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

TL;DR

This paper introduces the C^3 Framework, an open-source PyTorch toolkit for crowd counting that provides strong baseline models, flexible parameter strategies, and a logging system to improve reproducibility and performance.

Contribution

The paper presents a comprehensive crowd counting framework with state-of-the-art baselines, adaptable settings, and enhanced reproducibility features, which is publicly available for the community.

Findings

Achieved state-of-the-art results with baseline networks

Provided flexible parameter tuning strategies

Developed a logging system to improve experiment reproducibility

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 (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.