Presented By O’Reilly and Intel AI
Put AI to work
8-9 Oct 2018: Training
9-11 Oct 2018: Tutorials & Conference
London, UK

Image classification models in TensorFlow

Benoit Dherin (Google)
9:00–17:00 Tuesday, 9 October 2018
Interacting with AI
Location: Park Suite
Secondary topics:  Computer Vision, Deep Learning tools
Average rating: ****.
(4.00, 1 rating)

Who is this presentation for?

  • Developers

Prerequisite knowledge

  • Familiarity with machine learning

Materials or downloads needed in advance

  • A laptop with TensorFlow installed (This workshop will be conducted on Google Cloud Platform (GCP) and will use GCP's infrastructure to run TensorFlow.)

What you'll learn

  • Learn how to classify images using deep learning, implement convolutional neural networks, improve the model by augmentation, batch normalization, and more, and leverage transfer learning


Benoit Dherin explains how machine learning is applied to image classification, discusses evolving methods and challenges, and walks you through creating increasingly sophisticated image classification models using TensorFlow. You’ll learn different strategies for building an image classifier using convolutional neural networks and discover how to improve the model’s accuracy with augmentation, feature extraction, and fine-tuning hyperparameters while avoiding overfitting your data.

Photo of Benoit Dherin

Benoit Dherin


Benoit Dherin is a machine learning solutions engineer at Google’s Advanced Solutions Lab, where he teaches machine learning to Google clients and helps them implement machine learning solutions in the Google Cloud. Previously, Benoit held roles in data science, machine learning, and software engineering at various companies and startups in Silicon Valley as well as research and teaching positions at universities around the world. Benoit holds a PhD in mathematics from ETH Zurich. In his free time, he enjoys reading, traveling, and doing Bikram Yoga.

Comments on this page are now closed.


Cedric John | READER
5/10/2018 13:18 BST

I have tensor flow installed with Anaconda; I assume this will work?
I am also curious to hear during the workshop of alternative solution to TensorFlow, in particular for Java and Scala (DL4J, Weka, etc…). But of course this will depend on the time we have…

Rachel Vishnepolsky | DATA SCIENTIST
4/10/2018 18:32 BST

Hi, I want to make sure that my corporate computer’s proxy allows access to everything that we will be accessing. Are there any URLs I can test in advance to make sure it works?