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

val_loss在有些epoch突变特别大 #76

Open
PuckBlink opened this issue Dec 22, 2021 · 1 comment
Open

val_loss在有些epoch突变特别大 #76

PuckBlink opened this issue Dec 22, 2021 · 1 comment

Comments

@PuckBlink
Copy link

我用了您的一些keras的代码,发现您用keras的fit_generator的版本时,验证集的loss就偶然性地很大,train_on_batch就没有问题。不知道如何下手去debug。

例如若干个epoch的valloss的记录如下
2.328559160232544
46.456790924072266
2.044419527053833
72.33136749267578
1.930311918258667
15.246846199035645
1.9836046695709229
1934.048583984375
1.670356035232544
1.4758470058441162
2.3086090087890625

@bubbliiiing
Copy link
Owner

train_on_batch就没有问题是怎么做到的0 0

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