search

DeokyunKim / Progressive-Face-Super-Resolution

Official Pytorch Implementation of Progressive Face Super-Resolution (BMVC 2019 Accepted)
261 stars 60 forks source link

Question about ResBlock in Generator Network #9

Closed JauB1981 closed 5 years ago

JauB1981 commented 5 years ago

Hi @DeokyunKim Please can you tell why there is a deffirence between the paper and Model.py in ResBlock for Step =2 ?

ProgrSR

In the paper, the architecture shows for step = 2 a ResBlock with 512 channel (second level), but in your Model.py we see that level 1 and 2 in ResBlock have the same channels numbers as output (wich must = 256 i think ==> dim Variable):


self.conv = nn.Sequential(
                            EqualConv2d(dim, dim, kernel_size=3, padding=1, stride=1),
                            nn.BatchNorm2d(dim),
                            nn.ReLU(),
                            EqualConv2d(dim, dim, kernel_size=3, padding=1, stride=1),
                            nn.BatchNorm2d(dim),
                            nn.ReLU()
                            )
DeokyunKim commented 5 years ago

Thank you for your feedback.

There is miss typing in the paper.

The step 2 ResBlock's dimension is 256 and step 3 ResBlock's dimension is 128 as the uploaded code.

JauB1981 commented 5 years ago

Many thanks for your quick answer :)