daifeng2016
daifeng2016
Hi, I am wondering why you use trainloader_iter and trainloader_gt_iter at the same time during your training process, since they are both refer to the labeled dataset. During the D...
Hi, In your code, the unet model in 'unet_structure.py', 'unet_building.py', 'unet_road.py' seem to be the same? I have not found any difference in the model definition. What is the point...
Thank you for sharing the exciting work. I have three questions: 1) In traditional blind-SR setting, only LR images are provided such as kernelGAN/ZSSR, while in your work HR images...
Hi, Thanks for sharing the code, which is very clear. However, I am confused about the in_channels of the Generator in the "network.py". If the input is RGB images, should...
Thanks for sharing the code, I have tried but here are my problems. 1) How long do you spend to train the net from scatch? 2) During my test, I...
Hi, when reading the code, I found that "torch.mm(K.t(),a)" is used in perform_sinkhorn function. Does that mean only 2D correlation tensor can be processed per time. But in most cases,...
when I run Decoder_Spatial_MLP.ipynb, errors arise like "NotFoundError (see above for traceback): Unsuccessful TensorSliceReader constructor: Failed to find any matching files for model/model-MLP-1X1.ckpt-49999" . I am wondering how to solve...
Hi, I am wondering why 'filters.correlate' instead of 'convolution' is used in the function of 'numeric_kernel' in imresize.py. Is the kernel be filipped somewhere? In 'numeric_kernel', it is not.
Hi, after having scanned your code, I found you use trainloader_iter and trainloader_gt_iter in the train_s4GAN.py. Since both trainloader_iter and trainloader_gt_iter refer to the labeled dataset. I am wondering why...
Hi, this work is amzing. In MIC, image after masking is directly fed into student-teacher network. However, the masked areas will influence the convolution process and leads to much noise....