Hi! Thanks for sharing the code. The data loader raises an AttributeError when I run the code in unsupervised_TU. It seems that the data in the Batch is a tuple (data and data_aug):
(Data(edge_attr=[38, 4], edge_index=[2, 54], x=[17, 7], y=[1]), Data(edge_attr=[38, 4], edge_index=[2, 54], x=[17, 1], y=[1]))
But in the source code of torch geometric, the data is used as "keys = [set(data.keys) for data in data_list]". This raises the error:
AttributeError: 'tuple' object has no attribute 'keys'.
Could you please help me with this bug? The version of my torch geometric is 1.3.2. Thanks!
Hi! Thanks for sharing the code. The data loader raises an AttributeError when I run the code in unsupervised_TU. It seems that the data in the Batch is a tuple (data and data_aug):
(Data(edge_attr=[38, 4], edge_index=[2, 54], x=[17, 7], y=[1]), Data(edge_attr=[38, 4], edge_index=[2, 54], x=[17, 1], y=[1])) But in the source code of torch geometric, the data is used as "keys = [set(data.keys) for data in data_list]". This raises the error:
AttributeError: 'tuple' object has no attribute 'keys'.
Could you please help me with this bug? The version of my torch geometric is 1.3.2. Thanks!