> 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/roboflow-3.md).

# Roboflow 3.0

Roboflow 3.0은 Roboflow의 사내 모델 아키텍처입니다. 객체 탐지, 인스턴스 분할, 분류, 키포인트 탐지를 지원합니다. Roboflow 3.0 모델은 Roboflow 플랫폼에서 학습하고, 우리의 [Serverless Hosted API](/roboflow/roboflow-ko/deploy/serverless-hosted-api-v2.md).

셀프 호스팅 배포의 경우 다음을 참조하세요: [Roboflow Inference](https://inference.roboflow.com/).

{% hint style="info" %}
Roboflow 3.0에는 공개된 기본 COCO 별칭이 없습니다. 학습한 자체 모델은 다음을 사용해 호출합니다. `project/version` 식별자를 다음에서 가져옵니다. [Roboflow Project](https://app.roboflow.com/).
{% endhint %}

## 코드 샘플

다음을 설치하세요: [Inference SDK](https://inference.roboflow.com/) 및 [supervision](https://supervision.roboflow.com/):

```bash
pip install inference-sdk supervision
```

아래 샘플은 학습한 Roboflow 3.0 모델에 대해 추론을 실행합니다. 다음으로 바꾸세요 `your-project/1` 을 모델 URL과 버전으로 바꾸세요. 다음을 전달하세요. [Roboflow API Key](https://app.roboflow.com/settings/api) 다음을 통해 `API_KEY` 환경 변수.

### 객체 탐지

```python
import os
import cv2
import urllib.request
import supervision as sv
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/cars-highway.png"
image_path = "cars-highway.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image, model_id="your-project/1")

detections = sv.Detections.from_inference(result)
labels = [
    f"{class_name} {confidence:.2f}"
    for class_name, confidence
    in zip(detections.data.get("class_name", []), detections.confidence)
]

annotated = sv.BoxAnnotator().annotate(scene=image.copy(), detections=detections)
annotated = sv.LabelAnnotator().annotate(scene=annotated, detections=detections, labels=labels)
cv2.imwrite("output.png", annotated)
```

### 인스턴스 분할

```python
import os
import cv2
import urllib.request
import supervision as sv
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/bicycle.png"
image_path = "bicycle.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image, model_id="your-project/1")

detections = sv.Detections.from_inference(result)
labels = [
    f"{class_name} {confidence:.2f}"
    for class_name, confidence
    in zip(detections.data.get("class_name", []), detections.confidence)
]

annotated = sv.MaskAnnotator().annotate(scene=image.copy(), detections=detections)
annotated = sv.LabelAnnotator().annotate(scene=annotated, detections=detections, labels=labels)
cv2.imwrite("output.png", annotated)
```

### 키포인트 탐지

```python
import os
import cv2
import urllib.request
import supervision as sv
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/person-walking.png"
image_path = "person-walking.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image, model_id="your-project/1")

key_points = sv.KeyPoints.from_inference(result)

annotated = sv.EdgeAnnotator(color=sv.Color.BLUE, thickness=2).annotate(
    scene=image.copy(), key_points=key_points
)
annotated = sv.VertexAnnotator(color=sv.Color.GREEN, radius=5).annotate(
    scene=annotated, key_points=key_points
)
cv2.imwrite("output.png", annotated)
```

### 분류

분류 응답에는 신뢰도와 함께 클래스 예측 목록이 포함되므로 시각화는 적용되지 않습니다. 응답에서 최상위 클래스를 직접 읽어오세요.

```python
import os
import cv2
import urllib.request
from inference_sdk import InferenceHTTPClient

image_url = "https://storage.googleapis.com/com-roboflow-marketing/notebooks/examples/cars-highway.png"
image_path = "cars-highway.png"
urllib.request.urlretrieve(image_url, image_path)

image = cv2.imread(image_path)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image, model_id="your-project/1")

print(f"Top class: {result['top']} ({result['confidence']:.4f})")
```

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

* `https://serverless.roboflow.com` 은 Serverless Hosted API용입니다.
* `http://localhost:9001` 로컬 [Inference](https://inference.roboflow.com/) 서버용입니다.
* 귀하의 [Dedicated Deployment](/roboflow/roboflow-ko/deploy/dedicated-deployments.md) 비공개 엔드포인트용 URL입니다.
  {% endhint %}


---

# 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/roboflow-3.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.