torch.flip

torch.flip(input, dims) → Tensor

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

Note

torch.flip makes a copy of input’s data. This is different from NumPy’s np.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 than np.flip.

Parameters

• input (Tensor) – the input tensor.
• dims (a list or tuple) – axis to flip on

Example:

>>> x = torch.arange(8).view(2, 2, 2)
>>> x
tensor([[[ 0,  1],
         [ 2,  3]],

        [[ 4,  5],
         [ 6,  7]]])
>>> torch.flip(x, [0, 1])
tensor([[[ 6,  7],
         [ 4,  5]],

        [[ 2,  3],
         [ 0,  1]]])