torch view view_as

 

import torch

a = torch.rand(3, 3, 4, 5)
b = a.view(3, -1)
c = b.view(3, 3, 4, 5)

d = torch.rand(3, 12, 1, 5)
print(torch.equal(c, a))

e=a.view_as(d)
print(e)

view_as reshape到跟d一样

 

view只能改变一段连续的内存，

如果数据先筛选，再view，就会报错：

 view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces)

解决方法：

a_correct = a_trans.contiguous().view(3,-1) 

 

如果只转成1列，下面也可以：

torch.flatten(indexs)