Dense-Scale-Network-for-Crowd-Counting icon indicating copy to clipboard operation
Dense-Scale-Network-for-Crowd-Counting copied to clipboard

Published 20 hours ago • verified publisher icon rongliangzi

Network architecture issues

Open victorjourne opened this issue 3 years ago • 1 comments

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 ten first layers should be no trainable (not clear in the paper)
  2. There is no bias for the dilated convolution layer inside DDCB block. According to the paper, it is similar to DenseASPP layer implementation example
  3. At the end of DDCB block, there is no RELU layer according to the paper
  4. Inside DDCB block again, the last concat should include x1_raw, ie. x3 = torch.cat([x, x1_raw, x2_raw, x3_raw], 1) I think there is a typo in the figure 2 of the paper, the DDCB paragraph overlines a full connection of dilation layers.

I am training a network with these changes on ShangaiTech B dataset, let see if I retrieve paper results....

victorjourne avatar Oct 27 '21 22:10 victorjourne

retrieve paper results

Have you retrieved paper results?

luqijun avatar Jul 06 '23 07:07 luqijun