pow

Documentation

treetensor.torch.pow(input, exponent, *args, **kwargs)

Takes the power of each element in input with exponent and returns a tensor with the result.

Examples:

>>> import torch
>>> import treetensor.torch as ttorch
>>> ttorch.pow(
...     ttorch.tensor([4, 3, 2, 6, 2]),
...     ttorch.tensor([4, 2, 6, 4, 3]),
... )
tensor([ 256,    9,   64, 1296,    8])

>>> ttorch.pow(
...     ttorch.tensor({
...         'a': [4, 3, 2, 6, 2],
...         'b': {
...             'x': [[3, 4, 6],
...                   [6, 3, 5]],
...             'y': [[[3, 5, 5],
...                    [5, 7, 6]],
...                   [[4, 6, 5],
...                    [7, 2, 7]]],
...         },
...     }),
...     ttorch.tensor({
...         'a': [4, 2, 6, 4, 3],
...         'b': {
...             'x': [[7, 4, 6],
...                   [5, 2, 6]],
...             'y': [[[7, 2, 2],
...                    [2, 3, 2]],
...                   [[5, 2, 6],
...                    [7, 3, 4]]],
...         },
...     }),
... )
<Tensor 0x7f11b13b6e48>
├── a --> tensor([ 256,    9,   64, 1296,    8])
└── b --> <Tensor 0x7f11b13b6d68>
    ├── x --> tensor([[ 2187,   256, 46656],
    │                 [ 7776,     9, 15625]])
    └── y --> tensor([[[  2187,     25,     25],
                       [    25,    343,     36]],

                      [[  1024,     36,  15625],
                       [823543,      8,   2401]]])

Torch Version Related

This documentation is based on torch.pow in torch v2.4.1+cu121. Its arguments’ arrangements depend on the version of pytorch you installed.

If some arguments listed here are not working properly, please check your pytorch’s version with the following command and find its documentation.

python -c 'import torch;print(torch.__version__)'

The arguments and keyword arguments supported in torch v2.4.1+cu121 is listed below.

Description From Torch v2.4.1+cu121

torch.pow(input, exponent, *, out=None) → Tensor

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.

Args:

input (Tensor): the input tensor. exponent (float or tensor): the exponent value

Keyword args:

out (Tensor, optional): the output tensor.

Example:

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

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

torch.pow(self, exponent, *, out=None) → Tensor

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:

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

Args:

self (float): the scalar base value for the power operation exponent (Tensor): the exponent tensor

Keyword args:

out (Tensor, optional): the output tensor.

Example:

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