Book Image

TensorFlow Machine Learning Projects

By : Ankit Jain, Amita Kapoor
Book Image

TensorFlow Machine Learning Projects

By: Ankit Jain, Amita Kapoor

Overview of this book

TensorFlow has transformed the way machine learning is perceived. TensorFlow Machine Learning Projects teaches you how to exploit the benefits—simplicity, efficiency, and flexibility—of using TensorFlow in various real-world projects. With the help of this book, you’ll not only learn how to build advanced projects using different datasets but also be able to tackle common challenges using a range of libraries from the TensorFlow ecosystem. To start with, you’ll get to grips with using TensorFlow for machine learning projects; you’ll explore a wide range of projects using TensorForest and TensorBoard for detecting exoplanets, TensorFlow.js for sentiment analysis, and TensorFlow Lite for digit classification. As you make your way through the book, you’ll build projects in various real-world domains, incorporating natural language processing (NLP), the Gaussian process, autoencoders, recommender systems, and Bayesian neural networks, along with trending areas such as Generative Adversarial Networks (GANs), capsule networks, and reinforcement learning. You’ll learn how to use the TensorFlow on Spark API and GPU-accelerated computing with TensorFlow to detect objects, followed by how to train and develop a recurrent neural network (RNN) model to generate book scripts. By the end of this book, you’ll have gained the required expertise to build full-fledged machine learning projects at work.
Table of Contents (23 chapters)
Title Page
Copyright and Credits
Dedication
About Packt
Contributors
Preface
Index

Building a Bayesian neural network


For this project, we will use the German Traffic Sign Dataset (http://benchmark.ini.rub.de/?section=gtsrb&subsection=dataset) to build a Bayesian neural network. The training dataset contains 26,640 images in 43 classes. Similarly, the testing dataset contains 12,630 images.

Note

Please read the README.md file in this book's repository before executing the code to install the appropriate dependencies and for instructions on how to run the code.

The following is an image that's present in this dataset: 

You can see that there are different kinds of traffic sign depicted by different classes in the dataset.

We begin by pre-processing our dataset and making it conform to the requirements of the learning algorithm. This is done by reshaping the images to a uniform size via histogram equalization, which is used to enhance contrast, and cropping them to only focus on the traffic signs in the image. Also, we convert the images to grayscale as traffic signs...