Who this book is for

The reader wants to know how to apply deep learning to computer vision problems such as classification, detection, retrieval, segmentation, generation, captioning, and video classification. The reader also wants to understand how to achieve good accuracy under various constraints such as less data, imbalanced classes, and noise. Then the reader also wants to know how to deploy trained models on various platforms (AWS, Google Cloud, Raspberry Pi, and mobile phones). After completing this book, the reader should be able to develop code for problems of person detection, face recognition, product search, medical image segmentation, image generation, image captioning, video classification, and so on.