CSRNet-pytorch icon indicating copy to clipboard operation
CSRNet-pytorch copied to clipboard

Geometry-adaptive kernel

Open tempdata73 opened this issue 5 years ago • 1 comments

I couln't help but notice that the sigma defined in the code is different from the one mentioned in the paper. The latter is defined as the mean of the distances times beta=0.3, whilst the former is just the sum of the distances times beta=0.1. Does this make a real difference in performance/evaluation? issue

If I generate the density map by following the paper, I get this image, which is clearly different from the other ones... density

tempdata73 avatar Nov 03 '19 19:11 tempdata73

I guess it is right, because (d1+d2+d3)/3 *0.3 = (d1+d2+d3) * 0.1

jimeffry avatar Nov 28 '19 11:11 jimeffry