Skip to content

YOLOv12-AMC2fLEFEM: "A novel low light object detection method based on the YOLOv5 fusion feature enhancement" (https://doi.org/10.1038/s41598-024-54428-8) implemented with YOLOv12

License

Notifications You must be signed in to change notification settings

vmc-7645/yolov12-AMC2fLEFEM

 
 

Repository files navigation

YOLOv12-AMC2fLEFEM

YOLOv12-AMC2fLEFEM: Attention-Centric Real-Time Object Detectors With Novel Low Light Object Detection

Preliminary Results

Performs 20% better than YOLOv12 base fine-tuning on [UNLISTED] low contrast dataset.

Install

git clone https://github.com/vmc-7645/yolov12-AMC2fLEFEM.git
cd yolov12-AMC2fLEFEM
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Train

yolo train model=/home/user/repos/yolov12-AMC2fLEFEM/ultralytics/cfg/models/v12/yolov12n.yaml data=/home/user/repos/LSModels/utility/dataset/data.yaml epochs=16 imgsz=640

Export

python3 toonnx.py

Acknowledgement

The code is based on ultralytics. Thanks for their excellent work!

Citation

@article{tian2025yolov12,
  title={YOLOv12: Attention-Centric Real-Time Object Detectors},
  author={Tian, Yunjie and Ye, Qixiang and Doermann, David},
  journal={arXiv preprint arXiv:2502.12524},
  year={2025}
}

About

YOLOv12-AMC2fLEFEM: "A novel low light object detection method based on the YOLOv5 fusion feature enhancement" (https://doi.org/10.1038/s41598-024-54428-8) implemented with YOLOv12

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.6%
  • Other 0.4%