Skip to content

Bug Fixed and Adjustment on fedavg_v1.2.0 #50

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

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Bug Fixed and Adjustment on fedavg_v1.2.0 #50

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 9 additions & 2 deletions fedlab_benchmarks/fedavg_v1.2.0/standalone.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,8 @@
from fedlab.utils.functional import evaluate
from fedlab.utils.functional import get_best_gpu, load_dict

from fedlab.utils.dataset import MNISTPartitioner

# configuration
parser = argparse.ArgumentParser(description="Standalone training example")
parser.add_argument("--total_client", type=int, default=100)
Expand Down Expand Up @@ -81,7 +83,11 @@ def forward(self, x):
aggregator = Aggregators.fedavg_aggregate
total_client_num = args.total_client # client总数

data_indices = load_dict("mnist_partition.pkl")
#data_indices = load_dict("mnist_partition.pkl")
data_indices = MNISTPartitioner(trainset.targets,
args.total_client,
partition="iid",
seed=2025)

# fedlab setup
trainer = SubsetSerialTrainer(model=model,
Expand All @@ -91,7 +97,8 @@ def forward(self, x):
"batch_size": args.batch_size,
"epochs": args.epochs,
"lr": args.lr
})
},
cuda=args.cuda)

# train procedure
to_select = [i for i in range(total_client_num)]
Expand Down