Practical Deep Learning for Computer Vision with Python

DeepDream, Keypoint Detection, Image Captioning with KerasNLP Transformers and ConvNets, Semantic Segmentation with DeepLabV3+, Real-Time Object Detection from Videos with YOLOv5, Large-Scale Breast Cancer Classification... and more. Computer Vision is an exciting and almost prohibitively large field - and it's experiencing the largest advancements it has ever seen, in the past few years. We won't be doing classification of MNIST digits or MNIST fashion. They served their part a long time ago. Too many learning resources are focusing on basic datasets and basic architectures before letting advanced black-box architectures shoulder the burden of performance. We want to focus on demystification, practicality, understanding, intuition and real projects. Want to learn how you can make a difference? We'll take you on a ride from the way our brains process images to writing a research-grade deep learning classifier for breast cancer to reading and implementing papers, to deep learning networks that "hallucinate", teaching you the principles and theory through practical work, equipping you with the know-how and tools to become an expert at applying deep learning to solve computer vision. There's a plethora of tools, libraries and concepts used to make work easier and its results more robust. Also, these tools don't always work, especially when you want to combine them - you should know why you're applying a tool or library and when they can make a difference. We want this book to not only teach you the technical side of Computer Vision, but also how to be a Computer Vision engineer. It's meant for the researcher looking to apply computer vision to their field (medical imagery, agriculture, manufacturing, urbanism, etc.), the student who's looking to break into new roles, the software engineer to empower their code and for the data enthusiast. This book was written for anyone with a basic understanding of machine learning and deep learning looking to orient themselves towards, or initially step into, computer vision. The book primarily uses Keras - the official high-level API for TensorFlow, with some PyTorch in later lessons. While prerequisite knowledge of Keras isn't strictly required, it will undoubtedly help. I won't be explaining what an activation function is, how cross-entropy works, or what weights and biases are. There are amazing resources covering these topics, ranging from free blogs to paid books - and covering these topics would inherently steer the focus of the book in a different direction than it's intended to be set in. The book is written to be advanced but beginner-friendly, with layers to be extracted through multiple reads. Contents Preface Introduction to Computer Vision Guide to Convolutional Neural Networks Guided Project: Building Your First Convolutional Neural Network With Keras Overfitting Is Your Friend, Not Your Foe Image Classification with Transfer Learning ‑ Creating Cutting Edge CNN Models Guided Project ‑ Breast Cancer Classification with Keras Convolutional Neural Networks ‑ Beyond Basic Architectures Working with KerasCV Object Detection and Segmentation ‑ R‑CNNs, RetinaNet, SSD, YOLO... Guided Project: Real‑Time Road Sign Detection with YOLOv5 Guided Project: Image Captioning with CNNs and Transformers Guided Project: DeepLabV3+ Semantic Segmentation with Keras DeepDream ‑ Neural Networks That Hallucinate? Optimizing Deep Learning Models for Computer Vision