# tf.keras.losses.get

<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/losses.py#L2890-L2936) |

Retrieves a Keras loss as a `function`/`Loss` class instance.

#### View aliases


**Main aliases**

[`tf.losses.get`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/get)
**Compat aliases for migration**

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

\`tf.compat.v1.keras.losses.get\`

<br />

    tf.keras.losses.get(
        identifier
    )

The `identifier` may be the string name of a loss function or `Loss` class.

    loss = tf.keras.losses.get("categorical_crossentropy")
    type(loss)
    <class 'function'>
    loss = tf.keras.losses.get("CategoricalCrossentropy")
    type(loss)
    <class '...keras.losses.CategoricalCrossentropy'>

You can also specify `config` of the loss to this function by passing dict
containing `class_name` and `config` as an identifier. Also note that the
`class_name` must map to a `Loss` class

    identifier = {"class_name": "CategoricalCrossentropy",
                  "config": {"from_logits": True} }
    loss = tf.keras.losses.get(identifier)
    type(loss)
    <class '...keras.losses.CategoricalCrossentropy'>

<br />

<br />

<br />

| ## Args ||
|---|---|
| `identifier` | A loss identifier. One of None or string name of a loss function/class or loss configuration dictionary or a loss function or a loss class instance. |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A Keras loss as a `function`/ `Loss` class instance. ||

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | If `identifier` cannot be interpreted. |

<br />