← Modelos

CV / YOLOv5

YOLOv5

Modelos de detección de objetos YOLOv5n/s/m para reComputer RK3588/RK3576 (RKNN) y reComputer R Series con Hailo-8 o Hailo-10H.

441 descargas
Tamaño
~5.1MB
Memoria
1GB+
Precisión
INT8 / Hailo HEF

Elige el dispositivo que estás usando. La guía de configuración y la documentación se actualizarán en consecuencia.

Primeros pasos

Desplegar
sudo docker run --rm \
  --name rk3588-yolov5n \
  --privileged \
  --net=host \
  -e PYTHONUNBUFFERED=1 \
  -e RKNN_LOG_LEVEL=0 \
  --device /dev/video0:/dev/video0 \
  --device /dev/dri/renderD128:/dev/dri/renderD128 \
  -v /proc/device-tree/compatible:/proc/device-tree/compatible \
  ghcr.io/seeed-projects/recomputer-rk-cv/rk3588-yolov5:latest \
  python3 web_detection.py --model_path model/yolov5n.rknn --video video/test.mp4

Detalles del modelo

reComputer R Series (CM5 + Hailo-8)

YOLOv5 on reComputer R Series (CM5 + Hailo)

YOLOv5 object detection packaged for reComputer R Series with CM5 and a PCIe Hailo-8 accelerator.

This page is adapted from rpi5_hailo8_yolov5/README.md in reComputer-R20-CV. It targets reComputer R Series (CM5 + Hailo) with a PCIe Hailo-8 accelerator.

Hardware and Host Setup

ItemValue
BoardreComputer R Series with Raspberry Pi CM5
AcceleratorHailo-8 M.2 over PCIe, exposed as /dev/hailo0
OSRaspberry Pi OS Bookworm, aarch64
Host driverhailo-all apt package
Validated HailoRT4.23.x; host driver, firmware, native library, and Python wheel must share major.minor
bash
sudo apt update
sudo apt install hailo-all
sudo reboot

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

# Docker
curl -fsSL https://get.docker.com -o get-docker.sh
sudo sh get-docker.sh --mirror Aliyun
sudo systemctl enable docker
sudo systemctl start docker

Run With Demo Video

bash
sudo docker run --rm --privileged --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.4.23.0:/usr/lib/libhailort.so.4.23.0:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-r20-cv/yolov5:latest \
  python web_detection.py --model_path model/yolov5s.hef --video_path video/test.mp4

Open http://<R20_IP>:8000 to view the web preview. The image includes the module source, demo video, HailoRT Python wheel, and HEF files listed below.

The libhailort.so bind mounts intentionally come from the host. If your firmware is not 4.23.0, replace both paths with the version reported by hailortcli fw-control identify; rebuild the image if the major.minor version differs.

USB Camera Mode

bash
sudo docker run --rm --privileged --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  --device /dev/video0:/dev/video0 \
  -v /usr/lib/libhailort.so.4.23.0:/usr/lib/libhailort.so.4.23.0:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-r20-cv/yolov5:latest \
  python web_detection.py --model_path model/yolov5s.hef --camera_id 0

Switch HEF variants

Override the image default by passing a different --model_path:

bash
sudo docker run --rm --privileged --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.4.23.0:/usr/lib/libhailort.so.4.23.0:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-r20-cv/yolov5:latest \
  python web_detection.py --model_path model/yolov5m.hef --video_path video/test.mp4

HEF Files

HEFSizeNotes
yolov5s.hef8.71 MBSmall detector
yolov5m.hef16.31 MBMedium detector

REST API

Prediction endpoint:

text
POST http://<R20_IP>:8000/api/models/yolov5/predict

Example image request:

bash
curl -X POST "http://<R20_IP>:8000/api/models/yolov5/predict" \
  -F "file=@test.jpg"

Common service endpoints:

EndpointMethodPurpose
/GETWeb preview UI
/api/models/yolov5/predictPOSTSingle-frame inference from uploaded image/video or current frame
/api/video_feedGETMJPEG preview stream
/api/configGET / POSTRead or update runtime thresholds
/api/video/uploadPOSTUpload a video for offline analysis
/api/video/analyzePOSTStart offline analysis
/api/video/statusGETPoll analysis progress
/api/video/listGETList uploaded and processed videos
/api/video/download/{filename}GETDownload processed output

Development Notes

  • Source module: src/rpi5_hailo8_yolov5/
  • Dockerfile: docker/hailo8/yolov5.dockerfile
  • Main service: web_detection.py wraps HailoRT inference, post-processing, MJPEG preview, REST prediction, and offline video analysis.
  • When swapping in a custom HEF, keep the output layout compatible with the module post-processing code or update post_process_hailo().