openvision/yoloe26-n-seg

YOLOE-26N-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: 4.8M
• FLOPs: 6.0B
• mAP^minival_50-95 (e2e): 23.7 / 20.9
• mAP^minival_50-95: 24.7 / 21.9
• Input Size: 640x640

Usage

Install ultralytics with pip install ultralytics.

Download the model:

from huggingface_hub import hf_hub_download

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

Infer:

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.

License

This model is released under the AGPL-3.0 license.