Later I will jump directly to the actual project and realize the main tasks and goals of computer vision, but everyone needs to go down and understand and learn more. For example, what is deep learning, what is computer vision, what is natural language processing, what are the main tasks of computer vision, what are the basic knowledge to learn, etc.
And I will upload some free courseware to everyone. You can just go and find it in my resources. You don’t have to buy books specifically. It will save you a little bit.
Chapter 1 Overview of Computer Vision
Computer vision is one of the most popular research fields in the field of deep learning and has been widely used in various fields. So how has it developed so far? This chapter mainly explains the development process of computational vision and explains the main tasks in the field of computer vision. An overview is provided, and some typical vision application cases are selected to give readers an in-depth understanding of the role of computer vision in different fields such as smart cities, agriculture, energy and power, agriculture, and autonomous driving. Then it also introduces commonly used computer vision processing tools, such as opencv, etc., for the convenience of readers. Finally, the current and future development of computer vision is prospected. After studying this chapter, I hope readers can master the following knowledge points:
- Learn about the development of computer vision.
- Be familiar with the main tasks and application scenarios in the field of computer vision.
- Understand commonly used processing tools in computer vision.
Chapter 2 Deep Learning Development Framework
Deep learning development framework plays an important role in deep learning project development. This chapter introduces the three mainstream deep learning development frameworks currently used in the field of domestic deep learning project development. Since the flying paddle framework is used in the sample codes in each chapter of this book, this chapter focuses on the flying paddle framework. After years of development, the Flying Paddle Framework has achieved good performance and a very user-friendly experience. After studying this chapter, I hope readers can master the following knowledge points:
- Understand the significance of using deep learning frameworks;
- Understand what the three major frameworks are and their basic functions;
- Understand the characteristics of the flying paddle platform from a macro perspective.
Chapter 3 Basics of Deep Learning Algorithms
The rapid development of deep learning has made it more and more widely used in computer vision tasks. This chapter begins with an overview of machine learning and the basic components of neural networks. On this basis, some basic algorithms of deep learning are explained, so that readers can have an understanding of the basic knowledge necessary for entry into deep learning such as activation functions, backpropagation, and optimization algorithms. Finally, this chapter will introduce the basic structure and algorithm principles of convolutional neural networks commonly used in deep learning. After studying this chapter, I hope readers can master the following knowledge points:
- Understand the basic concepts of machine learning and master the structure of neural networks;
- Master some basic algorithms in deep learning;
- Master the basic components and algorithm principles of convolutional neural networks.
Chapter 4 Deep Learning Network Model
The overall architecture of the deep learning network model mainly consists of three parts: data set, model networking, and learning optimization process. This chapter mainly introduces the algorithm architecture and common models of the deep learning network model in detail, starting from the classic deep learning network model to CNN, RNN is represented by lightweight network design to solve problems such as insufficient memory and real-time performance, as well as the cutting-edge network models Transformer and MLP that have been involved in major computer vision tasks in recent years. In order to further analyze the process of building a deep learning network model, finally, taking the LeNet model algorithm as an example, a network building case was demonstrated under the flying paddle deep learning framework. After studying this chapter, I hope readers can master the following knowledge points:
- Understand classic network models (CNN and RNN);
- Familiar with cutting-edge network models (Transformer and MLP);
- Master the use of flying paddles to build a deep learning network model-LeNet.
You can learn through these simple introductions and courseware ppts. I will continue to update the blog and my small website in the future. Just keep paying attention. If you don’t want to get lost, remember to like, collect and follow.
https://space.bilibili.com/1032401779?spm_id_from=333.1007.0.0