Docker Deployment

Deploy YOLO-Toys using Docker containers.

---

📋 Prerequisites

• Docker 20.10+
• Docker Compose 2.0+ (optional)
• 4GB+ available RAM
• 2GB+ free disk space

---

🚀 Quick Start

Using Docker Run

# Clone repository
git clone https://github.com/LessUp/yolo-toys.git
cd yolo-toys

# Copy environment configuration
cp .env.example .env

# Build and run
docker build -t yolo-toys .
docker run -d -p 8000:8000 --env-file .env yolo-toys

Using Docker Compose (Recommended)

docker-compose up -d

---

⚙️ docker-compose.yml Reference

services:
  yolo-toys:
    build: .
    ports:
      - "8000:8000"
    environment:
      - MODEL_NAME=yolov8n.pt
      - DEVICE=cpu
    volumes:
      - model-cache:/root/.cache
    restart: unless-stopped

volumes:
  model-cache:

---

🖥️ GPU Support

NVIDIA GPU

services:
  yolo-toys:
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - DEVICE=cuda:0

---

🔧 Production Deployment

Reverse Proxy (Nginx)

server {
    listen 80;
    server_name yourdomain.com;

    location / {
        proxy_pass http://localhost:8000;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection 'upgrade';
    }
}

---

🔗 Related Documentation

• Installation — Native installation
• Environment Variables — Configuration reference
• Architecture — System design