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

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

KLDivLoss(reduction="mean", log_target=False)

    Kullback-Leibler divergence of ``target`` from ``input``, where ``input``
    holds log-probabilities.

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

    Args:
        reduction: how the elementwise losses reduce.
        log_target: reads ``target`` as log-probabilities.
    

## `__init__`

```python
__init__(self, reduction: '_Reduction' = 'mean', log_target: 'bool' = False) -> '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.kl_div`` on ``input``, ``target``
with the stored settings; returns a new tensor.