Also, it seems to me that most of what he says can be distilled into a boilerplate/template structure for any given deep learning framework, from which new projects can be forked - does this already exist?
Allennlp is one such project for NLP. Uses dependency injection to separate out the components driving for maximum re-usability. https://github.com/allenai/allennlp
Also, it seems to me that most of what he says can be distilled into a boilerplate/template structure for any given deep learning framework, from which new projects can be forked - does this already exist?