# tf.keras.experimental.CosineDecayRestarts

<br />

|---|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/keras/experimental/CosineDecayRestarts) | [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/optimizer_v2/learning_rate_schedule.py#L606-L726) |

A LearningRateSchedule that uses a cosine decay schedule with restarts.

Inherits From: [`LearningRateSchedule`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/keras/optimizers/schedules/LearningRateSchedule)

#### View aliases


**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

[`tf.compat.v1.keras.experimental.CosineDecayRestarts`](https://www.tensorflow.org/api_docs/python/tf/keras/experimental/CosineDecayRestarts), \`tf.compat.v2.keras.experimental.CosineDecayRestarts\`

<br />

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

<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/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/optimizer_v2/learning_rate_schedule.py#L50-L60)

    @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/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/optimizer_v2/learning_rate_schedule.py#L718-L726)

    get_config()

### `__call__`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/keras/optimizer_v2/learning_rate_schedule.py#L677-L716)

    __call__(
        step
    )

Call self as a function.