# tf.keras.activations.deserialize

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/activations.py#L605-L664) |

Returns activation function given a string identifier.

#### View aliases


**Compat aliases for migration**

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

\`tf.compat.v1.keras.activations.deserialize\`

<br />

    tf.keras.activations.deserialize(
        name, custom_objects=None, use_legacy_format=False
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `name` | The name of the activation function. |
| `custom_objects` | Optional `{function_name: function_obj}` dictionary listing user-provided activation functions. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| Corresponding activation function. ||

<br />

#### Example:

    tf.keras.activations.deserialize('linear')
     <function linear at 0x1239596a8>
    tf.keras.activations.deserialize('sigmoid')
     <function sigmoid at 0x123959510>
    tf.keras.activations.deserialize('abcd')
    Traceback (most recent call last):

    ValueError: Unknown activation function 'abcd' cannot be deserialized.

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | `Unknown activation function` if the input string does not denote any defined Tensorflow activation function. |

<br />