Rate this Page
★★★★★

torch.flip#

torch.flip(input,dims)→Tensor#

Reverse the order of an n-D tensor along given axis in dims.

Note

torch.flip makes a copy ofinput’s data. This is different from NumPy’snp.flip,which returns a view in constant time. Since copying a tensor’s data is more work than viewing that data,torch.flip is expected to be slower thannp.flip.

Parameters

  • input (Tensor) – the input tensor.

  • dims (a list ortuple) – axis to flip on

Example:

>>>x=torch.arange(8).view(2,2,2)>>>xtensor([[[ 0,  1],         [ 2,  3]],        [[ 4,  5],         [ 6,  7]]])>>>torch.flip(x,[0,1])tensor([[[ 6,  7],         [ 4,  5]],        [[ 2,  3],         [ 0,  1]]])