-
Notifications
You must be signed in to change notification settings - Fork 52
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
class PReNet(nn.Module): class PReNet_r(nn.Module): class PRN(nn.Module): class PRN_r(nn.Module): #3
Comments
这是用了residual learning,网络学的是negative rain streak layer。直接输出x 不加input也可以,数据集指标稍降一点,视觉上没区别。 |
谢谢 再麻烦问下 negative rain streak layer 是哪篇文章呢? |
目前几乎所有的去雨网络都用了residual learning,DDN是第一个用在去雨的。DnCNN第一个把这个策略用到去噪 https://github.com/cszn/DnCNN |
以前只注意到中间的残差会加上之前的输入 但是好像第一次见到在最后输出的时候还要加上最开始的输入 |
您好,有个小疑问: |
请看networks.py中的 class PReNet_LSTM |
是的 |
作者你好,在network.py中上述四个网络结构,为什么输出的时候倒数第三行的结果要加上input呢?x = x + input,这个应该是已经derain后的结果,在加上输入的图,是不是多余了?
The text was updated successfully, but these errors were encountered: