JRowbottomGit
commented
2 years ago Hi Abdullah,
The code definitely won’t run with pytorch geometric >= 2.0.0.
There were many changes. See here for release notes https://github.com/pyg-team/pytorch_geometric/releases.
Two things to check:
- Are you installing both torch and torch_geometric with pip inside a conda environment?
- Was the dataset = Planetoid(path, ds) installed with torch-geometric==1.7.0 or torch-geometric==2.0.2. If it’s the latter, delete the folder and rerun script to reimport. This is my suspicion as the error comes from the torch.load command.
Good luck!
James
From: Abdullah @.> Sent: 07 December 2021 21:57 To: twitter-research/graph-neural-pde @.> Cc: Subscribed @.***> Subject: [twitter-research/graph-neural-pde] python run_GNN.py --dataset Cora (Issue #8)
Hello,
When I run python run_GNN.py --dataset Cora , it creates the following error.
Traceback (most recent call last): File "run_GNN.py", line 401, in main(opt) File "run_GNN.py", line 190, in main dataset = get_dataset(opt, '../data', opt['not_lcc']) File "/home/saydemr/Documents/graph-neural-pde/src/data.py", line 36, in get_dataset dataset = Planetoid(path, ds) File "/home/saydemr/anaconda3/envs/grand/lib/python3.7/site-packages/torch_geometric/datasets/planetoid.py", line 56, in init self.data, self.slices = torch.load(self.processed_paths[0]) File "/home/saydemr/anaconda3/envs/grand/lib/python3.7/site-packages/torch/serialization.py", line 592, in load return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args) File "/home/saydemr/anaconda3/envs/grand/lib/python3.7/site-packages/torch/serialization.py", line 851, in _load result = unpickler.load() ModuleNotFoundError: No module named 'torch_geometric.data.storage'
System : Ubuntu 20.04 Torch : 1.8.1+cu102 Cuda : release 10.2, V10.2.89 torch-geometric==1.7.0
On torch-geometric==2.0.2 however, this error turns into the following
Traceback (most recent call last): File "run_GNN.py", line 401, in main(opt) File "run_GNN.py", line 202, in main model = GNN(opt, dataset, device).to(device) if opt["no_early"] else GNNEarly(opt, dataset, device).to(device) File "/home/saydemr/Documents/graph-neural-pde/src/GNN_early.py", line 25, in init self.odeblock = block(self.f, self.regularization_fns, opt, dataset.data, device, t=time_tensor).to(device) File "/home/saydemr/Documents/graph-neural-pde/src/block_transformer_attention.py", line 16, in init dtype=data.x.dtype) File "/home/saydemr/Documents/graph-neural-pde/src/utils.py", line 113, in get_rw_adj edge_index, edge_weight, fill_value, num_nodes) File "/home/saydemr/anaconda3/envs/grand/lib/python3.7/site-packages/torch_geometric/utils/loop.py", line 220, in add_remaining_self_loops raise AttributeError("No valid 'fill_value' provided") AttributeError: No valid 'fill_value' provided
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/twitter-research/graph-neural-pde/issues/8 , or unsubscribe https://github.com/notifications/unsubscribe-auth/APWNPYOPHSYJDPONDAKEPMDUPZ7KBANCNFSM5JSJENJQ . https://github.com/notifications/beacon/APWNPYIBRTCGWBHTXLA7ZZ3UPZ7KBA5CNFSM5JSJENJ2YY3PNVWWK3TUL52HS4DFUVEXG43VMWVGG33NNVSW45C7NFSM4QAAV3CQ.gif
Saydemr
Hello,
When I run
python run_GNN.py --dataset Cora, it creates the following error.Traceback (most recent call last): File "run_GNN.py", line 401, in
main(opt)
File "run_GNN.py", line 190, in main
dataset = get_dataset(opt, '../data', opt['not_lcc'])
File "/home/saydemr/Documents/graph-neural-pde/src/data.py", line 36, in get_dataset
dataset = Planetoid(path, ds)
File "/home/saydemr/anaconda3/envs/grand/lib/python3.7/site-packages/torch_geometric/datasets/planetoid.py", line 56, in init
self.data, self.slices = torch.load(self.processed_paths[0])
File "/home/saydemr/anaconda3/envs/grand/lib/python3.7/site-packages/torch/serialization.py", line 592, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/home/saydemr/anaconda3/envs/grand/lib/python3.7/site-packages/torch/serialization.py", line 851, in _load
result = unpickler.load()
ModuleNotFoundError: No module named 'torch_geometric.data.storage'
System : Ubuntu 20.04 Torch : 1.8.1+cu102 Cuda : release 10.2, V10.2.89 torch-geometric==1.7.0
On torch-geometric==2.0.2 however, this error turns into the following
Traceback (most recent call last): File "run_GNN.py", line 401, in
main(opt)
File "run_GNN.py", line 202, in main
model = GNN(opt, dataset, device).to(device) if opt["no_early"] else GNNEarly(opt, dataset, device).to(device)
File "/home/saydemr/Documents/graph-neural-pde/src/GNN_early.py", line 25, in init
self.odeblock = block(self.f, self.regularization_fns, opt, dataset.data, device, t=time_tensor).to(device)
File "/home/saydemr/Documents/graph-neural-pde/src/block_transformer_attention.py", line 16, in init
dtype=data.x.dtype)
File "/home/saydemr/Documents/graph-neural-pde/src/utils.py", line 113, in get_rw_adj
edge_index, edge_weight, fill_value, num_nodes)
File "/home/saydemr/anaconda3/envs/grand/lib/python3.7/site-packages/torch_geometric/utils/loop.py", line 220, in add_remaining_self_loops
raise AttributeError("No valid 'fill_value' provided")
AttributeError: No valid 'fill_value' provided