Skip to content
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

关于第三章Pytorch简单实现 #14

Open
Guncuke opened this issue Feb 28, 2023 · 2 comments
Open

关于第三章Pytorch简单实现 #14

Guncuke opened this issue Feb 28, 2023 · 2 comments

Comments

@Guncuke
Copy link

Guncuke commented Feb 28, 2023

初始化服务器模型的时候使用了self.global_model = models.get_model(self.conf["model_name"])
但是在添加参与客户端的时候,为什么也是使用self.local_model = models.get_model(self.conf["model_name"])
初始化函数参数里的model没有被使用,我觉得应该改为self.local_model=model, local_train函数不需要model参数,在前面每个通讯选中参与者时将参与者的self.model设置成新的全局模型会不会好一点。

@LianZhuotao
Copy link

哈咯,请问lambda什么含义呀?为什么取0.1?随机选五人训练聚合,不应该取0.2吗

@Guncuke
Copy link
Author

Guncuke commented Mar 27, 2023

哈咯,请问lambda什么含义呀?为什么取0.1?随机选五人训练聚合,不应该取0.2吗

取0.2就是之后的全局模型完全取决于本轮次客户端提交的参数差,如果提交小于0.2那就代表还考虑了全局模型的权重

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants