基础设施: 统一依赖版本 + 新增 Docker 部署配置

- requirements.txt: GPU 依赖从注释改为正式声明，统一版本
  PyTorch 2.1.2+cu121, TensorRT 8.6.1.6, ultralytics 8.3.5
  NumPy 1.24→1.26.4, OpenCV 4.8.0.74→76, 新增 onnx/Pillow 等
- Dockerfile: 基于 nvcr.io/nvidia/tensorrt:23.08-py3
  (CUDA 12.1 + cuDNN 8.9 + TRT 8.6)
- docker-compose.yml: GPU 访问、host 网络、卷挂载、日志限制
- .dockerignore: 排除模型/数据/日志等大文件

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docker-compose.yml

@@ -0,0 +1,46 @@
+version: "3.8"
+
+services:
+  edge-inference:
+    build: .
+    image: edge-inference:latest
+    container_name: edge-inference
+    restart: always
+
+    # GPU 访问
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+
+    # 环境变量
+    env_file:
+      - .env
+
+    # 卷挂载
+    volumes:
+      - ./models:/app/models        # TensorRT 引擎文件
+      - ./data:/app/data             # SQLite + 截图缓存
+      - ./logs:/app/logs             # 运行日志
+      - ./.env:/app/.env             # 环境配置
+
+    # 网络（需要访问摄像头 RTSP + 云端 API + Redis）
+    network_mode: host
+
+    # 健康检查
+    healthcheck:
+      test: ["CMD", "python", "-c", "import os; assert os.path.exists('/app/main.py')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 30s
+
+    # 日志限制
+    logging:
+      driver: json-file
+      options:
+        max-size: "50m"
+        max-file: "5"