odhiamboobuya/csrnet-pytorch

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

CSRNet-pytorch

This is the PyTorch version repo for CSRNet: 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.

Datasets

CC visdrone Dataset: web_site

Prerequisites

We strongly recommend Anaconda or Google Colab as the environment.

Python: 3.6

CUDA: 10.1

Training and validation Process

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

References

If you find the CSRNet useful, please cite the CSRNet 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}
}