I’m trying to implement the paper => Unsupervised Domain Adaptation by Backpropagation by Gannin et. al.
The architecture is as follows -
How do we implement something like this in PyTorch. More specifically:
- An architecture which has 2 different outputs that are trying to classify different things.
- Run back-propagation taking into account the individual losses from both “branches”.
- In this paper, the authors multiply the backprop values by
-1in the gradient reverse layer. How do we do something like that in PyTorch?