-
以下是我使用该仓库进行的一些方法复现所使用的超参数,走过路过的朋友们,如果发现哪里超参数的选择不合理或该使用的超参数未使用到,麻烦提醒下我,不胜感激。
-
Why does the FedAvg use a simple average without weight?
-
I wonder is it the official code implementation of the paper?
can this code achieve the performance claimed in the paper? The code set the same hyper-parameters as the paper and I'd like to know …
-
hi, when I test sh run_step_by_step_example.sh 4 config/mnist_lr/fedml_config.yaml, found below error which cause timeout
![image](https://user-images.githubusercontent.com/40284225/190858521-6ee0199…
-
I notice that the code uses CrossEntropyLoss for local training:
https://github.com/pliang279/LG-FedAvg/blob/7af0568b2cae88922ebeacc021b1679815092f4e/models/Update.py#L28
And it accepts the log-pr…
-
I am trying to reproduce the FedAvg results on 20news data. However, the FedAvg algorithm on 20news task seems not working. Comparing with the centralized run, the eval accuracy and loss of FedAvg did…
-
你好,请问代码要这样设置才能跑到论文的效果,我直接运行给的fedavg_10_1.sh和fedavg_10_2sh并不能跑到论文给的效果。
-
In class FedAvgLocalTrainingHandler in script party/training/fedavg_local_training_handler.py, I think there is a mistake. The two methods get_train_metrics_pre and get_train_metrics_post (of the inhe…
-
Dear Dr.Jia,
I attempted to run your code and encountered some questions regarding the calculation of the model's params and FLOPs.
dummy_input = torch.randn(1, 3, 32, 32)
flops, params = profi…
-
Hey, sorry to bother you again(`◕‸◕´+)
I have questions about reproducing the landscape and hessian in the FedSMOO paper.
I use the code of _"[Visualizing the Loss Landscape of Neural Nets](https://…