Tensorflow and deep leanrning, without a PhD – part 2

I've been wanting to dive into this subject for quite a while now. I've been playing with large data sets for a few years now. I learned only the basics of data mining. I re-took courses in linear algebra and inferential stats. How much time do you think I would need (per week) and for how long to achieve a knowledgeable status in Tensorflow and deep learning (assuming I know the kind of models i aim to build and improve) ?