search

wenzhu23333 / Differential-Privacy-Based-Federated-Learning

Everything you want about DP-Based Federated Learning, including Papers and Code. (Mechanism: Laplace or Gaussian, Dataset: femnist, shakespeare, mnist, cifar-10 and fashion-mnist. )
GNU General Public License v3.0
348 stars 56 forks source link

精度很低 #3

Closed zz978233034 closed 2 years ago

zz978233034 commented 2 years ago

你好，我想请问，为什么我在运行这个代码的时候，我发现他不收敛是咋回事呢，精度一直在十几

AshliaYan commented 2 years ago

我也有同样的问题，请问你解决了吗？

zz978233034 commented 2 years ago

没有

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年11月17日(星期四) 晚上9:29 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [wenzhu23333/Differential-Privacy-Based-Federated-Learning] 精度很低 (Issue #3)

我也有同样的问题，请问你解决了吗？

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

xiyuanyang45 commented 2 years ago

我也遇到了这个问题，这个project有没有讨论群什么的呀

wenzhu23333 commented 2 years ago

仓库已更新，添加了Per Sample Gradient Clip，以及run.sh里面提供了一些example，结果见readme。