TensorFlow 簡介

02-12

　　2015 年 11 月 9 日，Google Research 發布了文章：TensorFlow - Google』s latest machine learning system, open sourced for everyone，正式宣布其新一代機器學習系統開源。

原文連接：來自TalkingDataSDK技術博客

至於 Google 為什麼要開源 TensorFlow，官方的說法是：

If TensorFlow is so great, why open source it rather than keep it proprietary? The answer is simpler than you might think: We believe that machine learning is a key ingredient to the innovative products and technologies of the future. Research in this area is global and growing fast, but lacks standard tools. By sharing what we believe to be one of the best machine learning toolboxes in the world, we hope to create an open standard for exchanging research ideas and putting machine learning in products. Google engineers really do use TensorFlow in user-facing products and services, and our research group intends to share TensorFlow implementations along side many of our research publications.

Heres Why Google Is Open-Sourcing Some Of Its Most Important Technology 文章中援引了 TensorFlow 開發者的說法：

The decision to open-source was the brainchild of Jeff Dean, who felt that the company』s innovation efforts were being hampered by the slow pace of normal science. Google researchers would write a paper, which would then be discussed at a conference some months later. Months after that somebody else would write another paper building on their work.
Dean saw that open-sourcing TensorFlow could significantly accelerate the process. Rather than having to wait for the next paper or conference, Google』s researchers could actively collaborate with the scientific community in real-time. Smart people outside of Google could also improve the source code and, by sharing machine learning techniques more broadly, it would help populate the field with more technical talent.

「Having this system open sourced we』re able to collaborate with many other researchers at universities and startups, which gives us new ideas about how we can advance our technology. Since we made the decision to open-source, the code runs faster, it can do more things and it』s more flexible and convenient,」 says Rajat Monga, who leads the TensorFlow team.

毫無意外地，TensorFlow 在 Github 上的 Repo 在很短的時間內就收穫了大量的 Star 和Fork，學術界和工業界都對其表示了巨大的興趣，並投身於 TensorFlow 的社區和 Google 一起完善和改進 TensorFlow。

然而，當時在 Github 做基準測試、目前就職於 Facebook AI 部門的程序員 Soumith 發布了文章 Benchmark TensorFlow（中文解讀），對 TensorFlow 和其他主流深度學習框架的性能進行了比較，結果差強人意。當然，Google 團隊表示會繼續優化，並在後面的版本中支持分散式。

2016 年 4 月 13 日，Google 通過文章 Announcing TensorFlow 0.8 – now with distributed computing support! 正式發布支持分散式的 TensorFlow 0.8 版本，結合之前對 CPU 和 GPU 的支持，TensorFlow 終於可以被用於實際的大數據生產環境中了。

2016 年 4 月 29 日，開發出目前最強圍棋 AI 的 Google 旗下 DeepMind 宣布：DeepMind moves to TensorFlow，這在業界被認為 TensorFlow 終於可以被當作 TensorFlow 在工業界發展的里程碑事件，極大提升了 TensorFlow 使用者的研究熱情。

The Good, Bad & Ugly of TensorFlow（中文翻譯）對目前 TensorFlow 的優缺點做了詳細的分析。

TensorFlow 學習資源

TensorFlow 使用 Python 作為主要介面語言，所以掌握 Python 在 Data Science 領域的知識就成為學習 TensorFlow 的必要條件。A Complete Tutorial to Learn Data Science with Python from Scratch 就是一篇非常好的學習資料。

TensorFlow 官方文檔從首個版本就非常詳細。
LearningTensorFlow: A beginners guide to a powerful framework.，包含詳細的介面定義，各種學習資源和例子。
Hello, TensorFlow! Building and training your first TensorFlow graph from the ground up.
A noob』s guide to implementing RNN-LSTM using Tensorflow
Updated with Google』s TensorFlow: Artificial Intelligence, Neural Networks, and Deep Learning 強烈推薦這篇文章，對AI、NN、DL 的發展歷史以及其中的關鍵大牛的關鍵工作做了詳細介紹。
DeepDreaming with TensorFlow This notebook demonstrates a number of Convolutional Neural Network image generation techniques implemented with TensorFlow for fun and science
TensorFlow Examples TensorFlow Tutorial with popular machine learning algorithms implementation. This tutorial was designed for easily diving into TensorFlow, through examples.
TensorFlow-Tutorials Introduction to deep learning based on Googles TensorFlow framework. These tutorials are direct ports of Newmus Theano Tutorials.
Dive Into TensorFlow, Part II: Basic Concepts TensorFlow 中基本概念的解釋
TensorFlow學習筆記1：入門系列學習筆記，中文版
TensorFlow人工智慧引擎入門教程所有目錄非常多作者學習和使用 TensorFlow 的經驗文章。

深度學習不是一個突然出現的概念，而是從神經網路發展而來的，所以，學習 TensorFlow，對深度學習領域本身的發展歷史有基本的了解有助於理解技術的發展。這方面有很多非常好的文章：

[Machine Learning & Algorithm] 神經網路基礎
Deep Learning in Neural Networks: An Overview
Deep learning by Yann LeCun, Yoshua Bengio& Geoffrey Hinton
A Brief History of Neural Nets and Deep Learning 一個系列，圖文並茂，非常詳細。
A Gentle Guide to Machine Learning 條理非常清晰。
A Neural Network in 11 lines of Python 非常好的從頭開始實現一個神經網路的文章，對學習和理解神經網路中所用到的技術很有用。
Machine Learning is Fun! Part 3: Deep Learning and Convolutional Neural Networks 系列文章，非常詳細。
Neural Networks and Deep Learning
Welcome to the Deep Learning Tutorial! 斯坦福深度學習資料
Learning How To Code Neural Networks
Machine Learning in a Week Deep Learning 的學習計劃。
Conv-Nets-And-Gen TensorFlow 官方推薦的文章。
Convolutional Neural Networks backpropagation: from intuition to derivation 神經網路反向傳播演算法的詳細解釋。
RECURRENT NEURAL NETWORKS TUTORIAL, PART 1 – INTRODUCTION TO RNNS RNN 的系列學習文章。
A Deep Dive into Recurrent Neural Nets RNN 深度學習文章
How to implement a neural network 神經網路的系列學習文章
An Interactive Node-Link Visualization of Convolutional Neural Networks 非常好的可視化神經網路工作原理的博客。
How to Code and Understand DeepMinds Neural Stack Machine
Neural Networks Demystified 解密神經網路的視頻教程。
Fundamentals of Deep Learning – Starting with Artificial Neural Network 非常詳細。
神經網路淺講：從神經元到深度學習中文資料中難得的非常詳細的資料。
有趣的機器學習概念縱覽：從多元擬合，神經網路到深度學習，給每個感興趣的人中文資源中關於神經網路到深度學習的歷史講解很有意思的文章。
卷積神經網路CNN經典模型整理Lenet，Alexnet，Googlenet，VGG，Deep Residual Learning 對不同的 CNN 模型做了詳細的對比介紹。
反向傳播神經網路極簡入門這是極簡？BP 得多複雜？