search

nnzhan / MTGNN

MIT License
762 stars 216 forks source link

train multistep #25

Open zhilonglu opened 3 years ago

zhilonglu commented 3 years ago

when data prepared, and i try to run train_multi_step and modify the corresponding parameters, there is an error occurs.

MTGNN/layer.py", line 187, in forward s1,t1 = adj.topk(self.k,1) RuntimeError: invalid argument 5: k not in range for dimension at /tmp/pip-req-build 4baxydiv/aten/src/THC/generic/THCTensorTopK.cu:23

How to fix it?

zhilonglu commented 3 years ago

I try to modify subgraph_size to less than 5, for example ,used 4.