C2-Matching

C2-Matching copied to clipboard

关于使用gan损失生成图像的问题

1

我使用您发布的预训练模型来生成测试图片，我发现在一些相关度不足的纹理区域，使用gan损失好像并没有重建出好的很好的视觉效果。如下图所示，我对比了MASA-SR和C2-matching。  

Yi-Yang355

Does it support distributed training？

2

I would like to ask the author if the c2_matching code supports distributed training, and if so, can you share the command，such as，thank you！

ModestTony

No need to resize input image

3

I tried issue #10 because I don't need to resize the input image, but it doesn't work. And i tried commented out the PIL.resize part ex) l.129 in `ref_cufed_dataset.py` before:...

MasKogNavier

dataset configuration for no-reference dataset

1

Thanks for you great work, I was just wondering how the dataset configuration should be for datasets without any references, (like urban100). Currently, I'm simply forwarding a directory with downscaled...

himkmk

Pretrained Models

1

Hi, thank you for your great work. Would you release the pretrained model of the teacher contrastive network? I am looking forward to it.

cszhilu1998

Inference On Custom Images ? Colab Demo?

2

Hello, thank you for your great work it will be great if you provide a colab notebook demo of this amazing repo, if you can show how to inference on...

Adeel-Intizar

请教一下，这里的dcn和torchvision里面的DeformConv2d有什么区别？

NickYangMin

hi i got a problem on Installing MMSR and DCNv2 my virtual env setting is same ass read me setting Python 3.7.16 (c2_matching) C:\Users\user\C2-Matching\mmsr\models\archs\DCNv2>pip list Package Version ------------------ --------- addict...

dkkmin0

能否提供一下训练日志？谢谢

NickYangMin

Hello, now MMEditing has been renamed MMagic. [The code framework is mainly modified from [BasicSR](https://github.com/xinntao/BasicSR) and [MMSR](https://github.com/open-mmlab/mmediting) (Now reorganized as MMEditing).] could update.

ZhaoQiiii