Hands-On Computer Vision with Detectron2

2

Developing Computer Vision Applications Using Existing Detectron2 Models

This chapter guides you through the steps to develop applications for computer vision tasks using state-of-the-art models in Detectron2. Specifically, this chapter discusses the existing and pre-trained models in Detectron2’s Model Zoo and the steps to develop applications for object detection, instance segmentation, key-point detection, semantic segmentation, and panoptic segmentation using these models. Thus, you can quickly develop practical computer vision applications without having to train custom models.

By the end of this chapter, you will know what models are available in the Detectron2 Model Zoo. Furthermore, you will learn how to develop applications for vision ...