YOLOv8n — ONNX

ONNX export of YOLOv8n, the nano variant of Ultralytics YOLOv8 object detection model. Trained on COCO with 80-class output. Optimized for real-time inference.

Mirrored for use with inference4j, an inference-only AI library for Java.

Original Source

Repository: Kalray (Ultralytics YOLOv8)
License: agpl-3.0

Usage with inference4j

try (YoloV8 model = YoloV8.fromPretrained("models/yolov8n")) {
    List<Detection> detections = model.detect(Path.of("street.jpg"));
    detections.forEach(d -> System.out.printf("%s (%.0f%%) at [%.0f, %.0f, %.0f, %.0f]%n",
        d.label(), d.confidence() * 100,
        d.box().x1(), d.box().y1(), d.box().x2(), d.box().y2()));
}

Model Details

Property	Value
Architecture	YOLOv8 Nano (single-shot detector)
Task	Object detection (COCO 80 classes)
Input	`[1, 3, 640, 640]` — RGB, normalized 0-1
Output	`[1, 84, 8400]` — bounding boxes + class scores
Post-processing	Non-Maximum Suppression (NMS) required
Original framework	PyTorch (Ultralytics)

License

This model is licensed under the AGPL-3.0 License. Original model by Ultralytics, hosted by Kalray.

Downloads last month: -; Downloads are not tracked for this model. How to track