tensorplay.functional.pow

tensorplay.functional.pow(input, exponent, *, out=None) → Tensor[source]

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 or a Tensor with the same number of elements 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:

$$\text{out}_i = x_i ^ {\text{exponent}_i}$$

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

Parameters:

• input (Tensor) – the input tensor.

• exponent (float or tensor) – the exponent value

Keyword Arguments:

out (Tensor, optional) – the output tensor.

Example:

>>> a = tensorplay.randn(4)
>>> a
tensor([ 0.4331,  1.2475,  0.6834, -0.2791])
>>> tensorplay.pow(a, 2)
tensor([ 0.1875,  1.5561,  0.4670,  0.0779])
>>> exp = tensorplay.arange(1., 5.)

>>> a = tensorplay.arange(1., 5.)
>>> a
tensor([ 1.,  2.,  3.,  4.])
>>> exp
tensor([ 1.,  2.,  3.,  4.])
>>> tensorplay.pow(a, exp)
tensor([   1.,    4.,   27.,  256.])

tensorplay.functional.pow(self, exponent, *, out=None) → Tensor[source]

self is a scalar float value, and exponent is a tensor. The returned tensor out is of the same shape as exponent

The operation applied is:

$$\text{out}_i = \text{self} ^ {\text{exponent}_i}$$

Parameters:

• self (float) – the scalar base value for the power operation

• exponent (Tensor) – the exponent tensor

Keyword Arguments:

out (Tensor, optional) – the output tensor.

Example:

>>> exp = tensorplay.arange(1., 5.)
>>> base = 2
>>> tensorplay.pow(base, exp)
tensor([  2.,   4.,   8.,  16.])