detectron2/README.md

# Object Detection using Detectron2

*author: [filip-halt](https://github.com/filip-halt), [fzliu](https://github.com/fzliu)*

<br />

## Description

This operator uses Facebook's [Detectron2](https://github.com/facebookresearch/detectron2) library to compute bounding boxes, class labels, and class scores for detected objects in a given image.

<br />

## Code Example

```python
import towhee

towhee.glob('./towhee.jpg') \
      .image_decode.cv2() \
      .object_detection.detectron2(model_name='retinanet_resnet50') \
      .show()
```

## Factory Constructor

Create the operator via the following factory method

***object_detection.detectron2(model_name='retinanet_resnet50', thresh=0.5, num_classes=1000, skip_preprocess=False)***

**Parameters:**

***model_name:*** *str*

A string indicating which model to use.

***thresh:*** *float*

The threshold value for which an object is detected (default value: `0.5`). Set this value lower to detect more objects at the expense of accuracy, or higher to reduce the total number of detections but increase the quality of detected objects.