---
title: "SmoothL1Loss"
sidebar_label: "SmoothL1Loss"
description: "The clika_runtime.nn SmoothL1Loss class."
---

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

SmoothL1Loss(reduction="mean", beta=1.0)

    Squared error below ``beta``, absolute error above it, between ``input``
    and ``target``.

    The module form of ``clika_runtime.nn.functional.smooth_l1_loss``:
    construct it once with the settings, then call it like a function.

    Args:
        reduction: how the elementwise losses reduce.
        beta: the switch point between the quadratic and the linear regime.
    

## `__init__`

```python
__init__(self, reduction: '_Reduction' = 'mean', beta: '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', target: 'Tensor') -> 'Tensor'
```

forward(input, target) -> Tensor

Runs ``clika_runtime.nn.functional.smooth_l1_loss`` on ``input``,
``target`` with the stored settings; returns a new tensor.