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

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

Dropout(p=0.5, inplace=False)

    Zero each element with probability ``p`` and scale the rest by
    ``1 / (1 - p)`` while the module is in training mode; in evaluation mode
    the input passes through unchanged (the same tensor object).
    

## `forward`

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

forward(input) -> Tensor