DBPN-Pytorch
DBPN-Pytorch copied to clipboard
alterzero
The project is an official implement of our CVPR2018 paper "Deep Back-Projection Networks for Super-Resolution" (Winner of NTIRE2018 and PIRM2018)
The discriminator pretrained model is not in the drive folder, if you have it... I'll be so glad if you could send it to me or upload it into the...
I wanted to know if we are only training on one random patch of a whole image, rather than training on all the patches of the image. I could be...
I saw that your also involve in the 'NTIRE 2019 Challenge on Real Image Denoising: Methods and Results' and reach good results. In your code ,it's more about archs for...
Dear Sir, I find some contradictions in your code about main.py file that confused me. Thus, I wanna to verify this question. In L125, you declare critertion=nn.L1Loss(),  But according...
def train(epoch): epoch_loss = 0 model.train() for iteration, batch in enumerate(training_data_loader, 1): input, target, bicubic = Variable(batch[0]), Variable(batch[1]), Variable(batch[2]), What does 'input, target, bicubic = Variable(batch[0]), Variable(batch[1]), Variable(batch[2])' mean? I...
Can i train this model on other datasets，like ImageNet，voc etc。For the images in these datasets，Do I need to resize the images(for x8、x4)。
Using Prelu Activation, Did you initialize all models with zero 'a'?
I tested Set5, Set14, BSD100 and urban100 datasets use pretrained models DBPN_x8.pth or DBPN-RES-MR64-3_8x.pth, but the results I got have a big gap with your results showed in the paper....
It shows RuntimeError:Error(s) in loading state_dict for Net: Missing key(s) in state_dict:"feat0.conv.bias","feat0.conv.weight","feat0.conv.act.weight"........... Unexcepted key(s) in state_dict:"moudle.feat0.conv.weight","moudle.feat0.conv.bias"........ Can you give me some advices?Thank you very much.
@alterzero hi, is it appropriate that the last convolutional layer of DBPN has no activation function? [https://github.com/xinntao/ESRGAN/blob/master/RRDBNet_arch.py] The last layer of activation function is LeakyReLU.
