Hi He,

In the Pix2Pix paper the authors utilize dropout layers in the U-net in order to produce varied images. I left that out of this implementation, since it would generate inconsistency in a video if each of the frames was generated using a different procedure.

Adding the dropout layers should be pretty simple with the current code though, as there is a slim.dropout() op.

PhD. Interests include Deep (Reinforcement) Learning, Computational Neuroscience, and Phenomenology.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store