https://github.com/kaifcoder/dense-crowd-detection
https://github.com/kaifcoder/dense-crowd-detection
Last synced: 9 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/kaifcoder/dense-crowd-detection
- Owner: kaifcoder
- Created: 2022-08-26T18:15:54.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-08-26T19:03:22.000Z (over 3 years ago)
- Last Synced: 2025-05-31T05:18:56.398Z (10 months ago)
- Language: Jupyter Notebook
- Size: 177 KB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# CSRNet-pytorch
This is the PyTorch version repo for [CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes](https://arxiv.org/abs/1802.10062) in CVPR 2018, which delivered a state-of-the-art, straightforward and end-to-end architecture for crowd counting tasks.
## Datasets
ShanghaiTech Dataset: [Kaggle link](https://www.kaggle.com/datasets/tthien/shanghaitech)
## Prerequisites
We strongly recommend Anaconda as the environment.
Python: 2.7
PyTorch: 0.4.0
CUDA: 9.2
## Ground Truth
Please follow the `make_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.
## Training Process
Try `python train.py train.json val.json 0 0` to start training process.
## Validation
Follow the `val.ipynb` to try the validation. You can try to modify the notebook and see the output of each image.
## Results
ShanghaiA MAE: 66.4 [Google Drive](https://drive.google.com/open?id=1Z-atzS5Y2pOd-nEWqZRVBDMYJDreGWHH)
ShanghaiB MAE: 10.6 [Google Drive](https://drive.google.com/open?id=1zKn6YlLW3Z9ocgPbP99oz7r2nC7_TBXK)
## References
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}
}
```