-
Notifications
You must be signed in to change notification settings - Fork 212
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
Add FedSGLD Exp #520
Add FedSGLD Exp #520
Conversation
a0dd220
to
ba2be8e
Compare
|
||
for (( i=0; i<5; i++ )) | ||
do | ||
CUDA_VISIBLE_DEVICES="${cudaid}" python federatedscope/main.py --cfg scripts/wide_valley_exp_scripts/fedentsgd_on_cifar10.yaml seed $i data.splitter_args "[{'alpha': ${lda_alpha}}]" trainer.local_entropy.gamma $gamma fedopt.optimizer.lr 1.0 fedopt.annealing $annealing trainer.local_entropy.eps $eps trainer.local_entropy.alpha $alpha train.optimizer.lr $lr expname fedentsgd_${lda_alpha}_${gamma}_${eps}_${annealing}_${i} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
need &
?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
no need as they would run on the same device
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
Fixed bugs and prepared scripts to compare FedSGLD with other algorithms