Kaian Jiang
Results
1
comments of
Kaian Jiang
You can solve this problem simply by set lr_decay =0.95 and replae ``` w_local, loss = local.train(net=net_local.to(args.device)) ``` with ``` w_local, loss = local.train(net=net_local.to(args.device), lr=lr) ``` or choose other powerful...