search

rongliangzi / Dense-Scale-Network-for-Crowd-Counting

An unofficial implement of paper "Dense Scale Network for Crowd Counting", link: https://arxiv.org/abs/1906.09707
31 stars 8 forks source link

Network architecture issues #5

Open victorjourne opened 3 years ago

victorjourne commented 3 years ago

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....

luqijun commented 1 year ago

retrieve paper results

Have you retrieved paper results?