Dense-Scale-Network-for-Crowd-Counting
An unofficial implement of paper "Dense Scale Network for Crowd Counting", link: https://arxiv.org/abs/1906.09707
When training sha dataset, the model shows faster convergence if learning rate is set as 1e-4 compared to 1e-5 which is claimed by the paper.
Dataset | MAE | MSE |
---|---|---|
sha | 89.76 | 142.23 |
shb | to be done | tbd |
qrnf | tbd | tbd |
Anyone interested in implementing crowd counting models is welcomed to contact me.