Mastering Computer Vision with TensorFlow 2.x

Preface

Computer vision is a technique by which machines gain human-level ability to visualize, process, and analyze images or videos. This book will focus on using TensorFlow to develop and train deep neural networks to solve advanced computer vision problems and deploy solutions on mobile and edge devices.

You will start with the key principles of computer vision and deep learning and learn about various models and architectures, along with their pros and cons. You will cover various architectures, such as VGG, ResNet, Inception, R-CNN, YOLO, and many more. You will use various visual search methods using transfer learning. The book will help you to learn about various advanced concepts of computer vision, including semantic segmentation, ...