KBNet
KBNet copied to clipboard
zhangyi-3
KBNet: Kernel Basis Network for Image Restoration
Hi, would be a big help to get more information on how to train KBNet for educational purposes!
hello! I want to know how to train model Wolud you please help me? thanks
Hi there! Is there any examples of running on Mac using cpu/mps as a device?
When I run `test_gaussian_color_denoising.py`, I've already downloaded the `Denoising/pretrained_models/gaussian_color_denoising_sigma15.pth` from https://drive.google.com/drive/folders/1Qwsjyny54RZWa7zC4Apg7exixLBo4uF0, but it shows the pre-trained weights don't match the network:  Looking forward to your answer. Thanks~
I tried to compute the GMAC's for the KBNet_s, using thop and ptflops the MACs is: 69.09 GMACs. But in the paper the presented MACs are 57.8 GMACs for SIDD...
Hi, Thanks for the great work! I am new to the BasicSR related code base, so I was wondering if this repo supports training the model from scratch. I looked...
I hope this message finds you well. I recently came across your project KBNet and I'm quite interested in using it for raw image denoising task. However, I couldn't find...
Is it not allowed to test directly with my own data? Why can't I read the image (test) zkyd@zkyd:~/cxl/code/xlsk/KBNet/Denoising$ python -u test_gaussian_color_denoising.py --yml Options/gau_color_50.yml ** Options/gau_color_50.yml pretrained_models/gau_color_50.pth ===>Testing using weights:...
