BasicSR
BasicSR copied to clipboard
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also sup...
How can I train ESRGAN, detailed steps, thank you so much
你好, 为什么需要将DIV2K的数据集切分成480x480的小图? 我了解到在其他SR工程里都没有这么做,而是直接在2K的大图上采样192x192的训练图片若干次,请问如果我切分成480x480的小图对结果有什么影响? yours xiaoxiongli
I keep getting this error when i try to train the model --------------------------------------------------------------------------- KeyError Traceback (most recent call last) /content/realesrgan/train.py in () 10 root_path = osp.abspath(osp.join(__file__, osp.pardir, osp.pardir)) 11 print(root_path)...
Hi. I am trying to compute with your package the PSNR of your provided RRDB checkpoint. On set14 for instance, the result I get is 27.1531, whereas in the ESRGAN...
请问如何在PairedImageDataset基础上再新加一个数据读取 比如原来的是dataroot_gt和dataroot_lq 比如我想新增加一个dataroot_nq,我该怎么做,谢谢涛哥
Hi @xinntao, I'm trying to train ESRGAN with my own images. The GT images have a size of 256x256x3 and the LQ images have 128x128x3. I already crop both of...
Hi, I would like to ask, how to train SFTGAN model from scratch using my own data? I saw yaml for training other models, but not for SFTGAN model. Could...
I have add the lpips metrice by referring the https://github.com/xinntao/BasicSR/pull/367
I integrated IconVSR (weights and inference modules) into [our project](https://github.com/lotress/MoePhoto). Thank you for your work. 对您表示衷心感谢。 I have two questions here. ## Question 1: Real videos suffered from much compression...