DRIT_hr
DRIT_hr copied to clipboard
Multi-Modal Image-to-Image Translation on Tasks with High-Resolution Images
Thanks for your great work. I want to reproduce the experiment of high resolution (GTA to Cityscapes). How many images are in the two datasets, and are they from training...
some mistakes It may be : git clone https://github.com/hytseng0509/DRIT_hr.git cd DRIT_hr
Hello! I found a following thing in LeakyReLUConv2d: ``` class LeakyReLUConv2d(nn.Module): def __init__(self, ..., norm='None', ...): .... if 'norm' == 'Instance': model += [nn.InstanceNorm2d(n_out, affine=False)] ... ``` _https://github.com/hytseng0509/DRIT_hr/blob/master/networks.py#L496_ It seems...
self.decB5 = nn.Sequential(*decB6) => self.decB6 = nn.Sequential(*decB6)
Hello, what is the difference to the original code ? Why is this repository well suited for high resolution images? Which resolution of GTA and Cityscapes can you recommend for...