# RetinaFace Face Detection 

*author: David Wang*



<br />



## Description

This operator detects faces in the images by using [RetinaFace](https://arxiv.org/abs/1905.00641) Detector. It will return the bounding box positions and the confidence scores of detected faces. This repo is an adaptaion from [biubug6/Pytorch_Retinaface](https://github.com/biubug6/Pytorch_Retinaface).


<br />


## Code Example

Load an image from path './turing.png' and use the pretrained RetinaFace model to generate face bounding boxes and confidence scores. 

 *Write the pipeline in simplified style:*

```python
import towhee

towhee.glob('turing.png') \
  .image_decode.cv2() \
  .face_detection.retinaface() \
  .show()

```
<img src="https://towhee.io/face-detection/retinaface/raw/branch/main/result1.png" alt="result1" style="height:20px;"/>

*Write a same pipeline with explicit inputs/outputs name specifications:*

```python
import towhee

towhee.glob['path']('turing.png') \
  .image_decode.cv2['path', 'img']() \
  .face_detection.retinaface['img', ('bbox','score')]() \
  .select['img', 'bbox', 'score']() \
  .show()
```

<img src="https://towhee.io/face-detection/retinaface/raw/branch/main/result2.png" alt="result2" style="height:60px;"/>


<br />



## Factory Constructor

Create the operator via the following factory method.

***face_detection.retinaface()***


<br />



## Interface

A face detection operator takes an image as input. It generates the bounding box positions and confidence scores back to ndarray.

**Parameters:**

​	***img:*** *towhee.types.Image (a sub-class of numpy.ndarray)* 

​	the image to detect faces.

​	supported types: numpy.ndarray

**Returns:**

*List[(int, int, int, int)]*

​	The detected face bounding boxes.

*List[float]*

​	The detected face bounding boxes confident scores.