In Keras, the inverse of Conv2D is Conv2DTranspose. But how can I create the inverse of LocallyConnected2D? That is, using "local" connections, how can I map a small set of nodes into a larger set of nodes?
Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.Sign up to join this community