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

fchollet / deep-learning-with-python-notebooks

Jupyter notebooks for the code samples of the book "Deep Learning with Python"

MIT License

17.95k stars 8.48k forks source link

6.1.3 Why did I get worse when I increased the sample size? #210

Open fangxuehouwuming opened 1 year ago

fangxuehouwuming commented 1 year ago

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

ifond commented 1 year ago

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

lxl0506 commented 1 year ago

您好，攀枝花市文广旅局人事科已收到你的邮件！

fangxuehouwuming commented 1 year ago

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

Shuyib commented 1 year ago

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