Expand_as RuntimeError in torch_scatter!!!

[tjb-tech]

Hi, I am inheritanting Messagepassing in pytorch_geometric to create my own graph conv, but I face the error below. To be exact, it occurs in function propagate, and I sent edge_index (2, edge_num) and x (num_node, 128) into propagate. And I try my code on both linux and win. And they occurred the same problems. Note that I use the famous dataset Cora use the code dataset = Planetoid(path, 'Cora', transform=T.NormalizeFeatures())
linux:

Win:

BTW, linux is py3.8 and Win is py3.7.

[rusty1s]

Thanks for reporting. It looks like your node feature matrix is three-dimensional. In that case, you should set super().__init__(aggr=.., node_dim=0) in your MessagePassing constructor.

[tjb-tech]

Thanks a lot for replying!