For example,
A Tensor with shape [2, 3, 4] -> [4, 2, 3]
In numpy, we could directly use np.transpose(Tensor, [2, 0, 1]). However, in pytorch, I could not find a elegant way to do it.
Thanks for your help.
For example,
A Tensor with shape [2, 3, 4] -> [4, 2, 3]
In numpy, we could directly use np.transpose(Tensor, [2, 0, 1]). However, in pytorch, I could not find a elegant way to do it.
Thanks for your help.
torch.Tensor.permute…
Thanks.
I miss it in the document.