-
Notifications
You must be signed in to change notification settings - Fork 10
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
pointops_cuda error #12
Comments
I have the same issue |
This is a common issue. If you have complied it and had error message: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E |
You see, I used pytorch 1.12 cuda 11.6 2080ti to run the code, and cd to extensions/pointops and run python setup,py install, but this error still occurs. |
If you cannot compile it, you can use the pre-build wheel. Please refer to
Another option is to use pure-PyTorch operations to replace the fps and gather KNN operations. You can refer to
|
谢谢您 |
I have installed everything separately as requirements.txt is not valid anymore. I am facing problem while trying to train the model. please help me to solve it.
from models.transformer import Group
File "/home/amandal2023/Desktop/deep_learning3d/Partial2Complete/models/transformer.py", line 6, in
from extensions.pointops.functions import pointops
File "/home/amandal2023/Desktop/deep_learning3d/Partial2Complete/extensions/pointops/functions/pointops.py", line 4, in
import pointops_cuda
ModuleNotFoundError: No module named 'pointops_cuda'
The text was updated successfully, but these errors were encountered: