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

关于准确度和loss值 #42

Open
jingrunzhou opened this issue Aug 1, 2020 · 2 comments
Open

关于准确度和loss值 #42

jingrunzhou opened this issue Aug 1, 2020 · 2 comments

Comments

@jingrunzhou
Copy link

总共10类,每类几百张照片,val accuracy 在第三轮就达到了1.0,之后一直不变。test accuracy 在前几轮不断上升,上升到第8轮为0.69,之后不断震荡、下降,50轮时,test accuracy 为0.3。loss下降缓慢,到第10轮之后下降的特别特别慢,几乎保持不变。请问楼主,这是什么原因。

@wusaifei
Copy link
Owner

wusaifei commented Aug 2, 2020

这是因为过拟合了,因为你的数据量比较少,而且网络比较复杂,建议换成B1, B2试试。或者你的在进行测试的时候shuffle没有设置为FALSE,导致每次测试都会发生改变。你检查一下哈。

@jingrunzhou
Copy link
Author

好的,谢谢大佬指点,我试试您的方法,谢谢!

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