fliplr(input) → Tensor¶
Flip tensor in the left/right direction, returning a new tensor.
Flip the entries in each row in the left/right direction. Columns are preserved, but appear in a different order than before.
Requires the tensor to be at least 2-D.
torch.fliplr makes a copy of
input’s data. This is different from NumPy’s np.fliplr, which returns a view in constant time. Since copying a tensor’s data is more work than viewing that data, torch.fliplr is expected to be slower than np.fliplr.
input (Tensor) – Must be at least 2-dimensional.
>>> x = torch.arange(4).view(2, 2) >>> x tensor([[0, 1], [2, 3]]) >>> torch.fliplr(x) tensor([[1, 0], [3, 2]])