> 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/yolo26.md).

# YOLO26

저희는 다음을 통해 YOLO26 추론을 지원합니다 [Serverless Hosted API](/roboflow/roboflow-ko/deploy/serverless-hosted-api-v2.md). YOLO26은 네 가지 작업 변형으로 제공됩니다:

* 객체 탐지(COCO 사전 학습됨)
* 인스턴스 분할(COCO 사전 학습됨)
* 키포인트/포즈 탐지(COCO 사전 학습됨)
* 시맨틱 분할(Cityscapes 사전 학습됨)

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

## 코드 샘플

SDK와 다음을 설치하세요 [supervision](https://supervision.roboflow.com/) 주석 처리를 위한 라이브러리:

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

다음 값을 전달하세요 [Roboflow API Key](https://app.roboflow.com/settings/api) 를 `API_KEY` 환경 변수. 각 샘플은 테스트 이미지를 다운로드하고, 다음을 통해 추론을 실행합니다 `inference-sdk`, 다음을 사용해 응답을 디코딩하고 `supervision`, 그리고 주석이 달린 PNG를 디스크에 씁니다.

### 객체 탐지

```python
import os
import urllib.request
import cv2
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)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image_path, model_id="yolo26n-640")
detections = sv.Detections.from_inference(result)

image = cv2.imread(image_path)
labels = [
    f"{cls} {conf:.2f}"
    for cls, conf in zip(detections.data["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("cars-highway-annotated.png", annotated)
```

<figure><img src="/files/56dafc180fa742210493cdb2ec754280fddae06f" alt=""><figcaption></figcaption></figure>

### 인스턴스 분할

```python
import os
import urllib.request
import cv2
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)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image_path, model_id="yolo26n-seg-640")
detections = sv.Detections.from_inference(result)

image = cv2.imread(image_path)
labels = [
    f"{cls} {conf:.2f}"
    for cls, conf in zip(detections.data["class_name"], detections.confidence)
]
annotated = sv.MaskAnnotator().annotate(scene=image.copy(), detections=detections)
annotated = sv.BoxAnnotator().annotate(scene=annotated, detections=detections)
annotated = sv.LabelAnnotator().annotate(
    scene=annotated, detections=detections, labels=labels
)
cv2.imwrite("bicycle-annotated.png", annotated)
```

<figure><img src="/files/0aa3fc8c7582a33593b1c5258bd1ed88a37f66a7" alt=""><figcaption></figcaption></figure>

### 키포인트 탐지

```python
import os
import urllib.request
import cv2
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)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.getenv("API_KEY"),
)
result = client.infer(image_path, model_id="yolo26n-pose-640")
key_points = sv.KeyPoints.from_inference(result)

image = cv2.imread(image_path)
annotated = sv.VertexAnnotator(color=sv.Color.RED, radius=5).annotate(
    scene=image.copy(), key_points=key_points
)
cv2.imwrite("person-walking-annotated.png", annotated)
```

<figure><img src="/files/ada71dc5fd5550e7b68f115167dd0cc337d64778" alt=""><figcaption></figcaption></figure>

### 시맨틱 분할

YOLO26 시맨틱 분할 (`yolo26-sem`)는 Roboflow에서 시맨틱 분할을 위한 권장 아키텍처입니다. Cityscapes 사전 학습 가중치를 사용하며 기본 해상도 1024x1024에서 학습합니다. n, s, m, l, x의 다섯 가지 크기로 제공됩니다.

YOLO26-SEM 모델을 학습하려면 시맨틱 분할 Project를 만들고 아키텍처로 YOLO26을 선택하세요. 또한 [사용자 지정으로 학습한 가중치를 업로드할 수 있습니다](/roboflow/roboflow-ko/deploy/upload-custom-weights.md) YOLO26-SEM 모델에 대해.

Cityscapes 사전 학습 모델(19개 클래스)도 공용 모델로 제공되며, 다음에서 실행할 수 있습니다 [워크플로](/roboflow/roboflow-ko/workflows/what-is-workflows.md) 학습 없이.

## 기본 COCO 별칭

다음 별칭 중 하나를 다음으로 전달하세요 `model_id` SDK를 호출할 때. 다음은 `inference-sdk` 각 별칭을 클라이언트 측에서 해당 사전 학습된 Roboflow Universe 모델로 해석합니다.

| 작업 | 별칭                 |
| -- | ------------------ |
| 감지 | `yolo26n-640`      |
| 감지 | `yolo26s-640`      |
| 감지 | `yolo26m-640`      |
| 감지 | `yolo26l-640`      |
| 감지 | `yolo26x-640`      |
| 분할 | `yolo26n-seg-640`  |
| 분할 | `yolo26s-seg-640`  |
| 분할 | `yolo26m-seg-640`  |
| 분할 | `yolo26l-seg-640`  |
| 분할 | `yolo26x-seg-640`  |
| 포즈 | `yolo26n-pose-640` |
| 포즈 | `yolo26s-pose-640` |
| 포즈 | `yolo26m-pose-640` |
| 포즈 | `yolo26l-pose-640` |
| 포즈 | `yolo26x-pose-640` |

해당 `yolov26*` 접두사 변형은 동일한 모델로 해석됩니다.

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

* `https://serverless.roboflow.com` Serverless Hosted API용.
* `http://localhost:9001` 로컬 [Inference](https://inference.roboflow.com/) 서버용.
* 귀하의 [Dedicated Deployment](/roboflow/roboflow-ko/deploy/dedicated-deployments.md) 개인 엔드포인트용 URL.
  {% 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/yolo26.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.