-
Notifications
You must be signed in to change notification settings - Fork 288
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implement RSC (lightly tested) / Cleanup hyperparameter registry #12
Conversation
Note: MLP is used in DANN variants. |
Then the MLP parameters should only show in the console when DANN is used as an algorithm |
Merged, although we will have to find a solution to guarantee that the same random parameters are sampled in cc @igul222 |
@SirRob1997: Preliminar runs show a very poor performance (39%) at OfficeHome. The paper reports 63%. Could you investigate how to get a higher number in this dataset with default hyper-parameters? |
Implement RSC (lightly tested) / Cleanup hyperparameter registry
This PR implements the following features:
MNIST_CNN
forward pass to useAdaptiveAvgpool2d
instead of mean, this allows for more flexible usage in algorithms and feels more cleanYou might also want to delete the MLP parts in
networks.py
andhparams_registry.py
as well since I think MLP was only added for Debug datasets that don't get used anymore?