IGNN
IGNN copied to clipboard
sczhou
[NeurIPS 2020] Cross-Scale Internal Graph Neural Network for Image Super-Resolution
Hello, there is a newly computer in my office， which is equipped with a nvidia GPU 3090. Therefore, Cuda 11 and Pytorch 1.7.1 are supported in this computer. We try...
Your paper is very good and enlightening to me. When I apply your GraphAgg to my code, it will appear out of memory. Why is this? How should I deal...
Hello, if my pytorch>1.1.0, how should I use ‘matmul_cuda’? Will there be any performance impact if I don’t use this package? Or is it just an impact on speed? Currently,...
When you are proving ‘Effectiveness of Graph Aggregation Module’, how did you get GraphAgg*. I processed it like this: directly compare the input low-resolution image and its down-sampling form in...
Hello, I used your graph construction, graph aggregation module and my own data for training. During the training process, I found that increasing the size of the input data will...
``` python runner.py \ --gpu 0\ --phase 'test'\ --weights './ckpt/IGNN_x4.pth'\ --scale 4\ --demopath [my_path]\ --testname 'Demo' ``` By running the command, I got: ``` ... Using GPUs NUMBER: 1 [INFO]...
Hello, thank you for your contribution. Can adaPN be applied to other network structures? Can adaPN be used in deblurring network without coding-decoding structure
my system is windows. C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\link.exe /nologo /INCREMENTAL:NO /LTCG /DLL /MANIFEST:EMBED,ID=2 /MANIFESTUAC:NO /LIBPATH:C:\Users\Aimee\Anaconda3\envs\ignn2\lib\site-packages\torch\lib /LIBPATH:E:\CUDA\DEVELOPMENTS\lib/x64 /LIBPATH:C:\Users\Aimee\Anaconda3\envs\ignn2\libs /LIBPATH:C:\Users\Aimee\Anaconda3\envs\ignn2\PCbuild\amd64 "/LIBPATH:C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\LIB\amd64" "/LIBPATH:E:\Windows Kits\10\lib\10.0.10240.0\ucrt\x64" "/LIBPATH:C:\Program Files...
Is the graph you constructed for a channel, and is the FL aggregation processed separately for each channel
