Skip to content
This repository has been archived by the owner on May 22, 2024. It is now read-only.

valid acc always is 0.5 #15

Open
xiaqing10 opened this issue Mar 24, 2020 · 5 comments
Open

valid acc always is 0.5 #15

xiaqing10 opened this issue Mar 24, 2020 · 5 comments

Comments

@xiaqing10
Copy link

when I train this recognition model , the valid result always is 0.5 ,and the total loss change from 40 to 8.
can you explain the results?

@freefeifan
Copy link

我训练是也是同样的问题,难道是数据的问题吗

@freefeifan
Copy link

当我训练该识别模型时,有效结果始终为0.5,总损失从40变为8。
您能解释一下结果吗?

请问您现在解决了吗

@Mob97
Copy link

Mob97 commented Jun 4, 2020

Same problem here :(

@freefeifan
Copy link

是因为loss太大了 如果继续训练,当loss小些时,准确率会开始变化

@liushuan
Copy link

Same problem here

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants