Will ReLU be ever called for single dimensional node_state_dim?

[tsjain]

Since the default configuration of node_hidden_sizes is a vector of length 1, will the layers in the for loop on lines 38:40 ever get created?

Graph-Matching-Networks/GMN/graphembeddingnetwork.py

Line 38 in f63c575

for i in range(1, len(self._node_hidden_sizes)):

[Lin-Yijie]

No, won’t be created. If node_hidden_sizes is a vector of length 1, it will be only added on line 37.

Graph-Matching-Networks/GMN/graphembeddingnetwork.py

Line 37 in f63c575

layer.append(nn.Linear(self._node_feature_dim, self._node_hidden_sizes[0]))