Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://docs.pytorch.org/docs/stable/generated/torch.float_power.html below:

torch.float_power — PyTorch 2.7 documentation

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

Raises input to the power of exponent, elementwise, in double precision. If neither input is complex returns a torch.float64 tensor, and if one or more inputs is complex returns a torch.complex128 tensor.

Note

This function always computes in double precision, unlike torch.pow(), which implements more typical type promotion. This is useful when the computation needs to be performed in a wider or more precise dtype, or the results of the computation may contain fractional values not representable in the input dtypes, like when an integer base is raised to a negative integer exponent.

Parameters

• input (Tensor or Number) – the base value(s)

• exponent (Tensor or Number) – the exponent value(s)

Keyword Arguments

out (Tensor, optional) – the output tensor.

Example:

>>> a = torch.randint(10, (4,))
>>> a
tensor([6, 4, 7, 1])
>>> torch.float_power(a, 2)
tensor([36., 16., 49.,  1.], dtype=torch.float64)

>>> a = torch.arange(1, 5)
>>> a
tensor([ 1,  2,  3,  4])
>>> exp = torch.tensor([2, -3, 4, -5])
>>> exp
tensor([ 2, -3,  4, -5])
>>> torch.float_power(a, exp)
tensor([1.0000e+00, 1.2500e-01, 8.1000e+01, 9.7656e-04], dtype=torch.float64)

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4