keras/optimizers/schedules/LearningRateSchedule)

#### View aliases


**Main aliases**

\`tf.keras.experimental.CosineDecayRestarts\`

<br />

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

See [Loshchilov \& Hutter, ICLR2016](https://arxiv.org/abs/1608.03983),
SGDR: Stochastic Gradient Descent with Warm Restarts.

When training a model, it is often useful to lower the learning rate as
the training progresses. This schedule applies a cosine decay function with
restarts 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 is 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.

The learning rate multiplier first decays
from 1 to `alpha` for `first_decay_steps` steps. Then, a warm
restart is performed. Each new warm restart runs for `t_mul` times more
steps and with `m_mul` times initial learning rate as the new learning rate.

#### Example usage:

    first_decay_steps = 1000
    lr_decayed_fn = (
      tf.keras.optimizers.schedules.CosineDecayRestarts(
          initial_learning_rate,
          first_decay_steps))

You can pass this schedule directly into a [`tf.keras.optimizers.Optimizer`](https://www.tensorflow.org/versions/r2.15/api_docs/python/tf/keras/optimizers/Optimizer)
as the learning rate. The learning rate schedule is also serializable and
deserializable using [`tf.keras.optimizers.schedules.serialize`](https://www.tensorflow.org/versions/r2.15/api_docs/python/tf/keras/optimizers/schedules/serialize) and
[`tf.keras.optimizers.schedules.deserialize`](https://www.tensorflow.org/versions/r2.15/api_docs/python/tf/keras/optimizers/schedules/deserialize).

<br />

<br />

<br />

| ## 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`. ||

<br />

<br />

<br />

<br />

| ## 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'. |

<br />

## Methods

### `from_config`

[View source](https://github.com/keras-team/keras/tree/v2.15.0/keras/optimizers/schedules/learning_rate_schedule.py#L88-L98)

    @classmethod
    from_config(
        config
    )

Instantiates a `LearningRateSchedule` from its config.

<br />

<br />

<br />

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

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| A `LearningRateSchedule` instance. ||

<br />

### `get_config`

[View source](https://github.com/keras-team/keras/tree/v2.15.0/keras/optimizers/schedules/learning_rate_schedule.py#L903-L911)

    get_config()

### `__call__`

[View source](https://github.com/keras-team/keras/tree/v2.15.0/keras/optimizers/schedules/learning_rate_schedule.py#L849-L901)

    __call__(
        step
    )

Call self as a function.