[D] Using PyTorch from R

Except it uses something like the R6 class system and is more "Pythonic" anyways. I wish there were more ways to do DL without having to learn OOP, so that its more accessible for non-programmers. Seems like Keras/TF 2 are still easier if you don't come from that type of background of using OOP heavily. They can be used in R too (though its a wrapper for Python) and the % % in R sort of lets you do it in a more functional "tidy" way. Other than that the only non OOP framework I have seen would be Julia's Flux but its hardly used much.