C^3 Framework: An Open-source PyTorch Code for Crowd Counting
This is an incremental contribution that provides a practical code framework for researchers and practitioners in the domain of crowd counting.
The paper introduces the C^3 Framework, an open-source PyTorch toolkit for crowd counting, which provides baseline networks achieving state-of-the-art results, flexible parameter strategies to improve performance, and a log system to enhance experiment reproducibility.
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 (C$^3$F). The contributions of C$^3$F 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.