A problem-solving approach to learning all about Detectron2, getting up and running in no time with existing cutting-edge models, and complete steps for implementing future computer vision applications in custom domains.
Key Features
- Learn how to tackle common computer vision tasks in modern businesses with Detectron2
- Leverage Detectron2 performance tuning techniques to control the model's finest details
- Deploy Detectron2 models into production and develop Detectron2 models for mobile devices
Book Description
Computer vision has become a critical success factor in many modern businesses such as automobiles, robotics, and manufacturing, and its market is growing rapidly. This book will help you explore Detectron2. It is the next-generation library that provides cutting-edge detection and segmentation algorithms. Many research and practical projects at Facebook use it as a library to support computer vision tasks. Its models can be exported to TorchScript format, Caffe2, or TensorFlow for deployment.
This book will guide you step by step on how to use existing models in Detectron2 for computer vision tasks (object detection, instance segmentation, key-point detection, semantic detection, and panoptic segmentation). It also covers theories and visualizations of Detectron2's architectures and how each module in Detectron2 works. You will get to learn two complete hands-on, real-life projects (preparing data, training models, fine-tuning models, and deployments) for object detection and instance segmentation tasks using Detectron2. This book also covers steps for deploying Detectron2 models into production and developing Detectron2 applications for mobile devices.
By the end of the book, you will have sound theoretical knowledge and valuable practical skills to solve advanced computer vision tasks using Detectron2.
What you will learn
- Build computer vision applications using existing models in Detectron2
- Learn concepts underlying Detectron2's architecture and components
- Develop a real-life project for object detection using Detectron2
- Develop a real-life project for object segmentation using Detectron2
- Improve model accuracy using Detectron2 performance tuning techniques
- Deploy Detectron2 models into production
- Develop Detectron2 applications for mobile devices
Who This Book Is For
If you are a deep learning application developer, researcher, or software developer with some prior knowledge about deep learning, this book is for you to get started and develop deep learning models for computer vision applications. Even if you are an expert in computer vision and curious about the features of Detectron2, or you would like to learn some cutting-edge deep learning design patterns, you will find this book helpful. Some Android programming skills are advantageous if you want to deploy computer vision applications on mobile devices.
Table of Contents
- Introduction to Detectron2 and computer vision tasks
- Developing computer vision applications using existing Detectron2 models
- Data preparation for object detection applications
- Selecting the base models
- Training custom object detection models
- Inspecting training results and fine-tuning Detectron2 solver
- Fine-tuning object detection models
- Image data augmentation techniques
- Applying train time and test time image augmentations
- Training and fine-tuning instance segmentation models
- Deploying Detectron2 models
- Deploying Detectron2 models into mobile devices
