TensorFlow in Action

Name: TensorFlow in Action
ISBN: 9787121309120

黄文坚Publishing House of Electronics Industry · ChinaDec 2017

3.4

Word count: 120K words
Chapters: 50
ISBN: 9787121309120

Report an error Find this book

Summary

The first two chapters of this book introduce the basics and core concepts of TensorFlow; Chapters 3 and 4 cover simple examples and fully connected neural networks; Chapters 5 and 6 introduce basic convolutional neural networks and classic models such as AlexNet, VGGNet, Inception Net, and ResNet; Chapter 7 covers Word2Vec, RNN, and LSTM; Chapter 8 introduces reinforcement learning and deep-learning-based policy networks and value networks; Chapter 9 covers TensorBoard, single-machine multi-GPU parallelism, and distributed parallelism; and the final two chapters introduce TF Learn and other TensorFlow auxiliary components.

Editor's review

TensorFlow in Action, co-authored by Huang Wenjian and Tang Yuan, is one of the earlier hands-on guides in the Chinese-speaking world to systematically introduce the TensorFlow framework. Written for TensorFlow 1.0, its core value lies in guiding readers from basic concepts to practical model building with clear logic and abundant code examples. The book covers not only the fundamentals of deep learning and TensorFlow installation and basic operations but also classic models such as CNNs, RNNs, and autoencoders, extending to comprehensive application cases of TensorFlow in natural language processing, image recognition, and recommender systems.

Who it's for

A good fit for

Developers who want to understand TensorFlow 1.x and classic deep learning implementation paths
Teachers and students who need to refer to an early Chinese-language TensorFlow textbook for teaching or research
Learners interested in the deep learning application workflow who are willing to adapt the code to newer APIs themselves
Technical staff maintaining legacy AI engineering projects who need to understand early code logic

Not a good fit for

Beginners who want to learn the latest features of TensorFlow 2.x and above directly
Readers seeking ready-to-run code examples that fully match current mainstream development environments

Reading tips

While reading, focus on the ideas and workflow of model building rather than getting stuck on outdated API call details
It is recommended to read alongside the official TensorFlow documentation or the latest tutorials to understand the logic of change between versions
The hands-on cases in the book can serve as references for problem-solving approaches; when practicing, reproduce the code in a current stable environment

About the publisher

Publishing House of Electronics Industry China · Founded in 1982

The Publishing House of Electronics Industry is a comprehensive publisher distinguished by its focus on electronic information and related fields. Judging from the more than 3,000 titles in its catalogue, its publishing covers programming and design, artificial intelligence, computer science, finance and economics, photography, and social sciences, attending both to cutting-edge technology and to general readers. Representative titles include Factor Investing: Methods and Practice, x86 Assembly Language: From Real Mode to Protected Mode, The RISC-V Reader, Artificial Intelligence: Speech Recognition, Understanding and Practice, Phased Array Radar Technology, Radar Target Characteristics, and 100 Go Mistakes and How to Avoid Them, most of which centre on technical methods and engineering practice. Its authors include Shi Chuan, Li Zhong, Wang Xiaobo, David Patterson, Andrew Waterman, and Yu Zihao, among others from China and abroad. Owing to limited public information, no further publishing features are elaborated here.

版权信息
好评袭来
前言
1 TensorFlow基础
1.1 TensorFlow概要
1.2 TensorFlow编程模型简介
2 TensorFlow和其他深度学习框架的对比
2.1 主流深度学习框架对比
2.2 各深度学习框架简介
3 TensorFlow第一步
3.1 TensorFlow的编译及安装
3.2 TensorFlow实现Softmax Regression识别手写数字
4 TensorFlow实现自编码器及多层感知机
4.1 自编码器简介
4.2 TensorFlow实现自编码器
4.3 多层感知机简介
4.4 TensorFlow实现多层感知机
5 TensorFlow实现卷积神经网络
5.1 卷积神经网络简介
5.2 TensorFlow实现简单的卷积网络
5.3 TensorFlow实现进阶的卷积网络
6 TensorFlow实现经典卷积神经网络
6.1 TensorFlow实现AlexNet
6.2 TensorFlow实现VGGNet
6.3 TensorFlow实现Google Inception Net
6.4 TensorFlow实现ResNet
6.5 卷积神经网络发展趋势
7 TensorFlow实现循环神经网络及Word2Vec
7.1 TensorFlow实现Word2Vec
7.2 TensorFlow实现基于LSTM的语言模型
7.3 TensorFlow实现Bidirectional LSTM Classifier
8 TensorFlow实现深度强化学习
8.1 深度强化学习简介
8.2 TensorFlow实现策略网络
8.3 TensorFlow实现估值网络
9 TensorBoard、多GPU并行及分布式并行
9.1 TensorBoard
9.2 多GPU并行
9.3 分布式并行
10 TF.Learn从入门到精通
10.1 分布式Estimator
10.2 深度学习Estimator
10.3 机器学习Estimator
10.4 DataFrame
10.5 监督器Monitors
11 TF.Contrib的其他组件
11.1 统计分布
11.2 Layer模块
11.3 性能分析器tfprof
参考文献

FAQ

Can the code in this book run directly on TensorFlow 2.0 and above?

No, it cannot run directly. Because TensorFlow 2.x introduced major changes—including enabling Eager Execution by default, integrating Keras as the high-level API, and removing many 1.x symbolic APIs—the code in the book must be modified according to the official migration guide before it can run in the new environment.

Is this book suitable for learning deep learning from scratch?

The book assumes readers have some Python programming foundation and basic machine learning concepts. It focuses more on teaching readers how to implement models with the TensorFlow framework than on explaining all the mathematical principles of deep learning from scratch. Readers with no background are advised to first acquire the relevant prerequisite knowledge.

Compared with newer books on the market, does this book still have reading value?

It still has unique reference value, mainly in that: 1) it provides a clear interpretation of TensorFlow's early architecture in a Chinese-language context; 2) its case design reflects classic engineering implementation approaches; and 3) it helps readers understand the framework's development trajectory and design philosophy. However, for the latest technical developments and best practices, recent books based on TensorFlow 2.x should be preferred.

Comments

Find this book

This site is an index: you start “Search all sources” in your browser, and the entries it lists all point to third-party sites; please judge their availability yourself.

About the author

黄文坚 Author

Huang Wenjian is an author about whom limited public information is available; what can be confirmed is mainly his connection to computer technology writing. Only one work by him is held in the library, TensorFlow in Action (TensorFlow Shizhan), which is commonly classified under programming and design. Judging from the title and category, the book addresses the practical use of the TensorFlow deep learning framework and belongs to the field of technical introductions and engineering practice rather than theoretical monographs or academic research. It can therefore be inferred that the author focuses on explaining framework usage, model construction, and code implementation clearly, in a direct and pragmatic style aimed at readers who wish to learn by doing. For beginners and engineers, such a book is valuable for lowering the barrier to entry and offering workable, referenceable procedures. Because details such as dates of birth and death, nationality, education, and professional experience remain unconfirmed, this profile does not cover his personal life and only describes objectively the subject matter and orientation of the available work.