English

C^3 Framework: An Open-source PyTorch Code for Crowd Counting

Computer Vision and Pattern Recognition 2019-07-08 v1

Abstract

This technical report attempts to provide efficient and solid kits addressed on the field of crowd counting, which is denoted as Crowd Counting Code Framework (C3^3F). The contributions of C3^3F are in three folds: 1) Some solid baseline networks are presented, which have achieved the state-of-the-arts. 2) Some flexible parameter setting strategies are provided to further promote the performance. 3) A powerful log system is developed to record the experiment process, which can enhance the reproducibility of each experiment. Our code is made publicly available at \url{https://github.com/gjy3035/C-3-Framework}. Furthermore, we also post a Chinese blog\footnote{\url{https://zhuanlan.zhihu.com/p/65650998}} to describe the details and insights of crowd counting.

Cite

@article{arxiv.1907.02724,
  title  = {C^3 Framework: An Open-source PyTorch Code for Crowd Counting},
  author = {Junyu Gao and Wei Lin and Bin Zhao and Dong Wang and Chenyu Gao and Jun Wen},
  journal= {arXiv preprint arXiv:1907.02724},
  year   = {2019}
}

Comments

Technical report

R2 v1 2026-06-23T10:12:57.896Z