You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@scaldas Hi!
I have a question about the model for CelebA dataset.
In the paper, it said that
For the CelebA experiments, we use 10% of the total clients and the same model we described above for FEMNIST.
...
For the FEMNIST experiments in the same figure, we subsample 5% of the data, and use a model with two convolutional layers followed by pooling, and a final dense layer with 2048 units.
However, the code contains 4 convolutional layers and etc.
What is the correct version?
Thanks.
The text was updated successfully, but these errors were encountered:
@scaldas Hi!
I have a question about the model for CelebA dataset.
In the paper, it said that
However, the code contains 4 convolutional layers and etc.
What is the correct version?
Thanks.
The text was updated successfully, but these errors were encountered: