raytune as docker

src/docker-compose.tuning.doctr.yml

@@ -0,0 +1,50 @@
+# docker-compose.tuning.doctr.yml - Ray Tune with DocTR GPU
+# Usage:
+#   docker compose -f docker-compose.tuning.doctr.yml up -d doctr-gpu
+#   docker compose -f docker-compose.tuning.doctr.yml run raytune --service doctr --samples 64
+#   docker compose -f docker-compose.tuning.doctr.yml down
+
+services:
+  raytune:
+    image: seryus.ddns.net/unir/raytune:latest
+    command: ["--service", "doctr", "--host", "doctr-gpu", "--port", "8000", "--samples", "64"]
+    volumes:
+      - ./results:/app/results:rw
+    environment:
+      - PYTHONUNBUFFERED=1
+    depends_on:
+      doctr-gpu:
+        condition: service_healthy
+
+  doctr-gpu:
+    image: seryus.ddns.net/unir/doctr-gpu:latest
+    container_name: doctr-gpu-tuning
+    ports:
+      - "8003:8000"
+    volumes:
+      - ./dataset:/app/dataset:ro
+      - ./debugset:/app/debugset:rw
+      - doctr-cache:/root/.cache/doctr
+    environment:
+      - PYTHONUNBUFFERED=1
+      - CUDA_VISIBLE_DEVICES=0
+      - DOCTR_DET_ARCH=db_resnet50
+      - DOCTR_RECO_ARCH=crnn_vgg16_bn
+    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: 180s
+
+volumes:
+  doctr-cache:
+    name: doctr-model-cache