How to Run Object Detection on Constraint Devices

FOMO (Faster Objects, More Objects) is a novel machine-learning algorithm that brings object detection to highly constrained devices.

FOMO counts objects, finds the location of objects in an image, and tracks multiple objects in real-time using up to 30x less processing power and memory than MobileNet SSD or YOLOv5. In this session, we'll walk through how to use FOMO and where it can be applied.

Go to Session

Live Q&A - How to Run Object Detection on Constraint Devices

Live Q&A with Louis Moreau for the talk titled How to Run Object Detection on Constraint Devices

Go to Session

Automate your ML Pipeline

Louis Moreau will show you how to create complete automated data pipelines so you can work on your active learning strategies. To create your first data source, we will be using an S3-compatible open-source solution that you can install locally on your laptop and expose publicly. Then, we will see how to set up your labeling strategy. Finally, we will configure the pipeline so it can automatically refresh the data explorer, train your model, create a new version of your project, build a library and notify you when it is ready.

Go to Session