> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/roboflow/roboflow-ko/deploy/supported-models/owlv2.md).

# OwlV2

OwlV2는 Google의 open-vocabulary 객체 감지기입니다. 참조 이미지에 하나 이상의 예시 bounding box를 제공하면, OwlV2는 별도의 학습 없이 대상 이미지에서 유사한 객체를 감지합니다.

{% hint style="info" %}
OwlV2는 Serverless Hosted API에서 사용할 수 없습니다. 다음에서 실행하세요 [Dedicated Deployment](/roboflow/roboflow-ko/deploy/dedicated-deployments.md) 또는 [자체 호스팅 Inference](https://inference.roboflow.com/).
{% endhint %}

## 코드 샘플

의존성을 설치하세요:

```bash
pip install requests supervision opencv-python
```

아래 예시는 입력 이미지의 단일 예시 box를 prompt로 사용하여 같은 이미지에서 일치하는 객체를 감지합니다. 실제로는 일반적으로 별도의 참조 이미지를 전달합니다. 설정하세요 `URL` 를 Dedicated Deployment URL 또는 로컬 Inference 서버로 설정하세요. 다음을 전달하세요 [Roboflow API Key](https://app.roboflow.com/settings/api) 를 `API_KEY` 환경 변수.

```python
import base64
import os
import urllib.request

import cv2
import numpy as np
import requests
import supervision as sv

URL = "https://your-deployment.roboflow.cloud"
IMAGE_URL = "https://media.roboflow.com/notebooks/examples/dog.jpeg"
IMAGE_PATH = "dog.jpeg"
OUTPUT_PATH = "dog_annotated.png"

urllib.request.urlretrieve(IMAGE_URL, IMAGE_PATH)
image = cv2.imread(IMAGE_PATH)
_, buffer = cv2.imencode(".jpg", image)
image_base64 = base64.b64encode(buffer).decode("utf-8")

response = requests.post(
    f"{URL}/owlv2/infer",
    json={
        "api_key": os.getenv("API_KEY"),
        "image": {"type": "base64", "value": image_base64},
        "training_data": [{
            "image": {"type": "base64", "value": image_base64},
            "boxes": [{"x": 360, "y": 800, "w": 500, "h": 500, "cls": "dog"}],
        }],
        "confidence": 0.99,
    },
)
preds = response.json()["predictions"]

xyxys = [
    [p["x"] - p["width"] / 2, p["y"] - p["height"] / 2,
     p["x"] + p["width"] / 2, p["y"] + p["height"] / 2]
    for p in preds
]
detections = sv.Detections(
    xyxy=np.array(xyxys, dtype=float),
    class_id=np.array([p.get("class_id", 0) for p in preds]),
    confidence=np.array([p["confidence"] for p in preds], dtype=float),
    data={"class_name": np.array([p["class"] for p in preds])},
)
labels = [f"{p['class']} {p['confidence']:.2f}" for p in preds]
annotated = sv.BoxAnnotator().annotate(scene=image.copy(), detections=detections)
annotated = sv.LabelAnnotator().annotate(scene=annotated, detections=detections, labels=labels)
cv2.imwrite(OUTPUT_PATH, annotated)
```

<figure><img src="/files/34197b440bc496e95964824b06b1a2290c5b6947" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
설정하세요 `URL` 를 배포 대상에 맞게:

* `http://localhost:9001` 로컬 [Inference](https://inference.roboflow.com/) 서버용.
* 귀하의 [Dedicated Deployment](/roboflow/roboflow-ko/deploy/dedicated-deployments.md) 개인 엔드포인트용 URL.
  {% endhint %}

OwlV2의 confidence는 일반적으로 매우 높습니다(0.99 이상). 다음을 조정하세요 `confidence` 매개변수를 그에 맞게.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.roboflow.com/roboflow/roboflow-ko/deploy/supported-models/owlv2.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.