Pytorch geometric collate issue

1

File “/home/ubuntu/Desktop/new_origami/Origami/origami/data/utils.py”, line 91, in
collated_data_dict = { ligand_id : collate(data_list = list(data_dict[ligand_id]),cls=PairData,follow_batch=[‘atom_type_1’, ‘atom_type_2’])
File “/home/ubuntu/anaconda3/envs/origami/lib/python3.9/site-packages/torch_geometric/data/collate.py”, line 32, in collate
out = cls(_base_cls=data_list[0].class) # Dynamic inheritance.
TypeError: init() got an unexpected keyword argument ‘_base_cls’

I am trying to collate data based on the an id. the data is a bipartite graph, where ids can be repetative.
Pytorch geometric version is 2.0.4.

2

Could it be because of versions or something else? Any help is appreciated.

3

I’m not sure _base_cls was ever a keyword argument of collate: see an example usage of collate here: torch_geometric.data.batch — pytorch_geometric documentation (pytorch-geometric.readthedocs.io)