Issue with chemical dataset about geo-gcn HOT 3 OPEN

Hello!

I tried to run the code with chemical datasets. However there are always some dimension problems with the SpatialGraphConv layer. For instance I ran the 'freesolv' dataset and in the line 'aggr_out = self.lin_out(aggr_out' there is the problem. RuntimeError: mat1 and mat2 shapes cannot be multiplied (597x1600 and 64x64) Did you come across similar problem and do you have any idea how to solve it? Note that I used default parameters only and changed the train_model with the lines you suggested in Readme file.

By the way, I also wish to put edge_attr feature in the conv_layer. Could you point out where I can do so?

Thanks a lot. I'm trying to apply this to my current work :)

Hello, have you solved this issue?

I encountered the same error "RuntimeError: mat1 and mat2 shapes cannot be multiplied (2064x1600 and 64x16)" when I used other chemical datasets.

from geo-gcn.

parser.add_argument('--label_dim', type=int, default=25)

This may work with label_dim=25.

from geo-gcn.