---
title: "ELU"
sidebar_label: "ELU"
description: "The clika_runtime.nn ELU class."
---

<!-- Generated by tools/api_reference/generate_api_docs.py. Do not edit. -->

ELU(alpha=1.0, inplace=False, *, scale=1.0, input_scale=1.0)

    Exponential linear unit: scale * input for input > 0, scale * alpha *
    (exp(input_scale * input) - 1) otherwise.

    The module form of ``clika_runtime.nn.functional.elu``: construct it once
    with the settings, then call it like a function.

    Args:
        alpha: the negative-side saturation value.
        inplace: whether the forward writes the result into its input and
            returns that input.
        scale: multiplies the whole result.
        input_scale: scales the exponent on the negative side.
    

## `__init__`

```python
__init__(self, alpha: 'float' = 1.0, inplace: 'bool' = False, *, scale: 'float' = 1.0, input_scale: 'float' = 1.0) -> 'None'
```

Initialize self.  See help(type(self)) for accurate signature.

## `extra_repr`

```python
extra_repr(self) -> 'str'
```

extra_repr() -> str

One line of per-class detail for :meth:`__repr__`; a layer prints
its geometry here (``in_features=64, out_features=256``).

## `forward`

```python
forward(self, input: 'Tensor') -> 'Tensor'
```

forward(input) -> Tensor

Runs ``clika_runtime.nn.functional.elu`` on ``input`` with the stored
settings; returns a new tensor, or ``input`` itself, holding the
result, when ``inplace`` is set.