IndexError: list index out of range

[youngfish42]

When run python prepare_dataset.py
ONCE CONV =GIN and MINIBATCH =NeighborSampler
Regardless of the real-world dataset used, I got the following error message

Using device: cuda
GeForce GTX 1080
Graph density 0.030438832087358775
Data(edge_index=[2, 3238174], num_classes=1, test_mask=[3238174], train_mask=[3238174], val_mask=[3238174], x=[14587, 14587], y=[3238174])
{'batch_size': 512, 'hidden': 128, 'output': 64, 'lr': 0.001, 'wd': 0.0005, 'nb_size': -1, 'dropout': 0.4}
Traceback (most recent call last):
File "prepare_dataset.py", line 831, in
main()
File "prepare_dataset.py", line 827, in main
if config.GENERATE_NODE_EMB: train_node_emb.generate_emb()
File "/data/usr/XXX/SubGNN/prepare_dataset/train_node_emb.py", line 160, in generate_emb
model = mdl.TrainNet(all_data.x.shape[1], curr_hyperparameters['hidden'], curr_hyperparameters['output'], config.CONV.lower().split("_")[1], curr_hyperparameters['dropout']).to(device)
IndexError: list index out of range

However, when CONV = graphsaint_gcn and MINIBATCH = GraphSaint, that's all right.

[hoangntc]

When run python prepare_dataset.py ONCE CONV =GIN and MINIBATCH =NeighborSampler Regardless of the real-world dataset used, I got the following error message

Using device: cuda GeForce GTX 1080 Graph density 0.030438832087358775 Data(edge_index=[2, 3238174], num_classes=1, test_mask=[3238174], train_mask=[3238174], val_mask=[3238174], x=[14587, 14587], y=[3238174]) {'batch_size': 512, 'hidden': 128, 'output': 64, 'lr': 0.001, 'wd': 0.0005, 'nb_size': -1, 'dropout': 0.4} Traceback (most recent call last): File "prepare_dataset.py", line 831, in main() File "prepare_dataset.py", line 827, in main if config.GENERATE_NODE_EMB: train_node_emb.generate_emb() File "/data/usr/XXX/SubGNN/prepare_dataset/train_node_emb.py", line 160, in generate_emb model = mdl.TrainNet(all_data.x.shape[1], curr_hyperparameters['hidden'], curr_hyperparameters['output'], config.CONV.lower().split("_")[1], curr_hyperparameters['dropout']).to(device) IndexError: list index out of range

However, when CONV = graphsaint_gcn and MINIBATCH = GraphSaint, that's all right.

Hi, I got into the same problem. Do you know how to fix it?

[youngfish42]

When run python prepare_dataset.py ONCE CONV =GIN and MINIBATCH =NeighborSampler Regardless of the real-world dataset used, I got the following error message
Using device: cuda GeForce GTX 1080 Graph density 0.030438832087358775 Data(edge_index=[2, 3238174], num_classes=1, test_mask=[3238174], train_mask=[3238174], val_mask=[3238174], x=[14587, 14587], y=[3238174]) {'batch_size': 512, 'hidden': 128, 'output': 64, 'lr': 0.001, 'wd': 0.0005, 'nb_size': -1, 'dropout': 0.4} Traceback (most recent call last): File "prepare_dataset.py", line 831, in main() File "prepare_dataset.py", line 827, in main if config.GENERATE_NODE_EMB: train_node_emb.generate_emb() File "/data/usr/XXX/SubGNN/prepare_dataset/train_node_emb.py", line 160, in generate_emb model = mdl.TrainNet(all_data.x.shape[1], curr_hyperparameters['hidden'], curr_hyperparameters['output'], config.CONV.lower().split("_")[1], curr_hyperparameters['dropout']).to(device) IndexError: list index out of range
However, when CONV = graphsaint_gcn and MINIBATCH = GraphSaint, that's all right.

Hi, I got into the same problem. Do you know how to fix it?

YES，I have fixed it.

In ”SubGNN/prepare_dataset/train_node_emb.py", line 160
change
model = mdl.TrainNet(all_data.x.shape[1], curr_hyperparameters['hidden'], curr_hyperparameters['output'],config.CONV.lower().split("_")[1], curr_hyperparameters['dropout']).to(device)

with
model = mdl.TrainNet(all_data.x.shape[1], curr_hyperparameters['hidden'], curr_hyperparameters['output'],config.CONV.lower().split("_")[-1], curr_hyperparameters['dropout']).to(device)