tensorplay.functional.fliplr

tensorplay.functional.fliplr(input) → Tensor[source]

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.

Note

Requires the tensor to be at least 2-D.

Note

tensorplay.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, tensorplay.fliplr is expected to be slower than np.fliplr.

Parameters:

input (Tensor) – Must be at least 2-dimensional.

Example:

>>> x = tensorplay.arange(4).view(2, 2)
>>> x
tensor([[0, 1],
        [2, 3]])
>>> tensorplay.fliplr(x)
tensor([[1, 0],
        [3, 2]])