After you train a model in Tensorflow:
As Yaroslav said, you can hack restoring from a graph_def and checkpoint by importing the graph, manually creating variables, and then using a Saver.
I implemented this for my personal use, so I though I'd share the code here.
Link: https://gist.github.com/nikitakit/6ef3b72be67b86cb7868
(This is, of course, a hack, and there is no guarantee that models saved this way will remain readable in future versions of TensorFlow.)