Open lorenzozanisi opened 2 years ago
I think when writing the code we wanted it to be as general as possible and allow it to account for N outputs which I suppose with your suggested structure that could be acheivied by just adding a new key. So I agree this is a good idea
@zcapjdb did you get round to implement this in the end?
I have not yet, I wanted to just get some stuff running with all the new pipeline changes
at the moment all losses for both regressors are appended to the same output dictionary. Wouldn't it be easier to have N dictionaries, one for each regressor, and one dictionary only for the classifier? We could have
output_dict = {flux1:dict_flux1, flux2:dict_flux2, class: dict_class}
. @zcapjdb @thandi1908 Wouldn't that make things easier both in the code and in the postprocessing?