gammagl.models.GCNModel

class GCNModel(feature_dim, hidden_dim, num_class, drop_rate=0.2, num_layers=2, norm='both', name=None)

Graph Convolutional Network proposed in “Semi-supervised Classification with Graph Convolutional Networks” paper.

Parameters:

• feature_dim (int) – input feature dimension.

• hidden_dim (int) – hidden dimension.

• num_class (int) – number of classes.

• drop_rate (float, optional) – dropout rate.

• num_layers (int, optional) – number of layers.

• norm (str, optional) – apply the normalizer.

• name (str, optional) – model name.

forward(x, edge_index, edge_weight, num_nodes)