zsyoaoa / s2vd Goto Github PK

the 25th should be：base_data_path = Path('./testsets/synthetic_NTURain')
Your work is excellent!

您好，可以简单地解释一下这个网络么，例如紫色的那个减号的作用是减去雨层么，我可以认为第二个pixel-shuffle模块输出的是rain_streak么？

您好，看到您补充材料里关于rain streak的叙述，但是自己相减得到的rain streak结果并不是很理想，可能在代码里漏掉了一些细节，请问关于这一部分的代码可以提供一下吗？非常感谢，祝工作顺利，阖家幸福。

我从头开始训练了47轮，结果和论文中的表1相比，PSNR低了将近2个点，请问是什么原因造成的呢？谢谢。

Hello, your work is excellent, and I was reading your paper when I had a question: In Fig.3, which stage of the network do the Transition Model and Emission Model belong to? What I don't understand is what role these two modules play in the whole network. Do they play a role in the process of Fig.2? Looking forward to your reply.

你好，请问一下算法里E步骤中，s0,m0,z的初始值是怎么获取的？Langevin dynamics是什么原理？

您好:
想請問論文中Eq(12)這條式子是怎麼來的
非常感謝。

Hello! Thanks for your excellent work.
I wonder about the network architecture of the derainer f(-;w) in Figure 2. of your paper:
Why does it need to minus original image after the Pixel-Shuffle layer ?
Thank you.

您好，我想请问一下训练这个去雨算法需要几块多大显存的GPUs以及大概的训练时间。谢谢分享。

FileNotFoundError: [Errno 2] No such file or directory: ///**/latent_eps6_rho05_tv112
I can't find latent_eps6_rho05_tv112, and don't know how to generate it.

By using VPN , I try a lot of times to download the NTURain dataset in China ,but failure. Do you have another way to download this dataset ?
Expect your reply!

Thank you very much for your codes. Could your codes run on Windows system? Please.

you claim "Such a gap between synthetic and real data sets results in poor performance when applying them to real scenarios. To address these issues, this paper proposes a new semi-supervised video deraining method " in your paper, but i can't found it is suitable for real scenarios from the results attaching on your paper. Why is this happening? thank you.

您好，我想问一下trainers_singlegpu.py文件中训练需要mat文件但是数据集中没有，应该怎么获取呢

Hi, your work is fantastic, if I want to implement the baseline1 experiment in your ablation studies, i.e. ""train the derainer with the MSE loss on labeled dataset ", how can I do it exactly? Thanks.

您好，我在test的时候发现保存的文件为.mat，如何获取derain后的jpg图片呢