zknus / ICLR2024-FROND

Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND
4 stars 1 forks source link

Details of env #1

Open MohsenFazaeli opened 1 month ago

MohsenFazaeli commented 1 month ago

Hi,

I'm trying to set up the environment to run your code and learn more about it. I'm encountering errors during installation, specifically related to the llvm-openmp package.

Could you please provide some information about the environment used for developing the code? This might include:

Operating System: (e.g., Windows 10, Ubuntu 18.04) Python Version: (e.g., Python 3.7) Conda environment details: (If a specific conda environment was used) Versions of key dependencies: (Particularly llvm-openmp if known) This information would be very helpful in troubleshooting the installation issues I'm facing.

Thank you for your time and for sharing your work!

Sincerely, Mohsen

hizening commented 1 month ago

Hello, I also encountered the same problem when configuring the environment. Have you found the correct version?

zknus commented 1 week ago

Dear @MohsenFazaeli and @hizening,

Below is the Python environment setup I used, which you may find useful for reference. Based on my experience, the critical dependencies of this code include torch-geometric and its related packages (torch-scatter, torch-sparse, torch-spline-conv, and torch-cluster). Please follow the instructions at PyTorch Geometric Installation Guide.

  1. Install PyTorch appropriate for your CUDA version.
  2. Install the required packages based on your torch and CUDA version by using the command:
    
    pip install pyg_lib torch_scatter torch_sparse torch_cluster torch_spline_conv -f https://data.pyg.org/whl/torch-${TORCH}+${CUDA}.html  
  3. Finally, install torch-geometric.
    
    pip install torch_geometric
    Other packages should be straightforward to install. Please let me know if you have any other questions.

Operating System:

Python Version:

Package Manager:

Python Packages: