Recommendation - in depth learning frameworkPyTorch： Introduction and Practice
Click above“ Programmed life”, Choice“ Top public address”
First time focus on procedural apes（ Yuan） Stories around us
RivalTensorFlow Deep learning framework of!
actual combatKaggle Classic events in the competition
GAN Generate animation Avatar,AI Filter,RNN Writing poetry, Image description task
2016 Year belongs toTensorFlow One year, Thanks to Google's promotion,TensorFlow Dominated the headlines of major media.2017 Early in the year,PyTorch The emergence of the new technology has attracted great attention of researchers,PyTorch Simple and elegant design, Unified and easy-to-use interface, The speed of chasing the wind and the flexibility of changing are impressive.
As a door2017 Deep learning framework just released in, Researchers have limited access to learning materials, Chinese materials are even less. Long term concern of the authorPyTorch Development, Often help in forumsPyTorch Novice problem solving, Use in scientific research at ordinary timesPyTorch Conduct research in all aspects, With rich experience. See the domestic usersPyTorch Very interested, There is an urgent need for a comprehensive explanationPyTorch Books, So this book was born.
《 Deep learning frameworkPyTorch： Introduction and Practice》
Main contents of this book
This book from multidimensional arrayTensor start, Step by step to guide readers to understandPyTorch Basic knowledge of all aspects. Combining basic knowledge with cutting-edge research, Lead readers to complete several classic and interesting in-depth learning projects from scratch, IncludeGAN Generate animation Avatar,AI Filter,AI Writing poems, etc..《 Deep learning frameworkPyTorch： Introduction and Practice》 There is no simple and mechanical introduction to the use of each function interface, It's about trying to categorize, Introduce the reader step by stepPyTorch Knowledge, I hope the readers are rightPyTorch Have a complete understanding.
The content of this book goes from shallow to deep, Whether it's a beginner of deep learning, First contactPyTorch Of researchers, Can be mastered quickly in the process of learning this bookPyTorch. Even if there is a certainPyTorch Users with experience, You can also get the right answers from this bookPyTorch Different understanding.
Author brief introduction
economic expert：Python Programmer,Linux Lovers andPyTorch Source contributor. Main research fields include computer vision and machine learning.“2017 Zhihu watch mountain cup machine learning challenge” The first prize,“2017 Tianchi medical treatmentAI Competition” Eighth place.
Keen to promotePyTorch, With rich experience, Active inPyTorch Forum and Zhihu related sections.
The book is divided into two parts： The first2~5 Chapter introductionPyTorch Basic knowledge of.
√ The first2 Chapter introductionPyTorch Installation and configuration of learning environment. At the same time, it is introduced in the most general wayPyTorch Main content of, Let readersPyTorch Have a general impression.
The first3 Chapter introductionPyTorch Multi dimensional arrayTensor Dynamic graphautograd/Variable Use, With examples, Let readers use them separatelyTensor andautograd Realize linear regression, Compare their differences. This chapter is also right.Tensor Bottom design of, as well asautograd The principle of, Give readers a more comprehensive and specific explanation.
The first4 Chapter introductionPyTorch Central neural network modulenn Basic usage of, At the same time, the neural network“ layer”,“ loss function”,“ Optimizer” etc. At last, it can't be used to guide readers50 The code of line was built to winImageNet ChampionResNet.
√ The first5 Chapter introductionPyTorch Data loading in,GPU Relevant tools such as acceleration and visualization.
The first6~10 Chapter mainly introduces actual combat cases.
The first6 Chapter is a connecting chapter, The goal is not to teach readers new functions, New knowledge, It's a combination.Kaggle A classic game in, A simple image two classification problem in deep learning. In the process of implementation, Before leading readers to review5 Chapter knowledge, Code specification is proposed to organize program and code reasonably, Make the program more readable, Maintainable. The first6 The chapter also introducesPyTorch How to proceed indebug.
√ The first7 Chapter 3 explains the most popular generative network for readers（GAN）, Lead the reader to realize a cartoon image generator from scratch, Can make use ofGAN Generate animation avatars with changeable styles.
√ The first8 The chapter explains the knowledge of style transfer for readers, And lead readers to realize style migration network, Turn your photos into“ Tall and tall” Famous paintings.
The first9 Chapter 2 introduces some basic knowledge of natural language processing, And explainCharRNN Principle. And then use it to collect tens of thousands of Tang poems, Train a small program that can write poems automatically. This small program can control the format and artistic conception of poetry, Can also generate Tibetan Poems.
√ The first10 Chapter 2 introduces the task of image description, And with the latestAI Challenger For example, the data of the competition, Lead the reader to implement a simple image description of the small program.
The first1 Zhang He11 Chapter is the first and last chapter of the book, The first1 Chapter introductionPyTorch Advantage, And the comparison with other frameworks on the market. The first11 Chapter is a summary of the book, And rightPyTorch Thinking about the shortcomings, At the same time, some suggestions are put forward for the future study of readers.
To learn this book, you need to have the following basic knowledge：
√ understandPython Basic grammar of, BasicPython Usage method.
√ Have a deep learning foundation, Understanding back propagation, Convolution neural network and other basic knowledge, But it doesn't require a deep understanding.
√ With gradient, High school mathematics basic knowledge such as derivative.
The following knowledge is not required, But it's better to know：
√ numpy Use.
√ The basic process of deep learning or the use of other deep learning frameworks.
Scan QR code purchase《 Deep learning frameworkPyTorch： Introduction and Practice》
Previous period“ Recommendation” Announcement of award list
award-winning3 Famous student
Please leave your name in the comments, Contact information and address
After reading this, What are your views and ideas, Welcome to leave a message and discuss with us.
- THE END -
Click on the picture.get Contents in the past