BEGIN:VCALENDAR
VERSION:2.0
PRODID:Raspberry Pi Events
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260603T160830Z
UID:dac23829-3949-4937-bfab-809dc1fae5b1
DTSTART:20260609T133000Z
DTEND:20260609T143000Z
CLASS:PUBLIC
DESCRIPTION:Through hands-on Python code\, participants will train Ultralyt
 ics YOLO models\, including the latest YOLO26\, across a comprehensive set
  of computer vision tasks: object detection\, instance segmentation\, pose
  estimation\, oriented object detection (OBB)\, image classification\, mul
 ti-object tracking\, and open vocabulary detection. Open vocabulary models
  extend traditional detection beyond fixed category lists\, enabling flexi
 ble recognition driven by natural language\, a powerful paradigm for real-
 world deployment scenarios. \n\n\n\nA significant portion of the workshop 
 is dedicated to the full edge deployment pipeline\, and we will not shy aw
 ay from its complexity. Compiling a model for edge hardware is rarely a st
 raightforward process. It involves understanding the specific constraints 
 of each target platform\, navigating toolchains that differ significantly 
 across vendors\, managing quantization precision and its impact on accurac
 y\, handling operator compatibility issues\, and validating that the compi
 led model behaves as expected on device. We will walk through this process
  step by step\, demystifying quantization\, compilation\, and hardware-spe
 cific model export so that attendees come away with a realistic and practi
 cal understanding of what production edge deployment actually involves. \n
 \n\n\nThe workshop goes beyond slides and code. Attendees will have access
  to physical edge hardware devices brought directly to the session\, as we
 ll as live online connections to additional platforms\, allowing participa
 nts to witness real inference performance across multiple chips firsthand.
  This includes platforms such as STMicroelectronics STM32N6\, Intel OpenVI
 NO\, DeepX\, Axelera\, NVIDIA Jetson\, and many more. Rather than simply s
 howing benchmark numbers\, we will demonstrate how these results are achie
 ved and how attendees can replicate the same process on their own hardware
  targets using the Ultralytics ecosystem.\n\n\n\nIn addition\, the worksho
 p will feature contributions from hardware and software partners operating
  at the frontier of edge AI. These partners will share insights into the e
 ngineering work behind their platforms\, covering topics such as NPU archi
 tecture\, vendor-specific SDK toolchains\, model optimization strategies t
 ailored to their hardware\, and the practical lessons learned from deployi
 ng vision models at scale on constrained devices. This gives attendees a r
 are opportunity to engage directly with the teams building the chips and t
 ools that power modern edge AI systems. Participants will leave with worki
 ng code\, hands-on deployment experience across multiple real hardware pla
 tforms\, and a solid and honest framework for navigating the full complexi
 ty of bringing Ultralytics YOLO models from training to the edge in their 
 own projects.\n\n\nTARGET AUDIENCE\n\nMachine learning engineers\, compute
 r vision practitioners\, embedded systems developers\, and hardware engine
 ers interested in production edge AI deployment across diverse platforms.\
 n\n\nPREREQUISITES\n\nBasic familiarity with Python and deep learning conc
 epts. \n\nNo prior experience with Ultralytics or edge deployment required
 .\n\nhttps://events.raspberrypi.com/community/f1909be8-7ba0-4249-af85-9b0e
 ffc83a83
SUMMARY:Computer Vision at the Edge: Training and Deploying Ultralytics YOL
 O Models Across Real Hardware
END:VEVENT
END:VCALENDAR