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

关于优化器的问题 #448

Open
yanyvjiangnan opened this issue Aug 31, 2024 · 4 comments
Open

关于优化器的问题 #448

yanyvjiangnan opened this issue Aug 31, 2024 · 4 comments

Comments

@yanyvjiangnan
Copy link

当我运行MLDG方法在PACS数据集上,此时优化器是默认的SGD
===========epoch 1===========
total_loss:0.8481
train_acc:0.7129,valid_acc:0.7092,target_acc:0.5942
total cost time: 179.1731

但是当我把SGD换成Adam后发现:
===========epoch 1===========
total_loss:4.0192
train_acc:0.1492,valid_acc:0.1555,target_acc:0.1401
total cost time: 203.3469

还有就是algs/opt.py文件中的get_params方法中的 args.lr_decay1 * initlr,初始学习率乘以args.lr_decay1这个参数的作用是?

@yanyvjiangnan
Copy link
Author

还请老师们解惑一下

@luhaifeng19947
Copy link

luhaifeng19947 commented Aug 31, 2024 via email

@wlh-coconut
Copy link

wlh-coconut commented Aug 31, 2024 via email

@Sanfleeeee
Copy link

我已经收到您的邮件,会尽快处理。

我也有类似问题

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

4 participants