Method __init__

gat/main.py:149–181

Initializes the GAT model. Args: in_features (int): number of input features per node. n_hidden (int): output size of the first Graph Attention Layer. n_heads (int): number of attention heads in the first Graph Attention Layer. num_classes (

(self,
        in_features,
        n_hidden,
        n_heads,
        num_classes,
        concat=False,
        dropout=0.4,
        leaky_relu_slope=0.2)

    And the second (final) layer is a GAT layer with a single attention head and softmax activation function. 
    """
    def __init__(self,
        in_features,
        n_hidden,
        n_heads,
        num_classes,
        concat=False,
        dropout=0.4,
        leaky_relu_slope=0.2):
        """ Initializes the GAT model. 

        Args:
            in_features (int): number of input features per node.
            n_hidden (int): output size of the first Graph Attention Layer.
            n_heads (int): number of attention heads in the first Graph Attention Layer.
            num_classes (int): number of classes to predict for each node.
            concat (bool, optional): Wether to concatinate attention heads or take an average over them for the
                output of the first Graph Attention Layer. Defaults to False.
            dropout (float, optional): dropout rate. Defaults to 0.4.
            leaky_relu_slope (float, optional): alpha (slope) of the leaky relu activation. Defaults to 0.2.
        """

        super(GAT, self).__init__()

        # Define the Graph Attention layers
        self.gat1 = GraphAttentionLayer(
            in_features=in_features, out_features=n_hidden, n_heads=n_heads,
            concat=concat, dropout=dropout, leaky_relu_slope=leaky_relu_slope
            )
        
        self.gat2 = GraphAttentionLayer(
            in_features=n_hidden, out_features=num_classes, n_heads=1,
            concat=False, dropout=dropout, leaky_relu_slope=leaky_relu_slope
            )
        

    def forward(self, input_tensor: torch.Tensor , adj_mat: torch.Tensor):