zkawfanx / rlp Goto Github PK

你好，我试着训练你的代码，发现按照readme来loss一直是四十多降不下来，是我训练方法有问题吗？

I am getting cuda out of memory error, while testing UNet_RLP_RPIM model you have given, when ruuning in collab. Can you suggest some methods to overcome it ? Also, what file directory we have to give to test the images(gt or rainy)?

Excellent work！

Would it be appropriate to consider comparing it with two-stage methods that incorporate low-light enhancement algorithms for nighttime scenes along with deraining?

However, after checking carefully, we find that there exist a few scenes with misalignments due to operation mistakes during collection. We filter out these scenes and there's about 0.5dB improvement in PSNR, which applys to all evaluated methods.
请问下载链接的数据集包含这些错误场景吗？还有就是0.5db提升是指论文中表1的所有方法吗？

老哥，你这deraining module里的UNet和Uformer都是源论文一样的代码么，如果把你提出的两个块不加单独训的话是不是可以得到UNet和Uformer的数据，你对比方法贴的UNet和Uformer的数据是不是这样训的呀？我搞了个1k的数据集训你的方法，70秒出一轮，训Uformer40秒，UNet14秒...是不是哪里有问题，还是说就是这么快？

I use 4090 gpu to run the test. The training models of py Uformer_T_RLP_RPIM. PTH, but an error torch. Cuda. OutOfMemoryError: cuda out of memory. But I see that 3090 is used in your paper, why does this happen? I run a smaller picture is normal, but your original GTAV 500 test set will report an error, there are any parameters need to be modified? Looking forward to your recovery

老哥，我又来了，我想问下你的对比方法都是重新训的吗？是在你提供的kaggle上面的数据集上么？方便分享一下权重文件吗老哥，谢谢

Congratulations for your awesome work accepted by ICCV 2023. I am very interested in your nighttime rain removal work, so when will you release your re-rendering GTA-nighttime dataset as well as the source codes ?

您好！最近在复现代码的过程中，使用MPRNet训练您文章中提出的数据集，发现PSNR跟您提到的有些差距。如果可以的话可以分享一下对比实验其他模型的权重文件吗？谢谢！