-
Notifications
You must be signed in to change notification settings - Fork 52
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
.cpython-37m-x86_64-linux-gnu.so: undefined symbol: #11
Comments
Please provide more details about your environment and what you are trying to do. Unfortunately that error message alone is not nearly enough to understand what is going on. |
Hello, I met the same error while I was trying to run the inference with the provided pre-trained model (res50). Traceback (most recent call last): It seems like when we import _backend which is a cpython compiled file. There is some function definition missing. This is what I did : python -m torch.distributed.launch --nproc_per_node=1 test_panoptic.py --meta ../model/metadata.bin --log_dir ../log/ ../model/config.ini ../model/seamseg_r50_vistas.tar /imgs/ ../output/ The requirements are met. I have: Thanks, if you could help |
hey @HaoLIU94 i am also having same issue have you solved it thanks |
I wasn't able to use this project anyways. |
/home/qujiangang/conda/lib/python3.7/site-packages/seamseg/utils/bbx/_backend.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E
The text was updated successfully, but these errors were encountered: