We need to provide way better example of the deep methods. For each methods we should provide a training example (which is already done) and then an explanation of what is happening:
adversarial method -> domain prediction
divergence methods and OT methods -> TSNE of the features
We should also explain how to train the methods with skorch or torch. That is already what I started to do in plot_training_method.py.
We need to provide way better example of the deep methods. For each methods we should provide a training example (which is already done) and then an explanation of what is happening:
We should also explain how to train the methods with skorch or torch. That is already what I started to do in
plot_training_method.py
.