Dense-Scale-Network-for-Crowd-Counting

Dense-Scale-Network-for-Crowd-Counting copied to clipboard

Network architecture issues

1

Many thanks for your great work to attempt to reproduce the DSNet paper! After reading your code, in particular the `dsnet.py` file, I notice 4 potential issues : 1. Vgg-18...

victorjourne

victorjourne

cv2 interpolation to resize the target

1

It would be more accurate to use the **INTER_AREA** interpolation than the INTER_CUBIC one for the resize of the target. Indeed, this downsampling is more natural here because it computes...

victorjourne

Multi-scale density level consistency loss

1

Thanks again for your work! Regarding the Multi-scale density level consistency loss, I think the L1 loss has to be reduced by **sum** instead of **mean** (default pytorch paramater). Indeed,...

victorjourne

网络输出一张热力图，最后是dmp.sum()得到一个count，但是这个count是一个小数，怎么获得这张热力图的实际人数呢？

HandsLing

您好，对于您的程序有几个问题： 1、程序中使用的是python2 还是python3？ 2、Shanghaitech的数据集中groundtruth为.mat格式，程序中使用h5py读取，这样读出来之后为什么为空呢？ 3、读取groundtruth之后，索引['density']键时，会提示该键不存在，可能是什么原因呢？

ydlu