{"id":27177296,"url":"https://github.com/kaifcoder/dense-crowd-detection","last_synced_at":"2025-06-25T08:07:28.268Z","repository":{"id":140796956,"uuid":"529362601","full_name":"kaifcoder/dense-crowd-detection","owner":"kaifcoder","description":null,"archived":false,"fork":false,"pushed_at":"2022-08-26T19:03:22.000Z","size":181,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-05-31T05:18:56.398Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kaifcoder.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-08-26T18:15:54.000Z","updated_at":"2023-09-19T07:36:36.000Z","dependencies_parsed_at":null,"dependency_job_id":"2f1efdb3-5ad9-4ccf-8edd-26d44d16b3b0","html_url":"https://github.com/kaifcoder/dense-crowd-detection","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/kaifcoder/dense-crowd-detection","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaifcoder%2Fdense-crowd-detection","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaifcoder%2Fdense-crowd-detection/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaifcoder%2Fdense-crowd-detection/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaifcoder%2Fdense-crowd-detection/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kaifcoder","download_url":"https://codeload.github.com/kaifcoder/dense-crowd-detection/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kaifcoder%2Fdense-crowd-detection/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261832678,"owners_count":23216497,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-04-09T13:43:22.142Z","updated_at":"2025-06-25T08:07:28.258Z","avatar_url":"https://github.com/kaifcoder.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CSRNet-pytorch\n\nThis 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.\n\n## Datasets\nShanghaiTech Dataset: [Kaggle link](https://www.kaggle.com/datasets/tthien/shanghaitech)\n\n## Prerequisites\nWe strongly recommend Anaconda as the environment.\n\nPython: 2.7\n\nPyTorch: 0.4.0\n\nCUDA: 9.2\n## Ground Truth\n\nPlease 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.\n\n## Training Process\n\nTry `python train.py train.json val.json 0 0` to start training process.\n\n## Validation\n\nFollow the `val.ipynb` to try the validation. You can try to modify the notebook and see the output of each image.\n## Results\n\nShanghaiA MAE: 66.4 [Google Drive](https://drive.google.com/open?id=1Z-atzS5Y2pOd-nEWqZRVBDMYJDreGWHH)\nShanghaiB MAE: 10.6 [Google Drive](https://drive.google.com/open?id=1zKn6YlLW3Z9ocgPbP99oz7r2nC7_TBXK)\n\n## References\n\nIf you find the CSRNet useful, please cite our paper. Thank you!\n\n```\n@inproceedings{li2018csrnet,\n  title={CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes},\n  author={Li, Yuhong and Zhang, Xiaofan and Chen, Deming},\n  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},\n  pages={1091--1100},\n  year={2018}\n}\n```\nPlease cite the Shanghai datasets and other works if you use them.\n\n```\n@inproceedings{zhang2016single,\n  title={Single-image crowd counting via multi-column convolutional neural network},\n  author={Zhang, Yingying and Zhou, Desen and Chen, Siqin and Gao, Shenghua and Ma, Yi},\n  booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},\n  pages={589--597},\n  year={2016}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkaifcoder%2Fdense-crowd-detection","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkaifcoder%2Fdense-crowd-detection","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkaifcoder%2Fdense-crowd-detection/lists"}