# tf.keras.models.model_from_config

<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/saving/legacy/model_config.py#L27-L71) |

Instantiates a Keras model from its config.

#### View aliases


**Compat aliases for migration**

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

\`tf.compat.v1.keras.models.model_from_config\`

<br />

    tf.keras.models.model_from_config(
        config, custom_objects=None
    )

#### Usage:

    # for a Functional API model
    tf.keras.Model().from_config(model.get_config())

    # for a Sequential model
    tf.keras.Sequential().from_config(model.get_config())

<br />

<br />

<br />

| ## Args ||
|---|---|
| `config` | Configuration dictionary. |
| `custom_objects` | Optional dictionary mapping names (strings) to custom classes or functions to be considered during deserialization. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A Keras model instance (uncompiled). ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `TypeError` | if `config` is not a dictionary. |

<br />