A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition

🔧Requirements

Installation

pip install -r requirements.txt

Data Preparation

cd dataset/preprocess
python rap.py

Pre-trained Model

ImageNet pre-trained ViT-Base need to be download for training.

🚀Training

python train.py RAP

📌Citation

If you found this code/work to be useful in your own research, please consider citing the following:

@article{cheng2022simple,
  title={A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition},
  author={Cheng, Xinhua and Jia, Mengxi and Wang, Qian and Zhang, Jian},
  journal={IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)},
  year={2022}
}

👍Acknowledgements

This code is based on Rethinking_of_PAR and TransReID. Thanks for their efforts.