In this technical session, Intel and Ultralytics will explore how engineers can move from training to deployment on an edge system. We will dive into the current state of developer tooling: how to train a vision model in Geti™, prepare it for deployment using the OpenVINO™ toolkit, and the Ultralytics YOLO ecosystem. Attendees will see the full compute vision workflow using Geti and OpenVINO, optimized for deployment on Intel® hardware across CPUs, iGPUs, and NPUs. The session will also compare this workflow with more direct deployment approaches using frameworks such as PyTorch, TFLite, and ONNX, helping engineers understand where OpenVINO fits into the wide Edge AI development pipeline.
What you’ll learn:
- Build end-to-end workflows from image annotation to edge deployment.
- How to train custom vision models and accelerate dataset creation with Geti™
- Apply object detection with Ultralytics YOLO26 to manufacturing and inspection tasks to boost automation and efficiency.
- Optimize models with OpenVINO™ toolkit for low-latency, high-performance inference
- What performance, portability, and deployment considerations should engineers understand when deploying vision models across Intel® hardware platforms
Following the technical deep dive, our speakers will join a live panel discussion (with Q&A) on deployment challenges, optimization, common bottlenecks, and portability across Intel devices.
This webinar is presented by
Name
Company
Sed posuere nibh rhoncus, sagittis felis et, maximus sem. Aenean vel mauris maximus massa bibendum pulvinar sed quis arcu. Morbi tempor risus vel interdum varius. Proin nec porttitor dui. Cras nec finibus purus.
Free