ImportError:/fpn.pytorch-master/lib/model/nms/_ext/nms/_nms.so: undefined symbol: __cudaPopCallConfiguration

[AndrewNest]

When there is a problem with demo.py, we first use the demo.py given by the author @jwyang and report an error import error: no module named fast rcnn.faster rcnn_ cascade。 It was found that the demo of the project was not updated for FPN, so it was replaced by the demo.py provided by @Zongxianlee. My environment is Python 2.7.18, CUDA 9.0.176, torch 0.4.0 torch vision 0.2.1 cudatoolkit 9.0. It is confirmed that the CUDA version is consistent with the CUDA version of PyTorch, but running the updated demo.py still reports an error: undefined symbol:__ cudaPopCallConfiguration。Any idea about the problem? Thanks！

demo.py出现问题，最开始使用作者@jwyang给出的demo.py，报错ImportError: No module named faster_rcnn.faster_rcnn_cascade。发现该项目的demo并没有针对FPN更新，于是换成了@ZongxianLee 提供的demo.py. 我的环境是：python 2.7.18 、cuda 9.0.176 、torch 0.4.0 torchvision 0.2.1 cudatoolkit 9.0. 确定了cuda的版本和pytorch 的cuda版本是一致的，但运行更新后的demo.py依旧报错：undefined symbol: __cudaPopCallConfiguration。有什么建议吗？谢谢！

[lihuangtsai]

Have you solved the problem?

Thanks