Function dfdx::tensor_ops::logsumexp

pub fn logsumexp<T: Reduce1<-1>>(t: T) -> T::Reduced

Computes the LogSumExp function.

Pytorch equivalent: t.exp().sum(-1).log()

Related functions: ln(), sum_axis(), exp(), log_softmax(), softmax()

Examples:

let a = Tensor0D::new(0.0);
let r = logsumexp(a);
assert_eq!(r.data(), &0.0);

let a = Tensor1D::new([-2.0, -1.0, 0.0, 1.0, 2.0]);
let r = a.logsumexp();
assert_eq!(r.data(), &2.4519143);