SIXray：A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images

[Paper] [dataset]

Requirements

• Python 3.10 or newer
• PyTorch: 2.0.0 or newer

Usage

1. Clone the CHR repository:

   git clone https://github.com/loopback-kr/CHR.git

2. Create new container:

   docker compose up -d

3. Run the training demo in the container:

   python CHR/main.py

Checkpoint

If you only want to test images, you can download here.

Citation

If you use the code in your research, please cite:

@INPROCEEDINGS{Miao2019SIXray,
    author = {Miao, Caijing and Xie, Lingxi and Wan, Fang and Su, chi and Liu, Hongye and Jiao, jianbin and Ye, Qixiang },
    title = {SIXray: A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images},
    booktitle = {CVPR},
    year = {2019}
}

Acknowledgement

This project was forked from MeioJane/CHR and refactored to PyTorch 2.0 or newer.