HannesStark/3DInfomax
Making self-supervised learning work on molecules by using their 3D geometry to pre-train GNNs. Implemented in DGL and Pytorch Geometric.
Python
Issues
- 1
RuntimeError: Error(s) in loading state_dict for PNA: size mismatch for node_gnn.atom_encoder.atom_embedding_list.1.weight: copying a param with shape torch.Size([4, 200]) from checkpoint, the shape in current model is torch.Size([5, 200]).
#19 opened by chushuang203 - 4
pretrain loss with negative value
#18 opened by zhihuiY - 2
- 1
Embedding views in NTXentMultiplePositiveLoss
#15 opened by arunppsg - 1
"conda env create" problem
#17 opened by Gryff1ndor - 0
classification yml file
#20 opened by coderabbittank - 5
DglPCQM4MDataset ImportError for inference
#10 opened by jadolfbr - 1
Some questions about 3DInfomax
#13 opened by happyzhanglol - 1
- 1
Pretrained 3d model
#11 opened by ivandon15 - 1
Where is the "bbbpscaffold123.pkl"? And what is the "bbbpscaffold123.pkl"?
#9 opened by MianWang11111 - 1
What is the MAE of QM9? Which parameter in the following operation result is Mean Absolute Error? Thank you.
#8 opened by MianWang11111 - 4
What model is gin.py?
#7 opened by MianWang11111 - 4
- 2
ResolvePackageNotFound in Windows
#2 opened by MianWang11111 - 1
Linked video freezes
#5 opened by nfzd - 4
- 6
generating a fingerprint
#3 opened by rohanvarm - 5