torch.transpose(input, dim0, dim1) 
#input (Tensor) – the input tensor.
#dim0 (int) – the first dimension to be transposed
#dim1 (int) – the second dimension to be transposed
ex:-
>>> x = torch.randn(2, 3)
>>> x
        #dimention 1
tensor([[ 1.0028, -0.9893,  0.5809], # dimension 2
        [-0.1669,  0.7299,  0.4942]])
>>> torch.transpose(x, 0, 1)
tensor([[ 1.0028, -0.1669],
        [-0.9893,  0.7299],
        [ 0.5809,  0.4942]])