# Image Preprocessing Operator

Authors: derekdqc

## Overview

This operator uses PyTorch to transform the image, such as cropping, PIL.Image and Tensor conversion, normalization and other operations on the image.

In computer vision (CV) directions, image transformations are usually an indispensable part, which can be used to pre-process images and enhance data. And transforms are common image transformations, they can be chained together using [`Compose`](https://pytorch.org/vision/stable/transforms.html#torchvision.transforms.Compose) in Pytorch.

## Interface

```python
__init__(self, size: int)
```

**Args:**

- size:
  - the size of the output image
  - supported types: `int`

```python
__call__(self, img: Union[Image.Image, torch.Tensor, str])
```

**Args:**

- img:
  - the input image to be processed
  - supported type: `PIL.image` or `str` (path of the image)

**Returns:**

The Operator returns a tuple `Tuple[('img_transformed', torch.Tensor)]` containing following fields:

- img_transformed:
  - the tensor of the transformed image
  - data type: `torch.Tensor`

## Requirements

You can get the required python package by [requirements.txt](./requirements.txt).

## How it works

The `towhee/transform-image` Operator is used for image transformation and is an important part of data preprocessing. It can be added to the pipeline and is usually used as the first custom operator of the pipeline. For example, it's the first Operator named processing within [image-embedding-resnet50](https://hub.towhee.io/towhee/image-embedding-resnet50) pipeline, and it is the red box in the picture below.

![img](./readme_src/operator.png)

## Reference

- https://pytorch.org/vision/stable/transforms.html