Hi.
I am trying to run this repo with cpu.
OS/Distro : Ubuntu 22.04
Pytorch version : 2.3.0+cpu (1.8.0 is not longer supported as stable by Pytorch and downloading is made troublesome)
PyG version : https://data.pyg.org/whl/torch-2.3.0+cpu.html
Lightning : 2.4 (base install through pip).
Graphgym displayed version : 0.4.0
Followed install procedure of the README.md apart from using venv instead of conda.
Here is the returned error on bash run_single_cpu.sh call :
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.tx
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.allx
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.y
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.ty
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.ally
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.graph
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.test.index
Processing...
Done!
Traceback (most recent call last):
File "/home/oscar/Documents/WORK/internship-2025/GraphGym/run/main.py", line 37, in <module>
datasets = create_dataset()
File "/home/oscar/Documents/WORK/internship-2025/GraphGym/graphgym/loader.py", line 223, in create_dataset
graphs = load_dataset()
File "/home/oscar/Documents/WORK/internship-2025/GraphGym/graphgym/loader.py", line 109, in load_dataset
graphs = load_pyg(name, dataset_dir)
File "/home/oscar/Documents/WORK/internship-2025/GraphGym/graphgym/loader.py", line 72, in load_pyg
graphs = GraphDataset.pyg_to_graphs(dataset_raw)
File "/home/oscar/Documents/WORK/internship-2025/venv/lib/python3.10/site-packages/deepsnap/dataset.py", line 1276, in pyg_to_graphs
return [
File "/home/oscar/Documents/WORK/internship-2025/venv/lib/python3.10/site-packages/deepsnap/dataset.py", line 1277, in <listcomp>
Graph.pyg_to_graph(
File "/home/oscar/Documents/WORK/internship-2025/venv/lib/python3.10/site-packages/deepsnap/graph.py", line 1973, in pyg_to_graph
kwargs["node_feature"] = data.x if "x" in data.keys else None
TypeError: argument of type 'method' is not iterable
Would appreciate the help.
Thanks.
Hi.
I am trying to run this repo with cpu.
OS/Distro : Ubuntu 22.04
Pytorch version : 2.3.0+cpu (1.8.0 is not longer supported as stable by Pytorch and downloading is made troublesome)
PyG version : https://data.pyg.org/whl/torch-2.3.0+cpu.html
Lightning : 2.4 (base install through pip).
Graphgym displayed version : 0.4.0
Followed install procedure of the
README.mdapart from using venv instead of conda.Here is the returned error on
bash run_single_cpu.shcall :Would appreciate the help.
Thanks.