> 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/deploy/supported-models/yolov7.md).

# YOLOv7

We support YOLOv7 instance segmentation inferencing via our [Serverless Hosted API](/deploy/serverless-hosted-api-v2.md). Training YOLOv7 is not supported on Roboflow, but you can [upload your own weights](/deploy/upload-custom-weights.md) and run inference against them.

For self-hosted deployment, see [Roboflow Inference](https://inference.roboflow.com/).

YOLOv7 input size is set when you train your model outside Roboflow (typical values: 640x640 or 1280x1280).

## Code sample

{% stepper %}
{% step %}

### Get your API Key

Create a Roboflow account, find your key on the [Roboflow API settings page](https://app.roboflow.com/settings/api) and make it available to your shell:

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

{% endstep %}

{% step %}

### Install the dependencies

Install the Inference SDK and [supervision](https://supervision.roboflow.com/) for decoding and drawing masks:

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

{% endstep %}

{% step %}

### Run the model

This example runs a public YOLOv7 instance segmentation model trained on [concrete surface defects](https://universe.roboflow.com/road-ywxxe/concrete-pugqq) (`concrete-pugqq/3`), then uses supervision to render the predicted masks. To serve your own weights, swap in your `{workspace}/{model-slug}` ID (see [Versions, Trainings, and Models](/train/versions-trainings-and-models.md)).

```python
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/docs/concrete-crack.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"],
)
results = client.infer(image, model_id="concrete-pugqq/3")

detections = sv.Detections.from_inference(results)

annotated = sv.MaskAnnotator().annotate(image.copy(), detections)

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

<figure><img src="/files/GW8kIJTFPhz7S9TxrbIG" alt=""><figcaption></figcaption></figure>
{% endstep %}
{% endstepper %}

{% hint style="info" %}
Set `api_url` to match your deployment target:

* `https://serverless.roboflow.com` for the Serverless Hosted API.
* `http://localhost:9001` for a local [Inference](https://inference.roboflow.com/) server.
* Your [Dedicated Deployment](/deploy/dedicated-deployments.md) URL for a private endpoint.
  {% endhint %}