search

lightaime / deep_gcns_torch

Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org
MIT License
1.14k stars 155 forks source link

TypeError: getattr(): attribute name must be string #6

Closed hengliangzhu closed 5 years ago

hengliangzhu commented 5 years ago

Thank you for your good work！ But when training，i get some errors

Traceback (most recent call last): File "sem_seg/train.py", line 141, in main() File "sem_seg/train.py", line 61, in main train(model, train_loader, optimizer, scheduler, criterion, opt) File "sem_seg/train.py", line 81, in train out = model(data) File "/root/anaconda3/envs/deepgcn37/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in call result = self.forward(*input, **kwargs) File "/media/dgdr250/hd/hyydown/deep_gcns_torch/models/architecture.py", line 105, in forward feats = [self.head(inputs, self.knn(inputs[:, 0:3]))] File "/root/anaconda3/envs/deepgcn37/lib/python3.7/site-packages/torch_geometric/data/data.py", line 92, in getitem return getattr(self, key, None) TypeError: getattr(): attribute name must be string

Can you kindly tell me how to solve it? Many thanks!!!

guochengqian commented 5 years ago

@hengliangzhu Thanks for pointing out the issue. We just notice this is the issue with the sparse data format. I already push the new code, please check.

guochengqian commented 5 years ago

@hengliangzhu Hello. I believe the bug is fixed now.

hengliangzhu commented 5 years ago

Thank you very much, i will have a try....