It has been almost a year since I started learning machine learning knowledge. During this period, I read a lot of textbooks and books, some in-depth study, some books (such as the famous watermelon book in the field of deep learning) can not continue. Machine learning actually has many directions, such as reinforcement learning, computer vision, natural language processing, and so on, if you study in each direction, ordinary people will not have that much energy.

After a year of general learning, I decided to choose computer vision as my major, mainly because I am interested in computer image. After searching some materials and recommended books on the Internet, I decided to choose Deep Learning for Computer Vision with Python as a book to read seriously. Now I have almost finished the first book: Starter Bundle, for those interested in computer vision, thinks it’s great.

First of all, it should be noted that there is no Chinese version of this book at present. Fortunately, the author does not use uncommon vocabulary, and the words and sentences are relatively concise, which can be read smoothly with the help of Google Translation. You can download the electronic version of this book by replying “Computer Vision” in the background of the official account.

Deep Learning for Computer Vision with Python, written by Computer Vision expert Adrian Rosebrock, is rated as one of the best Deep Learning and Computer Vision resources available today. Francois Chollet, AI researcher at Google and author of the Keras Library, has this to say about the book:

This is an excellent, deep and practical deep learning exercise in computer vision. I found it very easy to read and understand: the explanations were clear and detailed. You’ll find a lot of practical advice that you won’t find in other books or college courses. I highly recommend this book for practitioners and beginners alike.

The book is divided into three bundles:

  • Starter Bundle – This section covers the basics of implementing regression algorithms, deep neural networks, and convolutional neural networks from scratch. For those with no machine learning background at all, the basics of deep learning can be learned from examples. If you have a certain knowledge background of deep learning, you can also learn how to apply deep learning (mainly image classification) in practice to deepen your understanding of deep learning.

  • Practition Bundle – This section goes further than the Starter Bundle and looks at problems that are likely to occur in practice, such as improving the accuracy of identification, model selection, and large data sets, and finally introduces several large and complex network models.

  • ImageNet Bundle – This section focuses more on the field. The first half is training various complex networks on ImageNet datasets, and the second half is solving real-world problems, including expression detection, vehicle recognition, age prediction, and more. After finishing this part of the study, I think your actual combat ability will improve a lot.

If you’re interested in applying deep learning to computer vision (image classification, object detection, image understanding, etc.), this is a great book.

In this book, you will be able to:

  • Learn the fundamentals of machine learning and deep learning both theoretically and practically
  • Learn advanced deep learning techniques, including object detection, multi-GPU training, transfer learning and generative adversarial networks
  • Reproduces cutting-edge papers, including ResNet, SqueezeNet, VGGNet, and others present in the ImageNet dataset

What attracted me most about this book is that it strikes a balance between theory and practice. For each deep learning theory, there is an associated Python implementation to help you consolidate your understanding and knowledge. There are detailed codes in the book, and the codes are more detailed explanation, very friendly to Engineer.

In the process of learning, I will try to input the code, deepen the understanding of the code. You can visit: github.com/mogoweb/aie…

You can download the electronic version of this book by replying “Computer Vision” in the background of the official account.