# tf.nn.elu

<br />

|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 2 version](https://www.tensorflow.org/api_docs/python/tf/nn/elu) |

Computes exponential linear: `exp(features) - 1` if \< 0, `features` otherwise.

#### View aliases


**Compat aliases for migration**

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

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

<br />

    tf.nn.elu(
        features, name=None
    )

See [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](http://arxiv.org/abs/1511.07289)

<br />

<br />

<br />

| ## Args ||
|---|---|
| `features` | A `Tensor`. Must be one of the following types: `half`, `bfloat16`, `float32`, `float64`. |
| `name` | A name for the operation (optional). |

<br />

<br />

<br />

<br />

| ## Returns ||
|---|---|
| A `Tensor`. Has the same type as `features`. ||

<br />