Stack Smashing Detected Error

[Glanceyes]

Thank you for your detailed explanation.

I have an additional question regarding an error encountered while running train_feat_gaussian.py to lift 2D features into 3D Gaussians.

I receive the following error: *** stack smashing detected ***: terminated. And I find that the issue arises when calling the distCUDA2 function defined in the simple-knn submodule. It seems that the code might be accessing memory outside the stack.

As I suspected this might be due to my environment setup, I followed the instructions provided in the README and re-ran the code on my local machine. However, the error persists again.

Could you please provide advice on how to resolve this issue?

Thanks.

[Glanceyes]

I managed to solve the issue. It seems that the problem is related to using an incompatible CUDA version within my virtual environment.

For anyone who encounters the same issue, the following commands might help:

conda create -n fit3d python=3.8 #
conda activate fit3d
conda install -c "nvidia/label/cuda-11.7.0" cuda-nvcc
conda install cuda-toolkit==11.7
pip install ninja
pip install cmake

conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia

pip install submodules/diff-feature-gaussian-rasterization
pip install submodules/simple-knn

pip install -r requirements.txt