oneflow.pow

oneflow.pow()

Takes the power of each element in input with exponent and returns a tensor with the result. Exponent can be either a single float number, a single int number, or a tensor with the same shape as input. When exponent is a scalar value, the operation applied is:

\[\text{out}_i = x_i ^ \text{exponent}\]

When exponent is a tensor, the operation applied is:

\[\text{out}_i = x_i ^ {\text{exponent}_i}\]
Parameters
  • input (Tensor) – the input tensor.

  • exponent (int, float, Tensor) – the exponent.

Returns

The result of variance on the specified axis of input Tensor

Return type

Tensor

For example:

>>> import oneflow as flow
>>> import numpy as np

>>> x = flow.tensor(np.array([1.0, 2.0, 3.0, 4.0, 5.0, 6.0]), dtype=flow.float32)
>>> out = flow.pow(x, 2)
>>> out
tensor([ 1.,  4.,  9., 16., 25., 36.], dtype=oneflow.float32)

>>> x = flow.tensor(np.array([1.0, 2.0, 3.0, 4.0]), dtype=flow.float32)
>>> y = flow.tensor(np.array([1.0, 2.0, 3.0, 4.0]), dtype=flow.float32)
>>> out = flow.pow(x, y)
>>> out
tensor([  1.,   4.,  27., 256.], dtype=oneflow.float32)