Developing an Image Classifier Using TensorFlow Convolutional Neural Networks

  • Saurabh Kulshrestha

Your browser needs to be JavaScript capable to view this video

Try reloading this page, or reviewing your browser settings

You're watching a preview of subscription content. Log in to check access

Use TensorFlow to classify images automatically. This video starts by explaining the basics of computerized image classification. You’ll understand how software processes images and how you can control and manipulate the images with that process. Then you’ll dive into the basics of artificial intelligence and machine learning, understanding the limitations of traditional machine learning algorithms, and learning the new avenues opened up by deep learning and advanced AI.

What You Will Learn

  • Apply the TensorFlow and Keras libraries to complex problems

  • Move past traditional machine learning algorithms into more advanced deep learning

  • Develop proficiency in convolutional neural network development

Who This Video Is For

Advanced programmers and engineers, such as data scientists, machine learning experts, Python developers, and research analysts.

With the foundation laid, you’ll dive into the TensorFlow and Keras libraries with Python. You’ll then build on that by learning about the different types of convolutional neural networks and how they overcome the limitations of fully connected networks. Finally, you’ll work directly with TensorFlow to create a CNN model that can classify ten different categories of images.

About The Author

Saurabh Kulshrestha

Saurabh Kulshrestha has a bachelor’s degree in telecommunication engineering and artificial intelligence. He currently works as an associate product manager at one of the leading e-learning companies in India. He has rich hands-on experience in handling entire product analytics, from reporting to insights.

 

About this video

Author(s)
Saurabh Kulshrestha
DOI
https://doi.org/10.1007/978-1-4842-5572-8
Online ISBN
978-1-4842-5572-8
Total duration
41 min
Publisher
Apress
Copyright information
© Saurabh Kulshrestha 2019

Related content

Video Transcript

[MUSIC PLAYING]

Welcome everyone to this particular session on developing an image classifier using TensorFlow. My name is Saurabh. And today, I’ll be teaching you everything about convolutional neural networks.

We’re going to build a convolutional neural network in this particular session. But before that, we have to cover a lot of basics as well. So let’s move forward and have a look at the agenda for today.

So this is what we’ll be discussing. We’ll begin by understanding what is image processing and how does it work? How does basically a computer read an image?

Then we are going to focus on a library called OpenCV and how we can use it for image processing. So I’m going to teach you a couple of things that are on OpenCV, how you can resize and image, how you can display an image, and then how you can read an image using OpenCV and all those things.

After that, I’m going to focus on artificial intelligence. So I’ll be giving you a quick introduction to artificial intelligence, machine learning, and deep learning. Post that, we are going to see how a convolutional neural network work. We’re going to see the four-layer architecture of the convolutional neural network with an example. And finally, I’ll be teaching you how you can develop an image classifier using TensorFlow in Python.