tensorplay.functional.flipud

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

Flip tensor in the up/down direction, returning a new tensor.

Flip the entries in each column in the up/down direction. Rows are preserved, but appear in a different order than before.

Note

Requires the tensor to be at least 1-D.

Note

tensorplay.flipud makes a copy of input’s data. This is different from NumPy’s np.flipud, which returns a view in constant time. Since copying a tensor’s data is more work than viewing that data, tensorplay.flipud is expected to be slower than np.flipud.

Parameters:

input (Tensor) – Must be at least 1-dimensional.

Example:

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