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


This chapter covered the necessary background knowledge and standard hyperparameters to help you fine-tune Detectron2’s solvers. Specifically, it showed you how to use TensorBoard to analyze training results and find insights. Then, we utilized the code and visualization approach to illustrate and find appropriate hyperparameters for Detectron2’s solver (optimizer). This chapter also provided a set of hyperparameters deemed suitable for the Detectron2 object detection model, which was trained on a brain tumor dataset. As an exercise, use all the configurations produced in this chapter, perform training experiments, load the results into TensorBoard, and analyze the differences and how these configurations improve accuracy.

This chapter covered the standard set of techniques and hyperparameters since they can be used to fine-tune machine learning in general. The following three chapters will cover fine-tuning techniques for fine-tuning object detection models...