Repository files navigation

This is the PyTorch version repo forCSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes in CVPR 2018, which delivered a state-of-the-art, straightforward and end-to-end architecture for crowd counting tasks.

ShanghaiTech Dataset:Google Drive

We strongly recommend Anaconda as the environment.

Python: 2.7

PyTorch: 0.4.0

CUDA: 9.2

Please follow themake_dataset.ipynb to generate the ground truth. It shall take some time to generate the dynamic ground truth. Note you need to generate your own json file.

Trypython train.py train.json val.json 0 0 to start training process.

Follow theval.ipynb to try the validation. You can try to modify the notebook and see the output of each image.

ShanghaiA MAE: 66.4Google DriveShanghaiB MAE: 10.6Google Drive

If you find the CSRNet useful, please cite our paper. Thank you!

@inproceedings{li2018csrnet,  title={CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes},  author={Li, Yuhong and Zhang, Xiaofan and Chen, Deming},  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},  pages={1091--1100},  year={2018}}

Please cite the Shanghai datasets and other works if you use them.

@inproceedings{zhang2016single,  title={Single-image crowd counting via multi-column convolutional neural network},  author={Zhang, Yingying and Zhou, Desen and Chen, Siqin and Gao, Shenghua and Ma, Yi},  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},  pages={589--597},  year={2016}}