Sensible insights for a data-driven strategy to mannequin optimization
On this final a part of my collection, I’ll share what I’ve realized on deciding on a mannequin for picture classification and methods to tremendous tune that mannequin. I may also present how one can leverage the mannequin to speed up your labelling course of, and eventually methods to justify your efforts by producing utilization and efficiency statistics.
In Half 1, I mentioned the method of labelling your picture information that you simply use in your picture classification mission. I confirmed how outline “good” photos and create sub-classes. In Half 2, I went over numerous information units, past the standard train-validation-test units, with benchmark units, plus methods to deal with artificial information and duplicate photos. In Half 3, I defined methods to apply totally different analysis standards to a skilled mannequin versus a deployed mannequin, and utilizing benchmarks to find out when to deploy a mannequin.
Mannequin choice
To this point I’ve targeted a number of time on labelling and curating the set of photos, and in addition evaluating mannequin efficiency, which is like placing the cart earlier than the horse. I’m not attempting to attenuate what it takes to design an enormous neural community — this can be a essential a part of the appliance you’re constructing. In my…
