Advertisement

Advanced Applied Deep Learning

Convolutional Neural Networks and Object Detection

  • Umberto Michelucci
Book

Table of contents

  1. Front Matter
    Pages i-xviii
  2. Umberto Michelucci
    Pages 1-26
  3. Umberto Michelucci
    Pages 27-77
  4. Umberto Michelucci
    Pages 79-123
  5. Umberto Michelucci
    Pages 125-160
  6. Umberto Michelucci
    Pages 161-193
  7. Umberto Michelucci
    Pages 195-220
  8. Umberto Michelucci
    Pages 221-241
  9. Umberto Michelucci
    Pages 243-277
  10. Back Matter
    Pages 279-285

About this book

Introduction

Develop and optimize deep learning models with advanced architectures. This book teaches you the intricate details and subtleties of the algorithms that are at the core of convolutional neural networks. In Advanced Applied Deep Learning, you will study advanced topics on CNN and object detection using Keras and TensorFlow. 

Along the way, you will look at the fundamental operations in CNN, such as convolution and pooling, and then look at more advanced architectures such as inception networks, resnets, and many more. While the book discusses theoretical topics, you will discover how to work efficiently with Keras with many tricks and tips, including how to customize logging in Keras with custom callback classes, what is eager execution, and how to use it in your models.

Finally, you will study how object detection works, and build a complete implementation of the YOLO (you only look once) algorithm in Keras and TensorFlow. By the end of the book you will have implemented various models in Keras and learned many advanced tricks that will bring your skills to the next level.


You will:

  • See how convolutional neural networks and object detection work
  • Save weights and models on disk
  • Pause training and restart it at a later stage
  • Use hardware acceleration (GPUs) in your code
  • Work with the Dataset TensorFlow abstraction and use pre-trained models and transfer learning
  • Remove and add layers to pre-trained networks to adapt them to your specific project
  • Apply pre-trained models such as Alexnet and VGG16 to new datasets

Keywords

Deep Learning Python TensorFlow Keras Sklearn Convolutional Neural Network Recurrent Neural Network Image recognition ResNets Speech Recognition

Authors and affiliations

  • Umberto Michelucci
    • 1
  1. 1.TOELT LLCDübendorfSwitzerland

Bibliographic information

Industry Sectors
Pharma
Materials & Steel
Automotive
Chemical Manufacturing
Health & Hospitals
Biotechnology
Finance, Business & Banking
Electronics
IT & Software
Telecommunications
Consumer Packaged Goods
Energy, Utilities & Environment
Aerospace
Oil, Gas & Geosciences
Engineering