Skip to content
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.

Sign up for GitHub

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

Jump to bottom

feddyn algorithm correction #401

Merged
merged 1 commit into from
Apr 26, 2023
Merged

feddyn algorithm correction #401

merged 1 commit into from
Apr 26, 2023

Commits on Apr 25, 2023

  1. feddyn algorithm correction 

    The FedDyn algorithm does not send out the same model for training as it uses for evaluation.
This is now implemented in this PR.

The labels will be changed to type long before being sent to the loss function in order to avoid NaN values as output.

Lastly, the FedDynRegularizer class now has a .to(device) function in order to transfer the information as needed for subprocesses that use the GPU.
    @GustavBaumgart
    GustavBaumgart committed Apr 25, 2023
    Configuration menu
    Copy the full SHA
    60d2479 View commit details
    Browse the repository at this point in the history