IndexError: too many indices for tensor of dimension 1

[Jack-Lin-gif]

Thanks for sharing your great code!
I'm trying to run your sample code:

python seal_link_pred.py --dataset ogbl-ppa --num_hops 1 --use_feature --use_edge_weight --eval_steps 5 --epochs 20 --dynamic_train --dynamic_val --dynamic_test --train_percent 5

there is an 'IndexError':

Traceback (most recent call last): File "<string>", line 1, in <module> File "/opt/anaconda3/envs/seal2/lib/python3.8/multiprocessing/spawn.py", line 116, in spawn_main exitcode = _main(fd, parent_sentinel) File "/opt/anaconda3/envs/seal2/lib/python3.8/multiprocessing/spawn.py", line 125, in _main prepare(preparation_data) File "/opt/anaconda3/envs/seal2/lib/python3.8/multiprocessing/spawn.py", line 236, in prepare _fixup_main_from_path(data['init_main_from_path']) File "/opt/anaconda3/envs/seal2/lib/python3.8/multiprocessing/spawn.py", line 287, in _fixup_main_from_path main_content = runpy.run_path(main_path, File "/opt/anaconda3/envs/seal2/lib/python3.8/runpy.py", line 265, in run_path return _run_module_code(code, init_globals, run_name, File "/opt/anaconda3/envs/seal2/lib/python3.8/runpy.py", line 97, in _run_module_code _run_code(code, mod_globals, init_globals, File "/opt/anaconda3/envs/seal2/lib/python3.8/runpy.py", line 87, in _run_code exec(code, run_globals) File "/Users/shanghanglin/SEAL_OGB/seal_link_pred.py", line 702, in <module> loggers[key].print_statistics() File "/Users/shanghanglin/SEAL_OGB/utils.py", line 364, in print_statistics valid = r[:, 0].max().item() IndexError: too many indices for tensor of dimension 1

Could you please help me with that? Thank you!

[muhanzhang]

Hi! Can you let me know which versions of PyTorch, PyG, OGB you used? Thanks.

[Jack-Lin-gif]

Thanks for your reply.

PyTouch: 1.6.0
PyG: 2.0.1
OGB: 1.2.4

[Jack-Lin-gif]

I just can’t find a way to install a specific version of PyG...like your version of 1.6.1. Could you help me?

[muhanzhang]

Hi! I have tested the repo with PyTorch 1.9.0, OGB 1.3.1 and PyG 2.0.2. Maybe your OGB version is too old. Can you update it by "pip install -U ogb"?