> 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-hi/deploy/supported-models/roboflow-2.md).

# Roboflow 2.0

Roboflow 2.0 एक DeepLabv3-आधारित semantic segmentation model है। आप Roboflow 2.0 models को Roboflow platform पर train करते हैं और उन्हें हमारे माध्यम से deploy करते हैं [Serverless Hosted API](/roboflow/roboflow-hi/deploy/serverless-hosted-api-v2.md).

self-hosted deployment के लिए, देखें [Roboflow Inference](https://inference.roboflow.com/).

## कोड नमूना

{% stepper %}
{% step %}

### अपनी API Key प्राप्त करें

एक Roboflow खाता बनाएं, अपनी key यहाँ पर ढूँढें [Roboflow API settings page](https://app.roboflow.com/settings/api) और इसे अपने shell में उपलब्ध कराएँ:

```bash
export ROBOFLOW_API_KEY="your-key-here"
```

{% endstep %}

{% step %}

### निर्भरताएँ इंस्टॉल करें

इंस्टॉल करें [Inference SDK](https://inference.roboflow.com/) और [supervision](https://supervision.roboflow.com/):

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

{% endstep %}

{% step %}

### मॉडल चलाएँ

आपके द्वारा train किए गए Roboflow 2.0 semantic segmentation model पर inference चलाएँ, per-pixel class map को decode करें, और एक annotated PNG लिखें। अपने model को उसके `{workspace}/{model-slug}` ID (देखें [Versions, Trainings, and Models](/roboflow/roboflow-hi/train/versions-trainings-and-models.md)).

Response में एक `segmentation_mask` (base64-encoded grayscale PNG, जिसमें प्रत्येक pixel value एक class ID है और `0` background है) और एक `class_map` class IDs को class names से mapping करता है। Script इसे एक में विभाजित करती है `sv.Detections` प्रत्येक class के लिए एक row, ताकि `sv.MaskAnnotator` source image पर masks overlay कर सके।

```python
import base64
import os
import cv2
import numpy as np
import requests
import supervision as sv
from inference_sdk import InferenceHTTPClient

content = requests.get("https://media.roboflow.com/quickstart/traffic.jpg").content
image = cv2.imdecode(np.frombuffer(content, np.uint8), cv2.IMREAD_COLOR)

client = InferenceHTTPClient(
    api_url="https://serverless.roboflow.com",
    api_key=os.environ["ROBOFLOW_API_KEY"],
)
# No pretrained aliases: अपना model train करें और "your-project/1" को अपने model ID से बदलें।
result = client.infer(image, model_id="your-project/1")
predictions = result["predictions"]

mask_bytes = base64.b64decode(predictions["segmentation_mask"])
class_map = predictions.get("class_map", {})
class_mask = cv2.imdecode(np.frombuffer(mask_bytes, np.uint8), cv2.IMREAD_GRAYSCALE)
class_mask = cv2.resize(class_mask, (image.shape[1], image.shape[0]), interpolation=cv2.INTER_NEAREST)

class_ids = [cid for cid in np.unique(class_mask).tolist() if cid != 0]
if class_ids:
    masks, xyxy, names = [], [], []
    for cid in class_ids:
        binary = class_mask == cid
        rows = np.where(np.any(binary, axis=1))[0]
        cols = np.where(np.any(binary, axis=0))[0]
        xyxy.append([cols[0], rows[0], cols[-1], rows[-1]])
        masks.append(binary)
        names.append(class_map.get(str(cid), str(cid)))

    detections = sv.Detections(
        xyxy=np.array(xyxy, dtype=np.float64),
        mask=np.array(masks),
        class_id=np.array(class_ids),
        data={"class_name": np.array(names)},
    )
    annotated = sv.MaskAnnotator().annotate(image.copy(), detections)
    annotated = sv.LabelAnnotator().annotate(annotated, detections)
else:
    annotated = image

cv2.imwrite("annotated.png", annotated)
print("Saved annotated.png")
```

{% endstep %}
{% endstepper %}

{% hint style="info" %}
सेट करें `api_url` को अपने deployment target से मिलाएँ:

* `https://serverless.roboflow.com` Serverless Hosted API के लिए।
* `http://localhost:9001` एक local [Inference](https://inference.roboflow.com/) server.
* आपका [Dedicated Deployment](/roboflow/roboflow-hi/deploy/dedicated-deployments.md) एक private endpoint के लिए URL.
  {% endhint %}