# tf.keras.optimizers.schedules.CosineDecay

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.7.0/keras/optimizer_v2/learning_rate_schedule.py#L550-L641) |

A LearningRateSchedule that uses a cosine decay schedule.

Inherits From: [`LearningRateSchedule`](https://www.tensorflow.org/versions/r2.7/api_docs/python/tf/keras/optimizers/schedules/LearningRateSchedule)

#### View aliases


**Main aliases**

[`tf.keras.experimental.CosineDecay`](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/schedules/CosineDecay), [`tf.optimizers.schedules.CosineDecay`](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/schedules/CosineDecay)
**Compat aliases for migration**

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

[`tf.compat.v1.keras.experimental.CosineDecay`](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/schedules/CosineDecay), [`tf.compat.v1.keras.optimizers.schedules.CosineDecay`](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/schedules/CosineDecay)

<br />

    tf.keras.optimizers.schedules.CosineDecay(
        initial_learning_rate, decay_steps, 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
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 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.
It is computed as:

    def decayed_learning_rate(step):
      step = min(step, decay_steps)
      cosine_decay = 0.5 * (1 + cos(pi * step / decay_steps))
      decayed = (1 - alpha) * cosine_decay + alpha
      return initial_learning_rate * decayed

#### Example usage:

    decay_steps = 1000
    lr_decayed_fn = tf.keras.optimizers.schedules.CosineDecay(
        initial_learning_rate, decay_steps)

You can pass this schedule directly into a [`tf.keras.optimizers.Optimizer`](https://www.tensorflow.org/versions/r2.7/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/r2.7/api_docs/python/tf/keras/optimizers/schedules/serialize) and
[`tf.keras.optimizers.schedules.deserialize`](https://www.tensorflow.org/versions/r2.7/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. |
| `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'. |

<br />

## Methods

### `from_config`

[View source](https://github.com/keras-team/keras/tree/v2.7.0/keras/optimizer_v2/learning_rate_schedule.py#L78-L88)

    @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/v2.7.0/keras/optimizer_v2/learning_rate_schedule.py#L635-L641)

    get_config()

### `__call__`

[View source](https://github.com/keras-team/keras/tree/v2.7.0/keras/optimizer_v2/learning_rate_schedule.py#L619-L633)

    __call__(
        step
    )

Call self as a function.