6.1.3 Why did I get worse when I increased the sample size?
fangxuehouwuming opened this issue · comments
Following the example in the book, I increased the sample size from 200 to 3000 and added a dropout regularization, but the final validation accuracy is only 50%.
YES!!! I have received your E-mail——Steven Lee
您好，攀枝花市文广旅局人事科已收到你的邮件！
My setting is training samples : validation samples =3000 : 10000 . Is it reasonable?
May be I know.
@fangxuehouwuming Maybe try to make a train,validation and test set. And see what happens?