mindspore.mint.pow

View Source On Gitee
mindspore.mint.pow(input, exponent)[source]

Calculates the exponent power of each element in input.

When exponent is a Tensor, the shapes of input and exponent must be broadcastable.

\[out_{i} = input_{i} ^{ exponent_{i}}\]

Warning

This is an experimental API that is subject to change or deletion.

Parameters

  • input (Union[Tensor, Number]) – The first input is a Number or a tensor whose data type is number or bool.

  • exponent (Union[Tensor, Number]) –

    The second input is a Number or a tensor whose data type is number or bool.

Returns

Tensor, the shape is the same as the one after broadcasting, and the data type is the one with higher precision or higher digits among the two inputs.

Raises

  • TypeError – If types of input and exponent are bool.

  • TypeError – The input is tensor and of type int or bool, while the exponent is negative int.

Supported Platforms:

Ascend

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, mint
>>> input = Tensor(np.array([1.0, 2.0, 4.0]), mindspore.float32)
>>> exponent = 3.0
>>> output = mint.pow(input, exponent)
>>> print(output)
[ 1.  8. 64.]
>>>
>>> input = Tensor(np.array([1.0, 2.0, 4.0]), mindspore.float32)
>>> exponent = Tensor(np.array([2.0, 4.0, 3.0]), mindspore.float32)
>>> output = mint.pow(input, exponent)
>>> print(output)
[ 1. 16. 64.]