# edge_index has shape [2, E]
########################################################################
# START OF YOUR CODE (DO NOT DELETE/MODIFY THIS LINE) #
########################################################################
# Step 1: Add self-loops to the adjacency matrix.
edge_index = add_self_loops(edge_index, num_nodes=x.size(0))
# Step 2: Linearly transform node feature matrix.
x = self.lin(x)
# Step 3-5: Start propagating messages.
return self.propagate(edge_index=edge_index, x=x) # Problem occurs here
########################################################################
# END OF YOUR CODE #
######################################################################## `
the base class throws an error: ```
Exception has occurred: TypeError
Required parameter edge_index is empty.
When I try running the example code with the latest version of pytorch_geometric, I am seeing an error with edge_index and message passing.
Inside GCNConv ` def forward(self, x, edge_index):
x has shape [N, in_channels]
the base class throws an error: ``` Exception has occurred: TypeError Required parameter edge_index is empty.