Open GuideWsp opened 3 years ago
The only difference is that we did not use big residual connections in RFDB, which we found is slightly better in the challenge
Yes, I had try it as the paper, finally I got a 30.47dB on DIV2K-val(YCbCr), the psnr of your model is 30.49dB, they are very similar. I just train it by L1, not finetune by L2. Whatever, it is a very good job.
Yes, I had try it as the paper, finally I got a 30.47dB on DIV2K-val(YCbCr), the psnr of your model is 30.49dB, they are very similar. I just train it by L1, not finetune by L2. Whatever, it is a very good job.
I also used the provided RFDN_AIM.pth file for testing, and the test result on DIV2K_val (only Y channel) was 30.517db. Maybe it is caused by the different calculation methods of psnr.
唯一的区别是,我们在RFDB中没有使用大的残差连接,我们发现这在挑战中略好一些。
why is 'self.remaining_channels = in_channels' in class RFDB?
@scutlrr 大佬,这个RFDN怎么基于EDSR框架训练的,需要把这个仓库的文件拷贝到EDSR仓库吗?其次RFDN的环境配置是什么样的?
@aiyunhug 大佬,这个RFDN怎么基于EDSR框架训练的,需要把这个仓库的文件拷贝到EDSR仓库吗?其次RFDN的环境配置是什么样的?
Finally, I found the code of the RFDB is not the same as the paper.