Learning Tensorflow: A Guide to Building Deep Learning Systems

Description

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 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