# chainer.functions.tile¶

chainer.functions.tile(x, reps)[source]

Construct an array by tiling a given array.

Parameters: x (Variable or numpy.ndarray or cupy.ndarray) – Input variable. Let the length of reps be d. If x.ndim < d, x is treated as d-dimensional array by prepending new axes. For example, when the shape of x is (2,) and tiled with 2-dim repetitions, x is treated as the shape (1, 2). If x.ndim > d, reps is treated as x.ndim-dimensional by pre-pending 1’s. For example, when the shape of x is (2, 3, 2, 3), the 2-dim reps of (2, 2) is treated as (1, 1, 2, 2). reps (int or tuple of int s) – The number of times which x is replicated along each axis. The tiled output Variable. Let the length of reps be d, the output has the dimension of max(d, x.ndim). Variable

Example

>>> x = np.array([0, 1, 2])
>>> x.shape
(3,)
>>> y = np.tile(x, 2)
>>> y.shape
(6,)
>>> y
array([0, 1, 2, 0, 1, 2])
>>> y = np.tile(x, (2, 2))
>>> y.shape
(2, 6)
>>> y
array([[0, 1, 2, 0, 1, 2],
[0, 1, 2, 0, 1, 2]])
>>> y = np.tile(x, (2, 1, 2))
>>> y.shape
(2, 1, 6)
>>> y
array([[[0, 1, 2, 0, 1, 2]],

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

>>> x = np.array([[1, 2], [3, 4]])
>>> x.shape
(2, 2)
>>> y = np.tile(x, 2)
>>> y.shape
(2, 4)
>>> y
array([[1, 2, 1, 2],
[3, 4, 3, 4]])
>>> y = np.tile(x, (2, 2))
>>> y.shape
(4, 4)
>>> y
array([[1, 2, 1, 2],
[3, 4, 3, 4],
[1, 2, 1, 2],
[3, 4, 3, 4]])
>>> y = np.tile(x, (2, 1, 2))
>>> y.shape
(2, 2, 4)
>>> y
array([[[1, 2, 1, 2],
[3, 4, 3, 4]],

[[1, 2, 1, 2],
[3, 4, 3, 4]]])