As per the assertion error, I’m interested in creating a regression CNN.
I’m of course willing to contribute to/make the initial solution, but it’s not clear to me exactly what additions need to be made. It looks like the only changes that would need to be made to get it working is to change the
create_head function and make an
RegressionLearner equivalent to the
The latter may be straight-forward, but the former (i.e., creating a default
create_head function) is not so clear. I use regression CNNs to learn image-to-image regressions (example). But regression could also mean: take an image to some arbitrarily-sized set of real numbers. Any thoughts on what the default behavior should be? And what else should be included in the