pow

paddle. pow ( x, y, name=None ) [source]

Compute the power of Tensor elements. The equation is:

\[out = x^{y}\]

Note

paddle.pow supports broadcasting. If you want know more about broadcasting, please refer to Introduction to Tensor .

Parameters
  • x (Tensor) – An N-D Tensor, the data type is float16, float32, float64, int32 or int64.

  • y (float|int|Tensor) – If it is an N-D Tensor, its data type should be the same as x.

  • name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Returns

N-D Tensor. A location into which the result is stored. Its dimension and data type are the same as x.

Examples

>>> import paddle

>>> x = paddle.to_tensor([1, 2, 3], dtype='float32')

>>> # example 1: y is a float or int
>>> res = paddle.pow(x, 2)
>>> print(res)
Tensor(shape=[3], dtype=float32, place=Place(cpu), stop_gradient=True,
[1., 4., 9.])
>>> res = paddle.pow(x, 2.5)
>>> print(res)
Tensor(shape=[3], dtype=float32, place=Place(cpu), stop_gradient=True,
[1.         , 5.65685415 , 15.58845711])

>>> # example 2: y is a Tensor
>>> y = paddle.to_tensor([2], dtype='float32')
>>> res = paddle.pow(x, y)
>>> print(res)
Tensor(shape=[3], dtype=float32, place=Place(cpu), stop_gradient=True,
[1., 4., 9.])