search

Paper99 / SRFBN_CVPR19

Pytorch code for our paper "Feedback Network for Image Super-Resolution" (CVPR2019)
MIT License
551 stars 126 forks source link

question about srfbn-arch.py #56

Closed Senwang98 closed 4 years ago

Senwang98 commented 4 years ago

Hi, paper99 I'm reading your paper and code recently. However, I feel confused about some code in your srfbn-arch.py/SRFBN/forward:

        outs = []
        for _ in range(self.num_steps):
            h = self.block(x)

            h = torch.add(inter_res, self.conv_out(self.out(h)))
            h = self.add_mean(h)
            outs.append(h)

I have no idea if you have removed some codes here, because I think the output h is always the same(that's to say all elements in outs are all the same). Can you give me some suggestions? Wishing for your reply!

qixicccc commented 2 years ago

I also found this problem. Have you solved it？