Closed vineetjohn closed 6 years ago
The gradients should be propagated through separate sets of differentiable variables for both the Adversarial component and the Reconstruction component.
The sets are not mutually exclusive. They will have some common variables to update.
Already handled by default in Tensorflow based on the dependency graph.
The gradients should be propagated through separate sets of differentiable variables for both the Adversarial component and the Reconstruction component.
The sets are not mutually exclusive. They will have some common variables to update.