TensorFlow: A proposal of good practices for files, folders and models architecture

Designing the right file architecture is not straightforward in Machine Learning. After struggling on that question for a few projects of my owns, I started to discover simple patterns that cover most of the use cases I stumbled upon when reading code or coding my own stuff. This article is about sharing those discoveries with you. That's quite a lot and one can be easily lost in refactoring files and folders to make everything fit nicely, on top of that, there are probably other needs that I'm not even addressing in the list above so let's try to find out some best practices. This is the very basics.