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
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。
The text was updated successfully, but these errors were encountered:
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。
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
Sorry, something went wrong.
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
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.
No branches or pull requests
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。
The text was updated successfully, but these errors were encountered: