Awesome

TransCrowd

• An officical implementation of TransCrowd: Weakly-Supervised Crowd Counting with Transformers. To the best of our knowledge, this is the first work to adopt a pure Transformer for crowd counting research. We observe that the proposed TransCrowd can effectively extract the semantic crowd information by using the self-attention mechanism of Transformer.

• Paper Link

Overview

Environment

python >=3.6 
pytorch >=1.5
opencv-python >=4.0
scipy >=1.4.0
h5py >=2.10
pillow >=7.0.0
imageio >=1.18
timm==0.1.30

Datasets

• Download ShanghaiTech dataset from Baidu-Disk, passward:cjnx; or Google-Drive
• Download UCF-QNRF dataset from here
• Download JHU-CROWD ++ dataset from here
• Download NWPU-CROWD dataset from Baidu-Disk, passward:3awa; or Google-Drive

Prepare data

cd data
run  python predataset_xx.py

“xx” means the dataset name, including sh, jhu, qnrf, and nwpu. You should change the dataset path.

Generate image file list:

run python make_npydata.py

Training

Training example:

python train.py --dataset ShanghaiA  --save_path ./save_file/ShanghaiA --batch_size 24 --model_type 'token' 
python train.py --dataset ShanghaiA  --save_path ./save_file/ShanghaiA --batch_size 24 --model_type 'gap'

Please utilize a single GPU with 24G memory or multiple GPU for training. On the other hand, you also can change the batch size.

Testing

Test example:

Download the pretrained model from Baidu-Disk, passward:8a8n

python test.py --dataset ShanghaiA  --pre model_best.pth --model_type 'gap'

Reference

If you find this project is useful for your research, please cite:

@article{liang2022transcrowd,
  title={TransCrowd: weakly-supervised crowd counting with transformers},
  author={Liang, Dingkang and Chen, Xiwu and Xu, Wei and Zhou, Yu and Bai, Xiang},
  journal={Science China Information Sciences},
  volume={65},
  number={6},
  pages={1--14},
  year={2022},
  publisher={Springer}
}