Book Image

Hands-On Computer Vision with Detectron2

By : Van Vung Pham
5 (4)
Book Image

Hands-On Computer Vision with Detectron2

5 (4)
By: Van Vung Pham

Overview of this book

Computer vision is a crucial component of many modern businesses, including automobiles, robotics, and manufacturing, and its market is growing rapidly. This book helps you explore Detectron2, Facebook's next-gen library providing cutting-edge detection and segmentation algorithms. It’s used in research and practical projects at Facebook to support computer vision tasks, and its models can be exported to TorchScript or ONNX for deployment. The book provides you with step-by-step guidance on using existing models in Detectron2 for computer vision tasks (object detection, instance segmentation, key-point detection, semantic detection, and panoptic segmentation). You’ll get to grips with the theories and visualizations of Detectron2’s architecture and learn how each module in Detectron2 works. As you advance, you’ll build your practical skills by working on two real-life projects (preparing data, training models, fine-tuning models, and deployments) for object detection and instance segmentation tasks using Detectron2. Finally, you’ll deploy Detectron2 models into production and develop Detectron2 applications for mobile devices. By the end of this deep learning book, you’ll have gained sound theoretical knowledge and useful hands-on skills to help you solve advanced computer vision tasks using Detectron2.
Table of Contents (20 chapters)
1
Part 1: Introduction to Detectron2
4
Part 2: Developing Custom Object Detection Models
12
Part 3: Developing a Custom Detectron2 Model for Instance Segmentation Tasks
15
Part 4: Deploying Detectron2 Models into Production

Developing a keypoint detection application

Besides detecting objects, keypoint detection also indicates important parts of the detected objects called keypoints. These keypoints describe the detected object’s essential trait. This trait is often invariant to image rotation, shrinkage, translation, or distortion. The following sections detail the steps to develop a keypoint detection application using Detectron2 pre-trained models.

Selecting a configuration file

Detectron2 also provides a list of cutting-edge algorithms pre-trained for keypoint detection for human objects. For instance, Figure 2.7 shows the list of Mask R-CNN models pre-trained on the COCO Person Keypoint Detection dataset.

Figure 2.7: COCO Person Keypoint Detection baselines with Keypoint R-CNN

Figure 2.7: COCO Person Keypoint Detection baselines with Keypoint R-CNN

In this specific case, we select the X101-FPN pre-trained model. Again, the link to the configuration file is linked with the model name in the first column, and we only use the part...