logsumexp(input, dim, keepdim=False, out=None)¶
Returns the log of summed exponentials of each row of the
inputtensor in the given dimension
dim. The computation is numerically stabilized.
For summation index given by dim and other indices , the result is
True, the output tensor is of the same size as
inputexcept in the dimension(s)
dimwhere it is of size 1. Otherwise,
dimis squeezed (see
torch.squeeze()), resulting in the output tensor having 1 (or
len(dim)) fewer dimension(s).
>>> a = torch.randn(3, 3) >>> torch.logsumexp(a, 1) tensor([ 0.8442, 1.4322, 0.8711])