Downloads · 30 days
347
11% of all-time downloads
rezzzq/yolo12s-road-damage-rdd2022
yolo12s-road-damage-rdd2022 is a object detection model from rezzzq. Use it when you need objects located in an image. It is set up for ultralytics. The card lists the license as mit.
A YOLOv12-small model fine-tuned on the Road Damage Dataset 2022 (RDD2022) for detecting road surface damage.
Downloads · 30 days
347
11% of all-time downloads
All-time downloads
3.2K
Public
Repo size
19 MB
Likes
6
Public
Click a slice to open those files.
.pt19 MB · 100%
From the Hugging Face model README
A YOLOv12-small model fine-tuned on the Road Damage Dataset 2022 (RDD2022) for detecting road surface damage.
| Class | Description |
|---|---|
| D00 | Longitudinal Crack |
| D10 | Transverse Crack |
| D20 | Alligator Crack |
| D40 | Pothole |
| Repair | Repaired Area |
# Install YOLOv12 ultralytics fork
# pip install git+https://github.com/sunsmarterjie/yolov12.git
from ultralytics import YOLO
# Load model
model = YOLO("rezzzq/yolo12s-road-damage-rdd2022")
# or download and load locally:
# model = YOLO("yolo12s_RDD2022_best.pt")
# Run inference
results = model("path/to/road_image.jpg")
# Process results
for result in results:
boxes = result.boxes
for box in boxes:
cls = int(box.cls[0])
conf = float(box.conf[0])
print(f"Class: {model.names[cls]}, Confidence: {conf:.2%}")
If you use this model, please cite the RDD2022 dataset:
@article{arya2022rdd2022,
title={RDD2022: A multi-national image dataset for automatic Road Damage Detection},
author={Arya, Deeksha and others},
year={2022}
}