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.

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

there is something wrong in federated_main.py #35

Open
Mr-lq7 opened this issue Jun 7, 2022 · 5 comments
Open

there is something wrong in federated_main.py #35

Mr-lq7 opened this issue Jun 7, 2022 · 5 comments

Comments

@Mr-lq7
Copy link

Mr-lq7 commented Jun 7, 2022

微信截图_20220607111935
the code should be the change to the place marked in the red box

@Mr-lq7
Copy link
Author

Mr-lq7 commented Jun 7, 2022

Sorry, it should be :
for idx in idxs_users:

@duchoang06
Copy link

Agreed. Should be 'idx' instead of 'c'.

@OuyangWenyu
Copy link

https://github.com/AshwinRJ/Federated-Learning-PyTorch/blob/26eaec40fa8beb56777feb89756f6401c28c4736/src/federated_main.py#L100C43-L100C72 the comment is "over all users at every epoch", I guess it should be c, and the idxs should be user_groups[c]

@saigontrade88
Copy link

Hi,
To calculate the average training accuracy over all users (also known as the variable "idxs_users") participating in a training round, we should calculate the training accuracy of each user. We sum them up and divide the sum by the number of participants.

@saigontrade88
Copy link

@Mr-lq7 If you are clear, please close this issue. Thanks.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants