def __init__(self): super(Net, self).__init__() self.conv1 = GraphConv(dataset.num_features, 32) self.conv2 = GraphConv(32, 64) self.conv3 = GraphConv(64, 64) self.fc1 = torch.nn.Linear(64, 64) self.fc2 = torch.nn.Linear(64, 32) self.fc3 = torch.nn.Linear(32, dataset.num_classes)
def __init__(self): super(Net, self).__init__() # This is the update step self.conv1 = GraphConv(dataset.num_features, 32) self.conv2 = GraphConv(32, 64) self.conv3 = GraphConv(64, 64) # The transforms the update step into something usable self.fc1 = torch.nn.Linear(64, 64) self.fc2 = torch.nn.Linear(64, 32) self.fc3 = torch.nn.Linear(32, dataset.num_classes)
def __init__(self): super(Net, self).__init__() M_in, M_out = dataset.num_features, 32 nn1 = Sequential(Linear(5, 128), ReLU(), Linear(128, M_in * M_out)) self.conv1 = NNConv(M_in, M_out, nn1) M_in, M_out = M_out, 64 nn2 = Sequential(Linear(5, 128), ReLU(), Linear(128, M_in * M_out)) self.conv2 = NNConv(M_in, M_out, nn2) M_in, M_out = M_out, 64 nn3 = Sequential(Linear(5, 128), ReLU(), Linear(128, M_in * M_out)) self.conv3 = NNConv(M_in, M_out, nn3) self.conv6 = GraphConv(64 + num_i_3, 64) self.conv7 = GraphConv(64, 64) self.fc1 = torch.nn.Linear(2 * 64, 64) self.fc2 = torch.nn.Linear(64, 32) self.fc3 = torch.nn.Linear(32, 1)
def __init__(self,config,args): super(Net, self).__init__() self.conv1 = GraphConv(config.num_features, 64) self.conv2 = GraphConv(64, 64) self.conv3 = GraphConv(64, 64) self.conv4 = GraphConv(64 + config.num_i_2, 64) self.conv5 = GraphConv(64, 64) self.conv6 = GraphConv(64 + config.num_i_3, 64) self.conv7 = GraphConv(64, 64) self.fc1 = torch.nn.Linear(3 * 64, 64) self.fc2 = torch.nn.Linear(64, 32) self.fc3 = torch.nn.Linear(32, 1) if args.type=="TU": self.fc3 = torch.nn.Linear(32, config.num_classes) self.args=args self.sigmoid = nn.Sigmoid()