You're reading from TensorFlow 2.0 Quick Start Guide

Product typeBook

Published inMar 2019

Reading LevelBeginner

PublisherPackt

ISBN-139781789530759

Edition1st Edition

Languages

Python

Tools

TensorFlow

Concepts

Machine Learning

Author (1)

Tony Holdroyd

TensorFlow Estimators and TensorFlow Hub

This chapter is divided into two sections, but the technologies here are related. First, we will look at how TensorFlow Estimators provide a simple, high-level API for TensorFlow, and secondly, we will look at how TensorFlow Hub contains modules that we can make use of in our own applications.

In this chapter, we will cover the following main topics:

TensorFlow Estimators
TensorFlow Hub

TensorFlow Estimators

tf.estimator is a high-level API for TensorFlow. It is used to simplify machine learning programming by providing the means for the straightforward training, evaluation, predicting, and exporting of models for serving.

Estimators confer many advantages on the TensorFlow developer. It is easier and more intuitive to develop models with Estimators than with low-level APIs. In particular, the same model can be run on a local machine or on a distributed multi-server system. The model is also agnostic to the processor it finds itself on, that is, either CPUs, GPUs, or TPUs. Estimators also simplify the development process by making it easier for model developers to share implementations and, being built on Keras layers, make customization simpler.

Estimators take care of all of the background plumbing that goes into working with a TensorFlow model. They support...

TensorFlow Hub

TensorFlow Hub is a software library. Its purpose is to provide reusable components, known as modules, that can be leveraged in contexts other than the original context in which they were developed. By a module, we mean a self-contained piece of a TensorFlow graph, along with its weights, which can be reused across other, similar tasks.

IMDb (database of movie reviews)

In this section, we will examine an application based on one from Google that analyzes a subset of the IMDb of movie reviews in what is termed sentiment analysis. The subset is hosted by Stanford and contains reviews of each movie, together with a sentiment on a positivity scale of 1 to 4 (bad) and 7 to 10 (good). The problem is determining the...

Summary

In this chapter, we looked at an Estimator for training the fashion dataset. We saw how Estimators provide a simple, intuitive API for TensorFlow.

We then looked at another application, this time for the sentiment classification of reviews of movies in the IMDb. We saw how TensorFlow Hub provides us with text embeddings, that is, vectors for words, which is where words with similar meanings have similar vectors.

In this book, we have seen an overview of TensorFlow 2.0 alpha.

The rest of the chapter is locked

You have been reading a chapter from

TensorFlow 2.0 Quick Start Guide

Published in: Mar 2019Publisher: PacktISBN-13: 9781789530759

A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.

undefined

Unlock this book and the full library FREE for 7 days

Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of

Start free trial

Renews at $15.99/month. Cancel anytime

Author (1)

Tony Holdroyd

Tony Holdroyd's first degree, from Durham University, was in maths and physics. He also has technical qualifications, including MCSD, MCSD.net, and SCJP. He holds an MSc in computer science from London University. He was a senior lecturer in computer science and maths in further education, designing and delivering programming courses in many languages, including C, C+, Java, C#, and SQL. His passion for neural networks stems from research he did for his MSc thesis. He has developed numerous machine learning, neural network, and deep learning applications, and has advised in the media industry on deep learning as applied to image and music processing. Tony lives in Gravesend, Kent, UK, with his wife, Sue McCreeth, who is a renowned musician.
Read more about Tony Holdroyd

Other recommended products

Related to this chapter

What's New in TensorFlow 2.0

This book will cover all the new features that have been introduced in TensorFlow 2.0 especially the major highlight, including eager execution and more. You will learn how to make the best use of these features to migrate your codes from TensorFlow 1.x to TensorFlow 2.0 in a seamless way.

BookAug 2019202 pages

TensorFlow 2.0 Computer Vision Cookbook

This book covers recipes for solving various computer vision tasks using TensorFlow, taking you through all the tips and tricks you need to overcome any challenges that you may face while building various computer vision applications. You will discover machine learning techniques to solve problems in image processing, feature extraction, and more.

BookFeb 2021542 pages

Learn TensorFlow Enterprise

This book is a comprehensive introduction for those who are new to scalable and optimized TensorFlow for production. You will learn how to deliver enterprise-grade support for your existing and newly built AI applications. You will address the various needs of AI-enabled organizations to manage and scale machine learning workloads in production.

BookNov 2020314 pages

Hands-On Deep Learning for Images with TensorFlow

In this book, you will come across various real-world projects which will teach you how to leverage Tensforflow’s capabilities to perform efficient image processing tasks. By the end of this book, you will have mastered all the concepts of deep learning for Images and their implementations with Tensorflow and Keras

BookJul 201896 pages

Hands-On Neural Networks with TensorFlow 2.0

This book is a guide to the TensorFlow (TF) framework, from the static graph architecture of TF 1.x to the eager execution and all the new features introduced in TF 2.0. Neural Networks applications are developed throughout the book with the aim of making the reader capable of developing neural networks-based solutions to real problems using TF 2.0

BookSep 2019358 pages

Python Deep Learning Cookbook

Deep Learning is a rapidly evolving field of Machine Learning science which gives machines the ability to learn from information. This book contains detailed recipes to tackle with the common and not so common problems while dealing with deep learning algorithms and models in Python. You will benefit from this book by finding technical solutions to the issues presented, along with a detailed explanation of the solutions, and a discussion on corresponding pros and cons of implementing the proposed solution using Theano, Tensorflow, MXNet, and Keras. You'll come across recipes on data pre-processing, network models and topologies, supervised and unsupervised learning presented in a “solution to problem” fashion.

BookOct 2017330 pages

Machine Learning Using TensorFlow Cookbook

This book is designed to guide you through TensorFlow and how to use it effectively. Throughout the book, you will work through recipes and get hands-on experience to perform complex data computations, gain insights into your data, and more.

BookFeb 2021416 pages

Keras Deep Learning Cookbook

This book gives you a practical, hands-on understanding of how you can leverage the power of Python and Keras to perform effective deep learning. It presents a unique problem-solution approach to tackle various problems in training different types of neural networks while taking care of the speed and accuracy of these models

BookOct 2018252 pages

Mastering PyTorch

Discover the flexibility of the PyTorch library for implementing new algorithms in a scalable and efficient way with this expert guide. This book will show you how to process data with deep learning methodologies using PyTorch 1.x and cover advanced topics such as GANs, Deep RL, and NLP using advanced deep learning techniques.

BookFeb 2021450 pages

Mastering TensorFlow 1.x

We cover advanced deep learning concepts (such as transfer learning, generative adversarial models, and reinforcement learning), and implement them using TensorFlow and Keras. We cover how to build and deploy at scale with distributed models. You will learn to build TensorFlow models using R, Keras, TensorFlow Learn, TensorFlow Slim and Sonnet

BookJan 2018474 pages

Deep Learning with Keras

Keras is a high-level neural network library written in Python that runs on top of either Theano or TensorFlow. With this book, you’ll learn the basics of Keras in a highly practical way and understand how this minimal, highly modular framework runs on both CPU and GPU, allowing you to put your ideas into action in the shortest possible time.

BookApr 2017318 pages

Hands-On Deep Learning Algorithms with Python

This book introduces basic-to-advanced deep learning algorithms used in a production environment by AI researchers and principal data scientists; it explains algorithms intuitively, including the underlying math, and shows how to implement them using popular Python-based deep learning libraries such as TensorFlow.

BookJul 2019512 pages

Personalised recommendations for you

Based on your interests and search pattern

Et al.

Ever wonder why speech recognition systems don't understand the Scottish accent, or what would happen if an astronaut only ate mac 'n' cheese, or other spurious reflections you'd have at a bar? We did, then collated those deliberations into absurd research articles with fake figures and methodologies inspired by even more fictionally absurd studies.

BookAug 2023230 pages5

Generative AI with LangChain

This book is a comprehensive introduction to LLMs and LangChain, demystifying the basic mechanics of LangChain, its functionalities, and the myriad of applications it can be integrated into.

BookDec 2023360 pages4

Generative AI with LangChain

This book is a comprehensive introduction to LLMs and LangChain, demystifying the basic mechanics of LangChain, its functionalities, and the myriad of applications it can be integrated into.

BookDec 2023360 pages5

Generative AI with LangChain

This book is a comprehensive introduction to LLMs and LangChain, demystifying the basic mechanics of LangChain, its functionalities, and the myriad of applications it can be integrated into.

BookDec 2023360 pages1

Generative AI with LangChain

This book is a comprehensive introduction to LLMs and LangChain, demystifying the basic mechanics of LangChain, its functionalities, and the myriad of applications it can be integrated into.

BookDec 2023360 pages5

Mastering Tableau 2023

This book is a comprehensive resource to mastering your Tableau skills and becoming a BI expert. As you progress, you will learn how to build advanced dashboards and improve your storytelling to derive key business insight, as well as make you well-versed with advanced functionalities of Tableau in the business intelligence domain.

BookAug 2023684 pages

Building AI Applications with ChatGPT APIs

This guide covers all ChatGPT API features for effortless creation of robust AI powered apps. With its help, you’ll be able to leverage ChatGPT’s cutting-edge NLP models to take your app development skills to the next level. You’ll also work on ten exciting projects that will give you the practical know-how that you can apply to your existing applications.

BookSep 2023258 pages5

Building AI Applications with ChatGPT APIs

This guide covers all ChatGPT API features for effortless creation of robust AI powered apps. With its help, you’ll be able to leverage ChatGPT’s cutting-edge NLP models to take your app development skills to the next level. You’ll also work on ten exciting projects that will give you the practical know-how that you can apply to your existing applications.

BookSep 2023258 pages2

Data Engineering with AWS

Embark on a journey to master data engineering pipelines on AWS! Our book offers a hands-on experience of AWS services for ingesting, transforming, and consuming data. Whether you're an absolute beginner or someone with basic data engineering experience, this guide is an indispensable resource.

BookOct 2023636 pages5

Modern Data Architecture on AWS

Every organization wants an agile, performant, and cost-effective data platform that meets all their current and future business needs. Purpose-built AWS analytics services and their features play a big part in building such a modern data platform. This book brings to you all the design and architectural patterns that’ll help you achieve this goal.

BookAug 2023420 pages5

Practical Guide to Applied Conformal Prediction in Python

Discover the power of Conformal Prediction with the "Practical Guide to Applied Conformal Prediction in Python." Master the latest techniques to quantify uncertainty in machine learning and computer vision models, and seamlessly apply them to your industry applications.

BookDec 2023240 pages

TinyML Cookbook

With over 70 project-based recipes, the TinyML Cookbook is a practical guide that will help you to get the most out of your microcontrollers. It provides a comprehensive understanding of the theoretical foundations while giving you hands-on experience training ML models for deployment on Arduino Nano 33 BLE Sense, Raspberry Pi Pico, and SparkFun RedBoard Artemis Nano microcontrollers.

BookNov 2023664 pages