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

about test.py #15

Open
Richardsh opened this issue Jun 23, 2020 · 1 comment
Open

about test.py #15

Richardsh opened this issue Jun 23, 2020 · 1 comment

Comments

@Richardsh
Copy link

你好!
因为我在训练到600多epoch的时候报错了,但是用“tensorboard”也能输出所有的mae, mse包括test数据集的mae, mse.
这里我只执行了python train_lr.py, 没有执行python test.py, 所以只执行python train_lr.py输出的mae, mse具体指的什么mae和mse, 我是必须要执行test才是输出的test的mae和mse?

@gjy3035
Copy link
Owner

gjy3035 commented Jun 24, 2020

由于数据集没有明确划分验证集,因此我们在train 的过程中使用test数据作为指标的监控。
严格来讲,是需要划分验证集的。建议从train中划分10%的数据。事实上,我们论文也是按照该方案执行的。为了保证大家的可复现性,才在最终release代码时,才用了test(毕竟每个人随机划分出的验证集是有差别的,这也会影响复现效果)。

test.py则是为了最终的评估和可视化。

@Wohoholo Wohoholo mentioned this issue Jan 12, 2021
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