torch.transpose：转置经常在矩阵中使用，交换两个维度。
torch.transpose(tensor,dim_0,dim_1)
代码示例：

import torch
a=torch.tensor([[[1,2,3],[4,5,6]],
                [[7,8,9],[10,11,12]]])
b=torch.transpose(a,1,2)
print("tensor_a",a)
print("tensor_b",b)
print("a的shape:",a.shape)
print("b的shape:",b.shape)

输出：

tensor_a: tensor([[[ 1,  2,  3],
         [ 4,  5,  6]],

        [[ 7,  8,  9],
         [10, 11, 12]]])
tensor_b: tensor([[[ 1,  4],
         [ 2,  5],
         [ 3,  6]],

        [[ 7, 10],
         [ 8, 11],
         [ 9, 12]]])
a的shape: torch.Size([2, 2, 3])
b的shape: torch.Size([2, 3, 2])

注：transpose只能交换两个维度，想想矩阵，再想想维度0是什么。