models.py [59:73]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if True:  # center pooling
            _, center_indices = np.unique(batch.cpu().numpy(), return_index=True)
            x_src = x[center_indices]
            x_dst = x[center_indices + 1]
            x = (x_src * x_dst)
            x = F.relu(self.lin1(x))
            x = F.dropout(x, p=self.dropout, training=self.training)
            x = self.lin2(x)
        else:  # sum pooling
            x = global_add_pool(x, batch)
            x = F.relu(self.lin1(x))
            x = F.dropout(x, p=self.dropout, training=self.training)
            x = self.lin2(x)

        return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



models.py [119:133]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if True:  # center pooling
            _, center_indices = np.unique(batch.cpu().numpy(), return_index=True)
            x_src = x[center_indices]
            x_dst = x[center_indices + 1]
            x = (x_src * x_dst)
            x = F.relu(self.lin1(x))
            x = F.dropout(x, p=self.dropout, training=self.training)
            x = self.lin2(x)
        else:  # sum pooling
            x = global_add_pool(x, batch)
            x = F.relu(self.lin1(x))
            x = F.dropout(x, p=self.dropout, training=self.training)
            x = self.lin2(x)

        return x
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -