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)
Part 1: Introduction to Detectron2
Part 2: Developing Custom Object Detection Models
Part 3: Developing a Custom Detectron2 Model for Instance Segmentation Tasks
Part 4: Deploying Detectron2 Models into Production

Inspecting training histories with TensorBoard

Before fine-tuning models, it is essential to understand the evaluation metrics that are measured during training, such as training losses (for example, classification losses and localization losses), learning rate changes, and validation measurements on the test set (for example, [email protected]), which change over time. These metrics allow us to understand the training processes for debugging and fine-tuning models. Detectron2’s logger automatically logs the evaluation metrics for training and testing data in a format that is usable by TensorBoard.

TensorBoard ( offers tools and visualizations so that we can explore training and evaluation processes in machine learning experiments. The following code snippet downloads the training logs for the two experiments we carried out in Chapter 5 and unzips them:

# download and extract
!wget {}
!wget {url_to_object_detector_hook...