-
Notifications
You must be signed in to change notification settings - Fork 212
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
The question about function create_compressed_model():RuntimeError: CUDA error: device-side assert triggered #2688
Comments
HI @zbnlala |
HI @AlexanderDokuchaev. Sure! the model architecture is described in Finally , run the script will cause the bug However, if I run script with extra --cpu-only, there will no bug.(CUDA version 12.3)
|
@zbnlala unfortunately this issue is not reproduced. Could you check that issue is not reproduced without nncf? |
🐛 Describe the bug
Hi, I want to ask about the quantization of the non-neural network parts in the neural network.
I want to realize the quantization of the PointNet-based network to deal with classification tasks
The other part of the network are just some conv1d and relu function. Then I modified the train function with
changed dataset and evaluation method. However the error occurred . Can you help me fix this problem?
This is the error information:
Environment
nccf==2.10.0
pytorch==2.2.2
python==3.9
Minimal Reproducible Example
The non-neural network parts of the network is as follow:
The text was updated successfully, but these errors were encountered: