Skip to content

Add rzv2n-drpai-yolo reference (YOLOv3 on RZ/V2N DRP-AI3)#11

Open
mobileoverlord wants to merge 1 commit into
mainfrom
jschneck/rzv2n-drpai-yolo
Open

Add rzv2n-drpai-yolo reference (YOLOv3 on RZ/V2N DRP-AI3)#11
mobileoverlord wants to merge 1 commit into
mainfrom
jschneck/rzv2n-drpai-yolo

Conversation

@mobileoverlord

Copy link
Copy Markdown
Contributor

Adds the rzv2n-drpai-yolo reference: YOLOv3 object detection on the SolidRun RZ/V2N HummingBoard SoM, running on the on-chip DRP-AI3 accelerator (Mera2 + TVM runtime) and rendered full-screen on Wayland/Weston.

  • Video-file (default) or IMX678 MIPI-CSI camera input via GStreamer
  • TVM-compiled YOLOv3 from the RZ/V2N AI SDK; fetch-model.sh / fetch-video.sh pull the bundle + sample clip at build time (gitignored)
  • Seek-on-EOS loop, OpenCV bbox overlay, systemd auto-start after Weston
  • Camera path documented as disabled pending a SolidRun rzg2l-cru/IMX678 4K format-misreport driver bug

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant