paddle. logsumexp ( x, axis=None, keepdim=False, name=None ) [source]

Calculates the log of the sum of exponentials of x along axis .

\[logsumexp(x) = \log\sum exp(x)\]
  • x (Tensor) – The input Tensor with data type float16, float32 or float64, which have no more than 4 dimensions.

  • axis (int|list|tuple, optional) – The axis along which to perform logsumexp calculations. axis should be int, list(int) or tuple(int). If axis is a list/tuple of dimension(s), logsumexp is calculated along all element(s) of axis . axis or element(s) of axis should be in range [-D, D), where D is the dimensions of x . If axis or element(s) of axis is less than 0, it works the same way as \(axis + D\) . If axis is None, logsumexp is calculated along all elements of x. Default is None.

  • keepdim (bool, optional) – Whether to reserve the reduced dimension(s) in the output Tensor. If keep_dim is True, the dimensions of the output Tensor is the same as x except in the reduced dimensions(it is of size 1 in this case). Otherwise, the shape of the output Tensor is squeezed in axis . Default is False.

  • name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.


Tensor, results of logsumexp along axis of x, with the same data type as x.


import paddle

x = paddle.to_tensor([[-1.5, 0., 2.], [3., 1.2, -2.4]])
out1 = paddle.logsumexp(x)    # 3.4691226
out2 = paddle.logsumexp(x, 1) # [2.15317821, 3.15684602]