[英]How reshape 3D tensor of shape (3, 1, 2) to (1, 2, 3)
I intended 我打算
(Pdb) aa = torch.tensor([[[1,2]], [[3,4]], [[5,6]]])
(Pdb) aa.shape
torch.Size([3, 1, 2])
(Pdb) aa
tensor([[[ 1, 2]],
[[ 3, 4]],
[[ 5, 6]]])
(Pdb) aa.view(1, 2, 3)
tensor([[[ 1, 2, 3],
[ 4, 5, 6]]])
But what I really want is 但是我真正想要的是
tensor([[[ 1, 3, 5],
[ 2, 4, 6]]])
How? 怎么样?
In my application, I am trying to transform my input data of shape (L, N, C_in) to (N, C_in, L) in order to use Conv1d , where 在我的应用程序中,我试图将形状为(L,N,C_in)的输入数据转换为(N,C_in,L)以便使用Conv1d ,其中
I am also wondering the input of Conv1d doesn't have the same input shape as GRU ? 我也想知道Conv1d的输入与GRU的输入形状不一样吗?
You can permute the axes to the desired shape. 您可以将轴置换为所需的形状。 (This is in some sense similar to
np.rollaxis
operation). (这在某种意义上类似于
np.rollaxis
操作)。
In [90]: aa
Out[90]:
tensor([[[ 1, 2]],
[[ 3, 4]],
[[ 5, 6]]])
In [91]: aa.shape
Out[91]: torch.Size([3, 1, 2])
# pass the desired ordering of the axes as argument
# assign the result back to some tensor since permute returns a "view"
In [97]: permuted = aa.permute(1, 2, 0)
In [98]: permuted.shape
Out[98]: torch.Size([1, 2, 3])
In [99]: permuted
Out[99]:
tensor([[[ 1, 3, 5],
[ 2, 4, 6]]])
This is one way to do it, still hope to see a solution with a single operation. 这是一种实现方法,仍然希望通过一次操作即可看到解决方案。
(Pdb) torch.transpose(aa, 0, 2).t()
tensor([[[ 1, 3, 5],
[ 2, 4, 6]]])
(Pdb) torch.transpose(aa, 0, 2).t().shape
torch.Size([1, 2, 3])
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.