Skip to content
This repository has been archived by the owner on Sep 27, 2020. It is now read-only.

关于input 和 step 的问题 #7

Closed
Fzz123 opened this issue Aug 27, 2018 · 2 comments
Closed

关于input 和 step 的问题 #7

Fzz123 opened this issue Aug 27, 2018 · 2 comments

Comments

@Fzz123
Copy link

Fzz123 commented Aug 27, 2018

代码的输入数据定义为: input = Variable(torch.randn(1, 512, 64, 32)).cuda() 参数分别为(batch_size, channels, height, weight)
在输入convlstm网络进行计算时有下面这个for循环:
for step in range(self.step): x= input for i in range(self.num_layers): ...

请问这个循环每次的输入x都是相同的吗?序列体现在哪里呢?有理解不对的地方希望能得到您的指正,谢谢!

@EnQing626
Copy link

你只需要在不同step输入不同的x即可~

@Chao86
Copy link

Chao86 commented Oct 9, 2019

你只需要在不同step输入不同的x即可~
如果用这个代码,同一num_layer的的不同step之间好像没有信息的传递啊

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

No branches or pull requests

4 participants