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

Question about binary_seg_pred #11

Open
zgh2022 opened this issue Feb 18, 2022 · 4 comments
Open

Question about binary_seg_pred #11

zgh2022 opened this issue Feb 18, 2022 · 4 comments

Comments

@zgh2022
Copy link

zgh2022 commented Feb 18, 2022

我用自己的数据集训练出了效果,instance的效果很好,但是binary_seg_pred一直是没有图像的,下面是打印的输出:
'binary_seg_pred': tensor([[[[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
...,
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0],
[0, 0, 0, ..., 0, 0, 0]]]], device='cuda:0',
grad_fn=),
但训练时是可以看到binary_seg_pred的loss值在下降的,我不知道是什么问题所导致。

@IrohXu
Copy link
Owner

IrohXu commented Feb 18, 2022

可以先尝试调整一下loss的权重看看:
试试将这个值增大,或者不计算instance只计算语义分割部分。
image

如果问题还不能解决,建议在模型训练过程中加一个实时输出图像的接口,观察训练是否出现问题,可以加在这里:
https://github.com/IrohXu/lanenet-lane-detection-pytorch/blob/main/model/lanenet/train_lanenet.py

@zgh2022
Copy link
Author

zgh2022 commented Feb 18, 2022

好的,感谢,我尝试一下

@DebuggerSunfz
Copy link

好的,感谢,我尝试一下

你好,我在训练自己数据集的时候也遇到了同样的问题,请问你解决了吗,怎么解决的

@BaitingLuo
Copy link

好的,感谢,我尝试一下

你好,我在训练自己数据集的时候也遇到了同样的问题,请问你解决了吗,怎么解决的

Removing the instance loss addressed the issue for me.

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

4 participants