← Modellen

CV / YOLO26

YOLO26-seg

reComputer R Series (CM5 + Hailo-10H)

YOLO26-segmentatiemodellen (n/s/m/l/x-seg) op reComputer R Series met Hailo-8 of Hailo-10H.

371 downloads
Grootte
6.0 MB
Geheugen
4GB+
Precisie
Hailo HEF / HailoRT

Kies het apparaat dat je gebruikt. De installatiehandleiding en documentatie worden dienovereenkomstig bijgewerkt.

Aan de slag

Implementeren
sudo docker run --rm \
  --name cm5-hailo-yolo26n-seg \
  --privileged \
  --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/yolo26n_seg:latest \
  python web_detection.py --model_path model/yolo26n_seg.hef --video_path video/test.mp4

Modeldetails

reComputer CM5 + Hailo-10H

YOLO26-seg op reComputer CM5 + Hailo-10H

YOLO26n/s/m/l-seg-modellen draaien op de Hailo-10H via HailoRT. De one2one CPU-decodering (DFL + top-k + prototypemaskerassemblage) produceert instantiemaskers en boxes voor 80 COCO-klassen.

Modelinformatie

VariantInvoerMeegeleverde HEFContainerimage
YOLO26n-seg640×640×3 RGB6.0 MByolo26n_seg
YOLO26s-seg640×640×3 RGB17.5 MByolo26s_seg
YOLO26m-seg640×640×3 RGB27.0 MiB (28.3 MB)yolo26m_seg
YOLO26l-seg640×640×3 RGB38.3 MiB (40.1 MB)yolo26l_seg

Hardware- en hostconfiguratie

OnderdeelWaarde
BoardRaspberry Pi CM5
AcceleratorHailo-10H, /dev/hailo0
RuntimeHailoRT 5.1.1
OSRaspberry Pi OS Bookworm, aarch64
bash
sudo apt update
sudo apt install hailo-h10-all -y
sudo reboot

# After reboot
hailortcli fw-control identify
ls /dev/hailo0

Uitvoeren met demovideo

Kies de opdracht die hoort bij de modelvariant.

YOLO26n-seg

bash
sudo docker run --rm --privileged --net=host \
  --name cm5-hailo-yolo26n-seg \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/yolo26n_seg:latest \
  python web_detection.py --model_path model/yolo26n_seg.hef --video_path video/test.mp4

YOLO26s-seg

bash
sudo docker run --rm --privileged --net=host \
  --name cm5-hailo-yolo26s-seg \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/yolo26s_seg:latest \
  python web_detection.py --model_path model/yolo26s_seg.hef --video_path video/test.mp4

YOLO26m-seg

bash
sudo docker run --rm --privileged --net=host \
  --name cm5-hailo-yolo26m-seg \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/yolo26m_seg:latest \
  python web_detection.py --model_path model/yolo26m_seg.hef --video_path video/test.mp4

YOLO26l-seg

bash
sudo docker run --rm --privileged --net=host \
  --name cm5-hailo-yolo26l-seg \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.5.1.1:/usr/lib/libhailort.so.5.1.1:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo10h-cv/yolo26l_seg:latest \
  python web_detection.py --model_path model/yolo26l_seg.hef --video_path video/test.mp4

Open http://<Board_IP>:8000 voor de webvoorbeeld. Gebruik /api/video_feed voor de MJPEG-stream.

REST API

Elke variant heeft een eigen endpoint:

VariantEndpoint
YOLO26n-segPOST /api/models/yolo26n_seg/predict
YOLO26s-segPOST /api/models/yolo26s_seg/predict
YOLO26m-segPOST /api/models/yolo26m_seg/predict
YOLO26l-segPOST /api/models/yolo26l_seg/predict

Voorbeeld:

bash
curl -X POST "http://<Board_IP>:8000/api/models/yolo26n_seg/predict" \
  -F "file=@test.jpg"

De respons bevat predictions-items met de velden box, confidence en class_id.

Ontwikkeling

VariantBronDockerfile
YOLO26n-segsrc/hailo10h_yolo26n_seg/docker/hailo10h/yolo26n_seg.dockerfile
YOLO26s-segsrc/hailo10h_yolo26s_seg/docker/hailo10h/yolo26s_seg.dockerfile
YOLO26m-segsrc/hailo10h_yolo26m_seg/docker/hailo10h/yolo26m_seg.dockerfile
YOLO26l-segsrc/hailo10h_yolo26l_seg/docker/hailo10h/yolo26l_seg.dockerfile

Invoer en uitvoer

Invoer: afbeelding (640x640 RGB). Uitvoer: bounding boxes + instantiemaskers (COCO 80 klassen).