We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
你好,想请教一下,我训练自己的数据集,totalloss一直在0.6-0.76之间波动,但是验证map最终达到0.99,这和在mmdetection上训练验证结果不同,想请教loss这样合理么?代码中有加入正则化防止过拟合么?非常感谢!
The text was updated successfully, but these errors were encountered:
@Fuhan1994 loss计算与官方release的是一致的 可以检查下在训练数据上的结果。total loss最后收敛在这个位置记忆中是正常的,因为centerness loss大概收敛到0.5。
Sorry, something went wrong.
No branches or pull requests
你好,想请教一下,我训练自己的数据集,totalloss一直在0.6-0.76之间波动,但是验证map最终达到0.99,这和在mmdetection上训练验证结果不同,想请教loss这样合理么?代码中有加入正则化防止过拟合么?非常感谢!
The text was updated successfully, but these errors were encountered: