Book Image

Machine Learning with TensorFlow 1.x

By : Quan Hua, Saif Ahmed, Shams Ul Azeem
Book Image

Machine Learning with TensorFlow 1.x

By: Quan Hua, Saif Ahmed, Shams Ul Azeem

Overview of this book

Google's TensorFlow is a game changer in the world of machine learning. It has made machine learning faster, simpler, and more accessible than ever before. This book will teach you how to easily get started with machine learning using the power of Python and TensorFlow 1.x. Firstly, you’ll cover the basic installation procedure and explore the capabilities of TensorFlow 1.x. This is followed by training and running the first classifier, and coverage of the unique features of the library including data ?ow graphs, training, and the visualization of performance with TensorBoard—all within an example-rich context using problems from multiple industries. You’ll be able to further explore text and image analysis, and be introduced to CNN models and their setup in TensorFlow 1.x. Next, you’ll implement a complete real-life production system from training to serving a deep learning model. As you advance you’ll learn about Amazon Web Services (AWS) and create a deep neural network to solve a video action recognition problem. Lastly, you’ll convert the Caffe model to TensorFlow and be introduced to the high-level TensorFlow library, TensorFlow-Slim. By the end of this book, you will be geared up to take on any challenges of implementing TensorFlow 1.x in your machine learning environment.

Related Content you might be interested in

Current Title:

Small book image
Machine Learning with TensorFlow 1.x
Quan Hua | Saif Ahmed | Shams Ul Azeem
Nov, 2017 | 304 pages
Small book image
Neural Network Programming with Tensorflow
Manpreet Singh Ghotra | Rajdeep Dua
Nov, 2017 | 274 pages
Small book image
Deep Learning with TensorFlow
Ahmed Menshawy | Md Rezaul Karim | Giancarlo Zaccone
Apr, 2017 | 320 pages
Small book image
Deep Learning for Computer Vision
Rajalingappaa Shanmugamani
Jan, 2018 | 310 pages
Table of Contents (13 chapters)
Preface
Preface
What this book covers
What you need for this book
Who this book is for
Conventions
Reader feedback
Customer support
Free Chapter
1
Getting Started with TensorFlow
Getting Started with TensorFlow
Current use
Installing TensorFlow
Summary
2
Your First Classifier
Your First Classifier
The key parts
Obtaining training data
Downloading training data
Understanding classes
Additional setup
Logical stopping points
The machine learning briefcase
Training day
Saving the model for ongoing use
Why hide the test set?
Using the classifier
Deep diving into the network
Skills learned
Summary
3
The TensorFlow Toolbox
The TensorFlow Toolbox
A quick preview
Installing TensorBoard
Automating runs
Summary
4
Cats and Dogs
Cats and Dogs
Revisiting notMNIST
Training day
Actual cats and dogs
Saving the model for ongoing use
Using the classifier
Skills learned
Summary
5
Sequence to Sequence Models-Parlez-vous Français?
Sequence to Sequence Models-Parlez-vous Français?
A quick preview
Drinking from the firehose
Training day
Summary
6
Finding Meaning
Finding Meaning
Additional setup
Skills learned
Summary
7
Making Money with Machine Learning
Making Money with Machine Learning
Inputs and approaches
Approaching the problem
Taking it further
Practical considerations for the individual
Skills learned
Summary
8
The Doctor Will See You Now
The Doctor Will See You Now
The challenge
The data
The pipeline
Going further
Skills Learned
Summary
9
Cruise Control - Automation
Cruise Control - Automation
An overview of the system
Setting up the project
Loading a pre-trained model to speed up the training
Training the model for our dataset
Serving the model in production
Automatic fine-tune in production
Summary
10
Go Live and Go Big
Go Live and Go Big
Quick look at Amazon Web Services
Overview of the application
Overview of Mechanical Turk
Summary
11
Going Further - 21 Problems
Going Further - 21 Problems
Dataset and challenges
TensorFlow-based Projects
Interesting Projects
Caffe to TensorFlow
TensorFlow-Slim
Summary
12
Advanced Installation
Advanced Installation
Installation
Using TensorFlow with Anaconda
Summary

Summary

In this chapter, we have implemented a complete real-life production, from training to serving a deep learning model. We also created a web interface in a Flask app so that users can upload their images and receive results. Our model can automatically be fine-tuned every day to improve the quality of the system. There are a few things that you can consider to improve the overall system:

  • The model and checkpoints should be saved in cloud storage.
  • The Flask app and TensorFlow Serving should be managed by another, better process management system, such as Supervisor.
  • There should be a web interface so that the team can approve the labels that users select. We shouldn't rely completely on users to decide the training set.
  • TensorFlow Serving should be built with GPU support to achieve the best performance.
Previous Section
End of Chapter 9
Next Chapter