zijundeng/pytorch-semantic-segmentation

DUC_HDC perfoemance

InstantWindy opened this issue · 1 comments

Hello! Do you use the 'DUC_HDC‘’ model train the Voc2012 dataset? I use it ,but I found the result was not good, it appears the griding situation,But it should not be the case, because the model is the solution to the grid phenomenon.I don't why ,could you help me? Thanks!

try changing the dilation rate parameter to Dilation-RF or Dilation-bigger (check the paper for more detail on the dilation rate setting) and again if still the issue exists try using resnet101 or greater if you are using lower resnet.