Learning Tensorflow: A Guide to Building Deep Learning Systems

✍ Scribed by Tom Hope; Yehezkel S Resheff; Itay Lieder

• Publisher: O'Reilly Media
• Year: 2017
• Tongue: English
• Leaves: 230
• Category: Library

✦ Synopsis

Roughly inspired by the human brain, deep neural networks trained with large amounts of data can solve complex tasks with unprecedented accuracy. This practical book provides an end-to-end guide to TensorFlow, the leading open source software library that helps you build and train neural networks for computer vision, natural language processing (NLP), speech recognition, and general predictive analytics.

Authors Tom Hope, Yehezkel Resheff, and Itay Lieder provide a hands-on approach to TensorFlow fundamentals for a broad technical audience, from data scientists and engineers to students and researchers. You'll begin by working through some basic examples in TensorFlow before diving deeper into topics such as neural network architectures, TensorBoard visualization, TensorFlow abstraction libraries, and multithreaded input pipelines. Once you finish this book, you'll know how to build and deploy production-ready deep learning systems in TensorFlow.

Get up and running with TensorFlow, rapidly and painlessly
Learn how to use TensorFlow to build deep learning models from the ground up
Train popular deep learning models for computer vision and NLP
Use extensive abstraction libraries to make development easier and faster
Learn how to scale TensorFlow, and use clusters to distribute model training
Deploy TensorFlow in a production setting

✦ Table of Contents

Contents
Preface
Introduction
Going Deep
TensorFlow: What’s in a Name?
A High-Level Overview
Summary
Up & Running with TensorFlow
Installing TensorFlow
Hello World
MNIST
Softmax Regression
Summary
TensorFlow Basics
Computation Graphs
Graphs, Sessions, and Fetches
Flowing Tensors
Variables, Placeholders, and Simple Optimization
Summary
Convolutional Neural Networks
Introduction to CNNs
MNIST: Take II
CIFAR10
Summary
Text & Sequences & Visualization
The Importance of Sequence Data
Introduction to Recurrent Neural Networks
RNN for Text Sequences
Summary
Word Vectors, Advanced RNN & embedding Visualization
Introduction to Word Embeddings
Word2vec
Pretrained Embeddings, Advanced RNN
Summary
TensorFlow Abstractions & Simplification
Chapter Overview
contrib.learn
TFLearn
Summary
Queues Threads & Reading Data
The Input Pipeline
TFRecords
Queues
A Full Multithreaded Input Pipeline
Summary
Distributed TensorFlow
Distributed Computing
TensorFlow Elements
Distributed Example
Summary
Exporting & Serving Models
Saving and Exporting Our Model
Introduction to TensorFlow Serving
Summary
Model Construction & TensorFlow Serving
Model Structuring and Customization
Required and Recommended Components for TensorFlow Serving
Index