flags.DEFINE_float('learning_rate', 0.01, 'Initial learning rate.')
flags.DEFINE_integer('epochs', 200, 'Number of epochs to train.')
flags.DEFINE_integer('hidden1', 32, 'Number of units in hidden layer 1.')
flags.DEFINE_integer('hidden2', 16, 'Number of units in hidden layer 2.')
flags.DEFINE_float('weight_decay', 0., 'Weight for L2 loss on embedding matrix.')
flags.DEFINE_float('dropout', 0., 'Dropout rate (1 - keep probability).')
flags.DEFINE_string('model', 'gcn_ae', 'Model string.')
flags.DEFINE_string('dataset', 'cora', 'Dataset string.')
flags.DEFINE_integer('features', 1, 'Whether to use features (1) or not (0).')
model_str = FLAGS.model
dataset_str = FLAGS.dataset
# Load data
adj, features = load_data(dataset_str)
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix((adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
adj = adj_train
if FLAGS.features == 0:
features = sp.identity(features.shape[0]) # featureless
# Some preprocessing
adj_norm = preprocess_graph(adj)
flags.DEFINE_integer('epochs', 200, 'Number of epochs to train.')
flags.DEFINE_integer('hidden1', 32, 'Number of units in hidden layer 1.')
flags.DEFINE_integer('hidden2', 16, 'Number of units in hidden layer 2.')
flags.DEFINE_float('weight_decay', 0., 'Weight for L2 loss on embedding matrix.')
flags.DEFINE_float('dropout', 0., 'Dropout rate (1 - keep probability).')
flags.DEFINE_string('model', 'gcn_vae', 'Model string.')
flags.DEFINE_string('dataset', 'cora', 'Dataset string.')
flags.DEFINE_integer('features', 1, 'Whether to use features (1) or not (0).')
flags.DEFINE_string("checkpoint_dir", "checkpoints", "checkpoint directory")
model_str = FLAGS.model
dataset_str = FLAGS.dataset
# Load data
adj, features = load_data(dataset_str)
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix((adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros()
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(adj)
adj = adj_train
if FLAGS.features == 0:
features = sp.identity(features.shape[0]) # featureless
# Some preprocessing
adj_norm = preprocess_graph(adj)
flags.DEFINE_string('model', 'gcn_ae', 'Model string.')
flags.DEFINE_string('dataset', 'hamster', 'Dataset string.')
flags.DEFINE_integer('datatype', 1, 'Datatype.')
flags.DEFINE_integer('features', 0, 'Whether to use features (1) or not (0).')
#datasets = [0, 107, 1684, 1912, 3437, 348, 3980, 414, 686, 698, 'facebook', 'twitter', 'gplus', 'hamster', 'advogato']
datasets = [348]
for dataset_str in datasets:
model_str = FLAGS.model
dataset_str = str(dataset_str)
# dataset_str = FLAGS.dataset
dataset_type = FLAGS.datatype
# Load data
adj, features = load_data(dataset_str, dataset_type)
# Store original adjacency matrix (without diagonal entries) for later
adj_orig = adj
adj_orig = adj_orig - sp.dia_matrix(
(adj_orig.diagonal()[np.newaxis, :], [0]), shape=adj_orig.shape)
adj_orig.eliminate_zeros() # 消除0元素
adj_train, train_edges, val_edges, val_edges_false, test_edges, test_edges_false = mask_test_edges(
adj)
adj = adj_train
if FLAGS.features == 0:
features = sp.identity(features.shape[0]) # featureless
# Some preprocessing
adj_norm = preprocess_graph(adj)