YingtongDou
commented
1 year ago The error might be due to the pyg dataloader version inconsistency. You can try to load the dataset like the pyg official example or install pyg 1.6.1 instead of 2.0+ version.
/usr/local/bin/python3.10 /Users/mac/PycharmProjects/gnnFakeNews/gnn_model/gnn.py dataset>> politifact(314) args>> Namespace(seed=777, device='cpu', dataset='politifact', batch_size=128, lr=0.01, weight_decay=0.01, nhid=128, dropout_ratio=0.0, epochs=35, concat=True, multi_gpu=False, feature='bert', model='sage') Traceback (most recent call last): File "/Users/mac/PycharmProjects/gnnFakeNews/gnn_model/gnn.py", line 119, in
args.num_classes = dataset.num_classes
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch_geometric/data/in_memory_dataset.py", line 66, in num_classes
return super().num_classes
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch_geometric/data/dataset.py", line 159, in num_classes
data_list = _get_flattened_data_list([data for data in self])
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch_geometric/data/dataset.py", line 159, in
data_list = _get_flattened_data_list([data for data in self])
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch_geometric/data/dataset.py", line 259, in getitem
data = data if self.transform is None else self.transform(data)
File "/Users/mac/PycharmProjects/gnnFakeNews/utils/data_loader.py", line 89, in call
edge_index = to_undirected(data.edge_index, data.x.size(0))
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torch_geometric/utils/undirected.py", line 173, in to_undirected
return coalesce(edge_index, edge_attr, num_nodes, reduce)
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/torchgeometric/utils/coalesce.py", line 99, in coalesce
idx[1:].mul(numnodes).add(edge_index[int(sort_byrow)])
TypeError: mul(): argument 'other' (position 1) must be Tensor, not str
Process finished with exit code 1