Chapter 1, Computer Vision and Neural Networks, introduces you to computer vision and deep learning, providing some theoretical background and teaching you how to implement and train a neural network for visual recognition from scratch.
Chapter 2, TensorFlow Basics and Training a Model, goes through TensorFlow 2 concepts related to computer vision, as well as some more advanced notions. It introduces Keras—now a submodule of TensorFlow—and describes the training of a simple recognition method implemented with these frameworks.
Chapter 3, Modern Neural Networks, presents CNNs and explains how they have revolutionized computer vision. This chapter also introduces regularization tools and modern optimization algorithms that can be used to train more robust recognition systems.
Chapter 4, Influential Classification Tools, provides theoretical details and practical code to expertly apply state-of-the-art solutions—such as Inception and ResNet—to the classification of images. This chapter also explains what makes transfer learning a key concept in machine learning, and how it can be performed with TensorFlow 2.
Chapter 5, Object Detection Models, covers the architecture of two methods to detect specific objects in images—You Only Look Once, known for its speed, and Faster R-CNN, known for its accuracy.
Chapter 6, Enhancing and Segmenting Images, introduces autoencoders and how networks such as U-Net and FCN can be applied to image denoising, semantic segmentation, and more.
Chapter 7, Training on Complex and Scarce Datasets, focuses on solutions to efficiently collect and preprocess datasets for your deep learning applications. TensorFlow tools that build optimized data pipelines are presented, as well as various solutions to compensate for data scarcity (image rendering, domain adaptation, and generative networks such as VAEs and GANs).
Chapter 8, Video and Recurrent Neural Networks, covers recurrent neural networks, presenting the more advanced version known as the long short-term memory architecture. It provides practical code to apply LSTMs to action recognition in video.
Chapter 9, Optimizing Models and Deploying on Mobile Devices, details model optimization in terms of speed, disk space, and computational performance. It goes through the deployment of TensorFlow solutions on mobile devices and in the browser, using a practical example.
Appendix, Migrating from TensorFlow 1 to TensorFlow 2, provides some information about TensorFlow 1, highlighting key changes introduced in TensorFlow 2. A guide to migrate older projects to the latest version is also included. Finally, per-chapter references are listed for those who want to dive deeper.
