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

做dev时也用了train_step #2

Open
charmpeng opened this issue Feb 6, 2019 · 2 comments
Open

做dev时也用了train_step #2

charmpeng opened this issue Feb 6, 2019 · 2 comments

Comments

@charmpeng
Copy link

train.py里的dev_step, 第173行,在做dev时,也用了train_step,这导致了log文件里,每100步做一次dev,但后续的train里,step数都是n+20开始,而不是从n+1开始。

@charmpeng
Copy link
Author

然后在epoch=85,batch size=64的情况下run,7k步时,acc一直都在0.2~0.3间震荡。

@JesseNLP
Copy link

train.py里的dev_step, 第173行,在做dev时,也用了train_step,这导致了log文件里,每100步做一次dev,但后续的train里,step数都是n+20开始,而不是从n+1开始。

同发现这个问题,dev里去掉train_step后,准确率一直很低,证明代码的泛化性能很差。最近在看一些优化方法,寻找提高准确率的方法。不知道你还有没有接着研究提高验证准确的方法。

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