raytune as docker

src/docker-compose.tuning.paddle.yml

@@ -0,0 +1,50 @@
+# docker-compose.tuning.paddle.yml - Ray Tune with PaddleOCR GPU
+# Usage:
+#   docker compose -f docker-compose.tuning.paddle.yml up -d paddle-ocr-gpu
+#   docker compose -f docker-compose.tuning.paddle.yml run raytune --service paddle --samples 64
+#   docker compose -f docker-compose.tuning.paddle.yml down
+
+services:
+  raytune:
+    image: seryus.ddns.net/unir/raytune:latest
+    command: ["--service", "paddle", "--host", "paddle-ocr-gpu", "--port", "8000", "--samples", "64"]
+    volumes:
+      - ./results:/app/results:rw
+    environment:
+      - PYTHONUNBUFFERED=1
+    depends_on:
+      paddle-ocr-gpu:
+        condition: service_healthy
+
+  paddle-ocr-gpu:
+    image: seryus.ddns.net/unir/paddle-ocr-gpu:latest
+    container_name: paddle-ocr-gpu-tuning
+    ports:
+      - "8002:8000"
+    volumes:
+      - ./dataset:/app/dataset:ro
+      - ./debugset:/app/debugset:rw
+      - paddlex-cache:/root/.paddlex
+    environment:
+      - PYTHONUNBUFFERED=1
+      - CUDA_VISIBLE_DEVICES=0
+      - PADDLE_DET_MODEL=PP-OCRv5_mobile_det
+      - PADDLE_REC_MODEL=PP-OCRv5_mobile_rec
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+
+volumes:
+  paddlex-cache:
+    name: paddlex-model-cache