---
license: agpl-3.0
pipeline_tag: zero-shot-object-detection
library_name: yolov26
---

# YOLOE-26M-seg

YOLOE-26 integrates the high-performance YOLO26 architecture with the open-vocabulary capabilities of the YOLOE series. It enables real-time detection and segmentation of any object class using text prompts, visual prompts, or a prompt-free mode for zero-shot inference, effectively removing the constraints of fixed-category training.

By leveraging YOLO26's NMS-free, end-to-end design, YOLOE-26 delivers fast open-world inference. This makes it a powerful solution for edge applications in dynamic environments where the objects of interest represent a broad and evolving vocabulary.

## Model Details

- **Parameters**: 27.9M
- **FLOPs**: 70.1B
- **mAP<sup>minival</sup><sub>50-95</sub> (e2e)**: 35.4 / 31.3
- **mAP<sup>minival</sup><sub>50-95</sub>**: 35.4 / 33.9
- **Input Size**: 640x640

## Usage

Install ultralytics with `pip install ultralytics`.

Download the model:
```python
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="openvision/yoloe-26m-seg", filename="model.pt")
```

Infer:
```python
from ultralytics import YOLO
from PIL import Image
import requests

model = YOLO(model_path)
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
names = ["striped cat"]
image = Image.open(requests.get(url, stream=True).raw)
model.set_classes(names, model.get_text_pe(names))

results = model.predict(image)
results[0].show()
```

## Documentation

For more information, visit the [official YOLO26 documentation](https://docs.ultralytics.com/models/yolo26/).

## License

This model is released under the AGPL-3.0 license.