mindspore.ops.logaddexp

mindspore.ops.logaddexp(input, other)[source]

Computes the logarithm of the sum of exponentiations of the inputs. This function is useful in statistics where the calculated probabilities of events may be so small as to exceed the range of normal floating point numbers.

\[out_i = \log(exp(input_i) + \exp(other_i))\]
Parameters

  • input (Tensor) – Input Tensor. The dtype of input must be float.

  • other (Tensor) – Input Tensor. The dtype of input must be float. If the shape of input is not equal to the shape of other, they must be broadcastable to a common shape (which becomes the shape of the output).

Returns

Tensor.

Raises

  • TypeError – If input, other is not a Tensor.

  • TypeError – The dtype of input or other is not float.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x1 = Tensor(np.array([1, 2, 3]).astype(np.float16))
>>> x2 = Tensor(np.array(2).astype(np.float16))
>>> output = ops.logaddexp(x1, x2)
>>> print(output)
[2.312 2.693 3.312]