ValueError: `MessagePassing.propagate` only supports `torch.LongTensor` of shape `[2, num_messages]` or `torch_sparse.SparseTensor` for argument `edge_index`.

[vrjmath]

====epoch 1 Iteration: 0%| | 0/38 [00:00<?, ?it/s] Traceback (most recent call last): File "/usr/scratch/vshitole6/Summer/pretraingnns/pretraingnns/chem/finetune.py", line 232, in main() File "/usr/scratch/vshitole6/Summer/pretraingnns/pretraingnns/chem/finetune.py", line 204, in main train(args, model, device, train_loader, optimizer) File "/usr/scratch/vshitole6/Summer/pretraingnns/pretraingnns/chem/finetune.py", line 32, in train pred = model(batch.x, batch.edge_index, batch.edge_attr, batch.batch) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/anaconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/anaconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/Summer/pretraingnns/pretraingnns/chem/model.py", line 367, in forward node_representation = self.gnn(x, edge_index, edge_attr) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/anaconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/anaconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/Summer/pretraingnns/pretraingnns/chem/model.py", line 268, in forward h = self.gnns[layer](h_list[layer], edge_index, edge_attr) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/anaconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/anaconda3/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/Summer/pretraingnns/pretraingnns/chem/model.py", line 49, in forward return self.propagate(self.aggr, edge_index, x=x, edge_attr=edge_embeddings) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/anaconda3/lib/python3.11/site-packages/torch_geometric/nn/conv/message_passing.py", line 216, in propagate size = self.check_input(edge_index, size) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/scratch/vshitole6/anaconda3/lib/python3.11/site-packages/torch_geometric/nn/conv/message_passing.py", line 110, in check_input raise ValueError( ValueError: MessagePassing.propagate only supports torch.LongTensor of shape [2, num_messages] or torch_sparse.SparseTensor for argument edge_index.