Link to this section사전 훈련된 YOLO 모델을 Ultralytics와 함께 Vertex AI에 배포하여 추론 수행하기#

YOUR_PROJECT/
├── src/
│   ├── __init__.py
│   ├── app.py              # Core YOLO26 inference logic
│   └── main.py             # FastAPI inference server
├── tests/
├── .env                    # Environment variables for local development
├── Dockerfile              # Container configuration
├── LICENSE                 # AGPL-3.0 License
└── pyproject.toml          # Python dependencies and project config

[project]
name = "YOUR_PROJECT_NAME"
version = "0.0.1"
description = "YOUR_PROJECT_DESCRIPTION"
requires-python = ">=3.10,<3.13"
dependencies = [
   "ultralytics>=8.3.0",
   "fastapi[all]>=0.89.1",
   "uvicorn[standard]>=0.20.0",
   "pillow>=9.0.0",
]

[build-system]
requires = ["setuptools>=61.0"]
build-backend = "setuptools.build_meta"

# src/app.py

from ultralytics import YOLO

# Model initialization and readiness state
model_yolo = None
_model_ready = False

def _initialize_model():
    """Initialize the YOLO model."""
    global model_yolo, _model_ready

    try:
        # Use pretrained YOLO26n model from Ultralytics base image
        model_yolo = YOLO("yolo26n.pt")
        _model_ready = True

    except Exception as e:
        print(f"Error initializing YOLO model: {e}")
        _model_ready = False
        model_yolo = None

# Initialize model on module import
_initialize_model()

def is_model_ready() -> bool:
    """Check if the model is ready for inference."""
    return _model_ready and model_yolo is not None

def get_image_from_bytes(binary_image: bytes) -> Image.Image:
    """Convert image from bytes to PIL RGB format."""
    input_image = Image.open(io.BytesIO(binary_image)).convert("RGB")
    return input_image

def get_bytes_from_image(image: Image.Image) -> bytes:
    """Convert PIL image to bytes."""
    return_image = io.BytesIO()
    image.save(return_image, format="JPEG", quality=85)
    return_image.seek(0)
    return return_image.getvalue()

def run_inference(input_image: Image.Image, confidence_threshold: float = 0.5) -> Dict[str, Any]:
    """Run inference on an image using YOLO26n model."""
    global model_yolo

    # Check if model is ready
    if not is_model_ready():
        print("Model not ready for inference")
        return {"detections": [], "results": None}

    try:
        # Make predictions and get raw results
        results = model_yolo.predict(
            imgsz=640, source=input_image, conf=confidence_threshold, save=False, augment=False, verbose=False
        )

        # Extract detections (bounding boxes, class names, and confidences)
        detections = []
        if results and len(results) > 0:
            result = results[0]
            if result.boxes is not None and len(result.boxes.xyxy) > 0:
                boxes = result.boxes

                # Convert tensors to numpy for processing
                xyxy = boxes.xyxy.cpu().numpy()
                conf = boxes.conf.cpu().numpy()
                cls = boxes.cls.cpu().numpy().astype(int)

                # Create detection dictionaries
                for i in range(len(xyxy)):
                    detection = {
                        "xmin": float(xyxy[i][0]),
                        "ymin": float(xyxy[i][1]),
                        "xmax": float(xyxy[i][2]),
                        "ymax": float(xyxy[i][3]),
                        "confidence": float(conf[i]),
                        "class": int(cls[i]),
                        "name": model_yolo.names.get(int(cls[i]), f"class_{int(cls[i])}"),
                    }
                    detections.append(detection)

        return {
            "detections": detections,
            "results": results,  # Keep raw results for annotation
        }
    except Exception as e:
        # If there's an error, return empty structure
        print(f"Error in YOLO detection: {e}")
        return {"detections": [], "results": None}

def get_annotated_image(results: list) -> Image.Image:
    """Get annotated image using Ultralytics built-in plot method."""
    if not results or len(results) == 0:
        raise ValueError("No results provided for annotation")

    result = results[0]
    # Use Ultralytics built-in plot method with PIL output
    return result.plot(pil=True)

import sys

from loguru import logger

# Configure logger
logger.remove()
logger.add(
    sys.stdout,
    colorize=True,
    format="<green>{time:HH:mm:ss}</green> | <level>{message}</level>",
    level=10,
)
logger.add("log.log", rotation="1 MB", level="DEBUG", compression="zip")

# Vertex AI environment variables
AIP_HTTP_PORT = int(os.getenv("AIP_HTTP_PORT", "8080"))
AIP_HEALTH_ROUTE = os.getenv("AIP_HEALTH_ROUTE", "/health")
AIP_PREDICT_ROUTE = os.getenv("AIP_PREDICT_ROUTE", "/predict")

# Request size limit (10 MB for private endpoints, 1.5 MB for public)
MAX_REQUEST_SIZE = 10 * 1024 * 1024  # 10 MB in bytes

# Pydantic models for request/response
class PredictionRequest(BaseModel):
    instances: list
    parameters: Optional[Dict[str, Any]] = None

class PredictionResponse(BaseModel):
    predictions: list

# Health check endpoint
@app.get(AIP_HEALTH_ROUTE, status_code=status.HTTP_200_OK)
def health_check():
    """Health check endpoint for Vertex AI."""
    if not is_model_ready():
        raise HTTPException(status_code=503, detail="Model not ready")
    return {"status": "healthy"}

@app.post(AIP_PREDICT_ROUTE, response_model=PredictionResponse)
async def predict(request: PredictionRequest):
    """Prediction endpoint for Vertex AI."""
    try:
        predictions = []

        for instance in request.instances:
            if isinstance(instance, dict):
                if "image" in instance:
                    image_data = base64.b64decode(instance["image"])
                    input_image = get_image_from_bytes(image_data)
                else:
                    raise HTTPException(status_code=400, detail="Instance must contain 'image' field")
            else:
                raise HTTPException(status_code=400, detail="Invalid instance format")

            # Extract YOLO26 parameters if provided
            parameters = request.parameters or {}
            confidence_threshold = parameters.get("confidence", 0.5)
            return_annotated_image = parameters.get("return_annotated_image", False)

            # Run inference with YOLO26n model
            result = run_inference(input_image, confidence_threshold=confidence_threshold)
            detections_list = result["detections"]

            # Format predictions for Vertex AI
            detections = []
            for detection in detections_list:
                formatted_detection = {
                    "class": detection["name"],
                    "confidence": detection["confidence"],
                    "bbox": {
                        "xmin": detection["xmin"],
                        "ymin": detection["ymin"],
                        "xmax": detection["xmax"],
                        "ymax": detection["ymax"],
                    },
                }
                detections.append(formatted_detection)

            # Build prediction response
            prediction = {"detections": detections, "detection_count": len(detections)}

            # Add annotated image if requested and detections exist
            if (
                return_annotated_image
                and result["results"]
                and result["results"][0].boxes is not None
                and len(result["results"][0].boxes) > 0
            ):
                import base64

                annotated_image = get_annotated_image(result["results"])
                img_bytes = get_bytes_from_image(annotated_image)
                prediction["annotated_image"] = base64.b64encode(img_bytes).decode("utf-8")

            predictions.append(prediction)

        logger.info(
            f"Processed {len(request.instances)} instances, found {sum(len(p['detections']) for p in predictions)} total detections"
        )

        return PredictionResponse(predictions=predictions)

    except HTTPException:
        # Re-raise HTTPException as-is (don't catch and convert to 500)
        raise
    except Exception as e:
        logger.error(f"Prediction error: {e}")
        raise HTTPException(status_code=500, detail=f"Prediction failed: {e}")

if __name__ == "__main__":
    import uvicorn

    logger.info(f"Starting server on port {AIP_HTTP_PORT}")
    logger.info(f"Health check route: {AIP_HEALTH_ROUTE}")
    logger.info(f"Predict route: {AIP_PREDICT_ROUTE}")
    uvicorn.run(app, host="0.0.0.0", port=AIP_HTTP_PORT)

# Install dependencies
uv pip install -e .

# Run the FastAPI server directly
uv run src/main.py

# Test health endpoint
curl http://localhost:8080/health

# Test predict endpoint with base64 encoded image
curl -X POST -H "Content-Type: application/json" -d "{\"instances\": [{\"image\": \"$(base64 -i tests/test_image.jpg)\"}]}" http://localhost:8080/predict

# Extends official Ultralytics Docker image for YOLO26
FROM ultralytics/ultralytics:latest

ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1

# Install FastAPI and dependencies
RUN uv pip install fastapi[all] uvicorn[standard] loguru

WORKDIR /app
COPY src/ ./src/
COPY pyproject.toml ./

# Install the application package
RUN uv pip install -e .

RUN mkdir -p /app/logs
ENV PYTHONPATH=/app/src

# Port for Vertex AI
EXPOSE 8080

# Start the inference server
ENTRYPOINT ["python", "src/main.py"]

docker build --platform linux/amd64 -t IMAGE_NAME:IMAGE_VERSION .

docker run --platform linux/amd64 -p 8080:8080 IMAGE_NAME:IMAGE_VERSION

# Test health endpoint
curl http://localhost:8080/health

# Test predict endpoint with base64 encoded image
curl -X POST -H "Content-Type: application/json" -d "{\"instances\": [{\"image\": \"$(base64 -i tests/test_image.jpg)\"}]}" http://localhost:8080/predict

gcloud auth configure-docker YOUR_REGION-docker.pkg.dev

docker tag IMAGE_NAME:IMAGE_VERSION YOUR_REGION-docker.pkg.dev/YOUR_PROJECT_ID/YOUR_REPOSITORY_NAME/IMAGE_NAME:IMAGE_VERSION

docker push YOUR_REGION-docker.pkg.dev/YOUR_PROJECT_ID/YOUR_REPOSITORY_NAME/IMAGE_NAME:IMAGE_VERSION