R/gen-namespace-docs.R
, R/gen-namespace-examples.R
, R/gen-namespace.R
torch_logsumexp.Rd
Logsumexp
torch_logsumexp(self, dim, keepdim = FALSE)
self | (Tensor) the input tensor. |
---|---|
dim | (int or tuple of ints) the dimension or dimensions to reduce. |
keepdim | (bool) whether the output tensor has |
Returns the log of summed exponentials of each row of the input
tensor in the given dimension dim
. The computation is numerically
stabilized.
For summation index \(j\) given by dim
and other indices \(i\), the result is
$$ \mbox{logsumexp}(x)_{i} = \log \sum_j \exp(x_{ij}) $$
If keepdim
is TRUE
, the output tensor is of the same size
as input
except in the dimension(s) dim
where it is of size 1.
Otherwise, dim
is squeezed (see torch_squeeze
), resulting in the
output tensor having 1 (or len(dim)
) fewer dimension(s).
#> torch_tensor #> 1.1955 #> 1.1585 #> 1.2833 #> [ CPUFloatType{3} ]