detectron2 Docker & Self-Hosted Deployment

GitHub

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

34,625 stars Python Python 1 file · ~3,135 tokens
RAW Compose
1. Pull Image (DOCKERHUB) docker pull facebookresearch/detectron2
2. Docker Run (1-Click Launch) docker run -d --name detectron2 --restart always facebookresearch/detectron2:latest
3. Podman Run podman run -d --name detectron2 --restart always facebookresearch/detectron2:latest
4. Skopeo Inspect (Zero-Pull Manifest) skopeo inspect docker://docker.io/facebookresearch/detectron2:latest
5. ORAS Pull (OCI Artifact) oras pull facebookresearch/detectron2:latest
6. Compose Deployment docker compose up -d
docker/docker-compose.yml
Download .yml 
version: "2.3"
services:
  detectron2:
    build:
      context: .
      dockerfile: Dockerfile
      args:
        USER_ID: ${USER_ID:-1000}
    deploy:
      resources:
        reservations:
          devices:
            - capabilities:
              - gpu
    shm_size: "8gb"
    ulimits:
      memlock: -1
      stack: 67108864
    volumes:
      - /tmp/.X11-unix:/tmp/.X11-unix:ro
    environment:
      - DISPLAY=$DISPLAY
      - NVIDIA_VISIBLE_DEVICES=all
    # Uncomment with proper source to access webcam from docker
    # devices: 
    #   - /dev/video0:/dev/video0