There is a debate that Keras isn't owned by anyone, so people are happier to contribute in and it'll be much easier to manage the project in the future.
On the other side, tf.keras is owned by Google, so more rigorous test and maintenance. Moreover, it seems this is a better option for taking advantage of new features which are presenting in Tensorflow v.2.
So, to start a data science (machine learning) project (in the research phase), that both are okay at the beginning, which one do you choose?!