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.

Sign up for GitHub

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

Jump to bottom

loss 大小 #40

Open
Pro-flynn opened this issue Sep 27, 2022 · 8 comments
Open

loss 大小 #40

Pro-flynn opened this issue Sep 27, 2022 · 8 comments

Comments

@Pro-flynn
Copy link

我用的我自己的数据集跑了一下 loss由7.2下降到5.8就收敛了 我调了学习率和batch也没有什么改观 请问loss这个下降幅度正常吗
@Yunfan-Li
Copy link
Owner

loss的数值和temperature的取值有关，但是loss不明显下降的时候聚类性能可能还会慢慢提升

@Pro-flynn
Copy link
Author

loss显著降低之后 聚类性能会有明显提升吗

@Pro-flynn
Copy link
Author

@Yunfan-Li

@Yunfan-Li
Copy link
Owner

CIFAR-10的话从500epoch训到1000epoch的过程能提升几个点这样

@Pro-flynn
Copy link
Author

请问 你的实验中5000到1000epoch loss能降低多少

@Pro-flynn
Copy link
Author

@Yunfan-Li

@Yunfan-Li
Copy link
Owner

具体数值记不太清了，应该变化不大，你可以跑一下代码看看

@showmeyourcodehaha
Copy link

你这效果这么好？我感觉这模型收敛挺慢的

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@Pro-flynn @Yunfan-Li @showmeyourcodehaha