author here: let me know if you have any questions
I know it's only a matter of training with other inputs, but most solutions I've seen haven't been trained with enough non-Caucasian images to give good results. Since this at least seems to be detecting shape regardless of skin tone it has more potential, but it'll only be as good as its training set.
I have not quantified how robust this net is in the face of noisy labels.
EDIT: Just created an account and tried it out on a test image, and it returned "nsfw" with prob 0.998, which is pretty amazing.
EDIT2: It's much less strong against oblique views, even with full color. http://40.media.tumblr.com/cfeea64370e3b1228906472ebd8f344e/... (NSFW, obviously!) only returns 0.541.