The Open Data Science Conference (East) looked a bit different this year. While typically 6,000+ data science professionals gather in Boston for the Expo, the team at ODSC moved the entire event online. Still, over 3,000 "attendees" gathered in a shared Slack Workspace and online livestream to enjoy the dozens of speakers.

Applied Deep Learning: Building a Chess Object Detection Model with Tensorflow. Joseph Nelson, Cofounder, Principal Data Scientist & Faculty | Roboflow.ai
An overview of my talk.

I had the privilege of offering a three-hour tutorial on building a custom object detection model from scratch. In some ways, the live online delivery format improved the discussion: participants were able to live react to commentary about space, answer one another's questions with minimal disruption, and have a live-log of all comments for after the presentation.

Screen recording of slack showing messages posted during the talk.
Participant were able to follow along live in Slack.

In my tutorial, we walked through a live example of preparing an object detection problem from end-to-end. This includes identifying a good problem statements, tips on collecting images, best practices for labeling images, practical tips on preprocessing, the importance of considering good image augmentations, training a model, and using that model for inference.

I've made all slides available here, the Colab notebook is here, all other models are here, and a resources page for more is here.

If you missed the tutorial, this blog post on training YOLOv3 with a custom dataset is a good complement to the discussion.