models.py: absolute import layers.GraphConvolution

The relative import statement fails when pygcn is installed and used as a package. Using the absolute import (like in train.py) lets the program be run in any context.
yuvalsimon · Oct 17, 2018 · ec1b125 · ec1b125
1 parent 5488806
commit ec1b125
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/pygcn/models.py b/pygcn/models.py
@@ -1,6 +1,6 @@
 import torch.nn as nn
 import torch.nn.functional as F
-from layers import GraphConvolution
+from pygcn.layers import GraphConvolution
 
 
 class GCN(nn.Module):