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...
Hi, not sure if this is a bug, maybe just a general question. When using extract_images.py, it was possible to run it on multiple threads and save a lot of...
你好,目前我的数据集的分辨率都太小,不论高质量和低质量的图片的长和宽都小于480,如100*90,不够extract的尺寸该怎么办呢?
作者您好,我在安装BasicSR的时候,出现找不到包的情况,就是出现持续找包的过程,从高到低的依次下载,最后还找失败了,这个是什么原有呢,谢谢
hi
How to use esrgan for 2 GPU training? What are the commands?The training time of the two GPUs I gave was longer Thank you
Hi, thanks for your amazing work. I want to train my own model using the ESRGAN framework. Follow the steps in the paper,first train PSNR-oriented model. The experiment is performed...
Hello, I'am trying to test my trained model and evaluate it on the niqe metric. In put this in my yaml file: ``` val: save_img: true suffix: ~ # add...
Trying to train ESRGAN with custom lr/hr size, get the following error: ``` 2020-11-12 19:13:17,807 INFO: Model [ESRGANModel] is created. 2020-11-12 19:13:18,060 INFO: Start training from epoch: 0, iter: 0...
Hello, I know it says TODO, but here you reference this discriminator, yet I cannot find it in the files. Could you please provide it? https://github.com/xinntao/BasicSR/blob/0e77ebb9987ab99547394c2b13f32b8547868332/options/train/EDVR/train_EDVRM_woTSA_GAN_TODO.yml#L66 Also, I am curious,...
I'm running this cell in [colab](https://colab.research.google.com/drive/1RoNDeipp9yPjI3EbpEbUhn66k5Uzg4n8?usp=sharing#scrollTo=iOOKuMG_VHg3) `!python inference/inference_dfdnet.py --upscale_factor 1 --test_path datasets/childhood/ --official_adaption True` and got error like this > Cannot import fused_act and upfirdn2d. Ignore this warning if they...
Hi, @xinntao Disturb you again, have you tested the speed of **.pt** file(which is used in github repo EDSR-Pytorch) vs **.lmdb**(which is used in your repo). Is **.lmdb** file train...