deep-learning-with-python-notebooks 6.1.3 Why did I get worse when I increased the sample size?

6.1.3 Why did I get worse when I increased the sample size?

Open fangxuehouwuming opened this issue 2 years ago • 4 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%. 1661074009976

Aug 21 '22 09:08 fangxuehouwuming

YES!!! I have received your E-mail——Steven Lee

Aug 21 '22 09:08 ifond

您好，攀枝花市文广旅局人事科已收到你的邮件！

Aug 21 '22 09:08 lxl0506

My setting is training samples : validation samples =3000 : 10000 . Is it reasonable? May be I know.

Aug 21 '22 13:08 fangxuehouwuming

@fangxuehouwuming Maybe try to make a train,validation and test set. And see what happens?

Sep 07 '22 06:09 Shuyib

deep-learning-with-python-notebooks deep-learning-with-python-notebooks copied to clipboard

6.1.3 Why did I get worse when I increased the sample size?

deep-learning-with-python-notebooks
deep-learning-with-python-notebooks copied to clipboard