Thank you for your great work.
When I followed the method in the previous issue to implement feature extraction for pdb files, I encountered the following problem.
Traceback (most recent call last): File "script\tcr_extract.py", line 48, in <module> output = gearnet_edge(protein, protein.node_feature.float(), all_loss=None, metric=None) File "C:\Users\mercy\anaconda3\envs\proj_v1\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "C:\Users\mercy\anaconda3\envs\proj_v1\lib\site-packages\torchdrug\models\gearnet.py", line 95, in forward hidden = self.layers[i](graph, layer_input) File "C:\Users\mercy\anaconda3\envs\proj_v1\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl return forward_call(*input, **kwargs) File "C:\Users\mercy\anaconda3\envs\proj_v1\lib\site-packages\torchdrug\layers\conv.py", line 91, in forward update = self.message_and_aggregate(graph, input) File "C:\Users\mercy\anaconda3\envs\proj_v1\lib\site-packages\torchdrug\layers\conv.py", line 813, in message_and_aggregate return update.view(graph.num_node, self.num_relation * self.input_dim) RuntimeError: shape '[31, 147]' is invalid for input of size 651
I used exactly the same code as in the issue, just modified the pthfile to mc_gearnet_edge.pth. The error appears on the last line.
output = gearnet_edge(protein, protein.node_feature.float(), all_loss=None, metric=None)
The pdb file I used had 31 residues. In this error, I guessed that 651 of them were 31*21. But I don't know why this is the case. I hope I can get some help. I have been troubled by this problem for a week. Thanks for all.