SCUNet
SCUNet copied to clipboard
cszn
Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis (Machine Intelligence Research 2023)
SCUNet does a GREAT job. But sometimes some details are lost. Is there any chance of a v2 in the future that might preserve or restore the details while still...
Dear author: In your paper, The learning rate decays by a factor of 0.5 every 200,000 iterations. I want to confirm if it's 200,000 iterations, because in my opinion, 200,000...
its checked in Extensions tab but i cant see it in a list.Why?
https://github.com/NVIDIA-AI-IOT/torch2trt/issues/807 TensorRT not support move batch dim. https://forums.developer.nvidia.com/t/tensorrt-does-not-support-permute-in-n-batch-dimension/69925
Thanks for the code sharing. Any idea on how to train the model on our data?
In predict, determine whether the size is 8： [ if not x8 and img_L.size(2)//8==0 and img_L.size(3)//8==0](https://github.com/cszn/SCUNet/blob/52e440a80a655b01e0b41e9dd9bfe599bc11625e/main_test_scunet_color_gaussian.py#L115). What does this mean？Should it be %8==0?
