Awesome
<h2 align="center"> A Simple Visual-Textual Baseline for Pedestrian Attribute Recognition </h2> <p align="center"> <img src="assets/teaser.png" width="75%"> </p>🔧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.