Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

关于Table4 #17

Open
jjb202 opened this issue Oct 12, 2020 · 8 comments
Open

关于Table4 #17

jjb202 opened this issue Oct 12, 2020 · 8 comments

Comments

@jjb202
Copy link

jjb202 commented Oct 12, 2020

PreNet.最后Rain100l和100H的数据集都达到了37.48和29.46,似乎不像你在文中描述的这么低

@kuijiang94
Copy link
Owner

您好,感谢您对我们工作的关注!
因为我们论文和PreNet原文的训练集不一样,而且所用的样本数量都存在差异,自然和PreNet原文的测试结果不一样。
我们论文里的结果是用统一的训练集训练得到的,因此是公平的。

@jjb202
Copy link
Author

jjb202 commented Oct 12, 2020

感谢您的回复,请问可否帮忙跑一下,prenet的rain100l和H的训练集么?

@kuijiang94
Copy link
Owner

实在不好意思,这段时间太忙了,而且我们这边卡的资源分配比较紧张,如果您那边有条件,可以直接用作者公布的代码在rain100l和H训练集上训练

@jjb202
Copy link
Author

jjb202 commented Oct 15, 2020 via email

@kuijiang94
Copy link
Owner

不客气了,有啥问题欢迎交流讨论

@jjb202
Copy link
Author

jjb202 commented Oct 18, 2020

我想问下,自己的训练数据集是放在preprocess.py生成的/raw/train_rain里面是么?那个cleansample和rainsample里面的是用来干嘛的

@kuijiang94
Copy link
Owner

放在cleansample和rainsample,raw/train_rain里面是你用来训练的样本,比如你的train和val的比例是1:9,那么raw/train_rain里面就有占比0.9的训练样本,0.1的样本用来评估

@jjb202
Copy link
Author

jjb202 commented Oct 18, 2020

6
你好 这是python版本不一致问题么?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants