obj_offspring_weights_reparam: Reparameterization of 'obj_offspring_weights'.
In dcgerard/updogAlpha: Using Parental Data for Offspring Genotyping

It doesn't make any sense to have outlier = true since the weights are just for the EM already.

1 2	obj_offspring_weights_reparam(ocounts, osize, weight_vec, ploidy, prob_geno, s, ell, r)

`ocounts`	The observed counts of the refernce allele for each individual.
`osize`	The observed number of reads for each individuals.
`weight_vec`	A vector of numerics between 0 and 1. They don't have to sum to 1.
`ploidy`	An integer. The ploidy of the species. This is assumed to be the same for each individual.
`prob_geno`	The allele frequencies of the genotypes. See `get_prob_geno`.
`s`	Same as `log(bias_val)` in `obj_offspring`.
`ell`	We have `seq_error = expit(ell)` from `obj_offspring`.
`r`	Same as `log((1.0 - od_param) / od_param)` from `obj_offspring`.