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

PyTorch: A flexible approach for computer vision models

Mo Patel (Independent)
9:00–12:30 Tuesday, 9 October 2018
Implementing AI
Location: Buckingham Room - Palace Suite
Secondary topics:  Computer Vision, Deep Learning tools
Average rating: *....
(1.50, 2 ratings)

Who is this presentation for?

  • Data scientists and application developers

Prerequisite knowledge

  • A working knowledge of supervised machine learning concepts and Python

Materials or downloads needed in advance

What you'll learn

  • Understand the fundamentals of computer vision, convolutional neural networks, and PyTorch
  • Learn how to use PyTorch for object classification understanding and object detection and how to put PyTorch models into production via Caffe2


Computer vision has led the artificial intelligence renaissance. In a few short years, we have seen advancements in computer vision research turned into production-level systems from web applications to mobile devices and the automotive industry, to name a few. Much of this progress is derived from convolutional neural networks (CNNs), and techniques such as object classification, localization and detection, tracking, and segmentation are foundational concepts for most vision-based applications today.

PyTorch enables researchers and practitioners to more easily build CNNs for computer vision. Released in early 2017, it has increasingly gained popularity in the computer vision community. Mo Patel offers an overview of computer vision fundamentals and walks you through PyTorch code explanations for notable objection classification and object detection models. There will be an equal balance of theory and hands-on PyTorch coding. You’ll also learn how to deploy PyTorch models into production via Caffe2.

Photo of Mo Patel

Mo Patel


Mo Patel is an independent deep learning consultant advising individuals, startups, and enterprise clients on strategic and technical AI topics. Mo has successfully managed and executed data science projects with clients across several industries, including cable, auto manufacturing, medical device manufacturing, technology, and car insurance. Previously, he was practice director for AI and deep learning at Think Big Analytics, a Teradata company, where he mentored and advised Think Big clients and provided guidance on ongoing deep learning projects; he was also a management consultant and a software engineer earlier in his career. A continuous learner, Mo conducts research on applications of deep learning, reinforcement learning, and graph analytics toward solving existing and novel business problems and brings a diversity of educational and hands-on expertise connecting business and technology. He holds an MBA, a master’s degree in computer science, and a bachelor’s degree in mathematics.

Comments on this page are now closed.


Picture of Mo Patel
4/10/2018 14:16 BST

Yes. A machine with CUDA enabled GPU is not required for the tutorial.

4/10/2018 13:40 BST

Can we still ‘follow along’ if our machine does not have a CUDA-enabled GPU?

Picture of Mo Patel
28/08/2018 5:17 BST

Hi Robert,
For now PyTorch should be sufficient along with Jupyter Notebook. If you mean Caffe 2 to export you model for production purposes certainly we will cover that use case, however there are some changes on the horizon so I will attempt to present the most update to materials.

24/08/2018 16:09 BST

Should we have Caffe installed before the tutorial?