def main(_):
flags_obj = tf.flags.FLAGS
euler_graph = tf_euler.dataset.get_dataset(flags_obj.dataset)
euler_graph.load_graph()
fanouts = list(map(int, flags_obj.fanouts))
assert flags_obj.layers == len(fanouts)
dims = [flags_obj.hidden_dim] * (flags_obj.layers + 1)
if flags_obj.run_mode == 'train':
metapath = [euler_graph.train_edge_type] * flags_obj.layers
else:
metapath = [euler_graph.all_edge_type] * flags_obj.layers
num_steps = int((euler_graph.total_size + 1) // flags_obj.batch_size *
flags_obj.num_epochs)
model = get_solution_model(conv=flags_obj.conv,
dataflow=flags_obj.flow,
dims=dims,
fanouts=fanouts,
metapath=metapath,
feature_idx=euler_graph.feature_idx,
feature_dim=euler_graph.feature_dim,
label_idx=euler_graph.label_idx,
label_dim=euler_graph.label_dim)
params = {
'train_node_type': euler_graph.train_node_type[0],
'batch_size': flags_obj.batch_size,
'optimizer': flags_obj.optimizer,
'learning_rate': flags_obj.learning_rate,
'log_steps': flags_obj.log_steps,
'model_dir': flags_obj.model_dir,
'id_file': euler_graph.id_file,
'infer_dir': flags_obj.model_dir,
'total_step': num_steps
}
config = tf.estimator.RunConfig(log_step_count_steps=None)
model_estimator = NodeEstimator(model, params, config)
if flags_obj.run_mode == 'train':
model_estimator.train()
elif flags_obj.run_mode == 'evaluate':
model_estimator.evaluate()
elif flags_obj.run_mode == 'infer':
model_estimator.infer()
else:
raise ValueError('Run mode not exist!')
def main(_):
flags_obj = tf.flags.FLAGS
euler_graph = tf_euler.dataset.get_dataset(flags_obj.dataset)
euler_graph.load_graph()
if flags_obj.run_mode == 'train':
metapath = [euler_graph.train_edge_type] * flags_obj.layers
else:
metapath = [euler_graph.all_edge_type] * flags_obj.layers
head_num = [flags_obj.num_heads] * flags_obj.layers
num_steps = int((euler_graph.total_size + 1) // flags_obj.batch_size *
flags_obj.num_epochs)
model = GeniePath(flags_obj.hidden_dim,
metapath,
euler_graph.label_idx,
euler_graph.label_dim,
max_id=euler_graph.max_node_id,
feature_idx=euler_graph.feature_idx,
feature_dim=euler_graph.feature_dim,
use_id=flags_obj.use_id,
embedding_dim=flags_obj.embedding_dim,
head_num=head_num)
params = {
'train_node_type': euler_graph.train_node_type[0],
'batch_size': flags_obj.batch_size,
'learning_rate': flags_obj.learning_rate,
'log_steps': flags_obj.log_steps,
'model_dir': flags_obj.model_dir,
'id_file': euler_graph.id_file,
'infer_dir': flags_obj.model_dir,
'total_step': num_steps
}
config = tf.estimator.RunConfig(log_step_count_steps=None)
model_estimator = NodeEstimator(model, params, config)
if flags_obj.run_mode == 'train':
model_estimator.train()
elif flags_obj.run_mode == 'evaluate':
model_estimator.evaluate()
elif flags_obj.run_mode == 'infer':
model_estimator.infer()
else:
raise ValueError('Run mode not exist!')
def main(_):
flags_obj = tf.flags.FLAGS
euler_graph = tf_euler.dataset.get_dataset(flags_obj.dataset)
euler_graph.load_graph()
dims = [flags_obj.hidden_dim, flags_obj.hidden_dim]
if flags_obj.run_mode == 'train':
metapath = [euler_graph.train_edge_type]
else:
metapath = [euler_graph.all_edge_type]
num_steps = int((euler_graph.total_size + 1) // flags_obj.batch_size *
flags_obj.num_epochs)
model = ARMA(dims,
metapath,
euler_graph.feature_idx,
euler_graph.feature_dim,
euler_graph.label_idx,
euler_graph.label_dim,
num_layers=flags_obj.layers,
K=flags_obj.K)
params = {
'train_node_type': euler_graph.train_node_type[0],
'batch_size': flags_obj.batch_size,
'optimizer': flags_obj.optimizer,
'learning_rate': flags_obj.learning_rate,
'log_steps': flags_obj.log_steps,
'model_dir': flags_obj.model_dir,
'id_file': euler_graph.id_file,
'infer_dir': flags_obj.model_dir,
'total_size': euler_graph.total_size,
'total_step': num_steps
}
config = tf.estimator.RunConfig(log_step_count_steps=None)
model_estimator = NodeEstimator(model, params, config)
if flags_obj.run_mode == 'train':
model_estimator.train()
elif flags_obj.run_mode == 'evaluate':
model_estimator.evaluate()
elif flags_obj.run_mode == 'infer':
model_estimator.infer()
else:
raise ValueError('Run mode not exist!')
def main(_):
flags_obj = tf.flags.FLAGS
euler_graph = tf_euler.dataset.get_dataset(flags_obj.dataset)
euler_graph.load_graph()
dims = [flags_obj.hidden_dim] * (flags_obj.layers + 1)
if flags_obj.run_mode == 'train':
metapath = [euler_graph.all_edge_type] * flags_obj.layers
else:
metapath = [euler_graph.all_edge_type] * flags_obj.layers
num_steps = int((euler_graph.total_size + 1) // flags_obj.batch_size *
flags_obj.num_epochs)
model = UnsupervisedRGCN(euler_graph.all_node_type,
euler_graph.all_edge_type,
euler_graph.max_node_id, dims, metapath,
euler_graph.max_edge_id, euler_graph.edge_id_idx,
euler_graph.edge_id_dim, flags_obj.embedding_dim,
flags_obj.num_negs, flags_obj.metric)
params = {
'train_node_type': euler_graph.train_node_type[0],
'batch_size': flags_obj.batch_size,
'optimizer': flags_obj.optimizer,
'learning_rate': flags_obj.learning_rate,
'log_steps': flags_obj.log_steps,
'model_dir': flags_obj.model_dir,
'id_file': euler_graph.node_id_file,
'infer_dir': flags_obj.model_dir,
'total_step': num_steps
}
config = tf.estimator.RunConfig(log_step_count_steps=None)
model_estimator = NodeEstimator(model, params, config)
if flags_obj.run_mode == 'train':
model_estimator.train()
elif flags_obj.run_mode == 'evaluate':
model_estimator.evaluate()
elif flags_obj.run_mode == 'infer':
model_estimator.infer()
else:
raise ValueError('Run mode not exist!')
def main(_):
flags_obj = tf.flags.FLAGS
euler_graph = tf_euler.dataset.get_dataset(flags_obj.dataset)
euler_graph.load_graph()
num_steps = int((euler_graph.total_size + 1) // flags_obj.batch_size *
flags_obj.num_epochs)
model = Line(euler_graph.all_node_type,
euler_graph.all_edge_type,
euler_graph.max_node_id,
flags_obj.hidden_dim,
num_negs=flags_obj.num_negs,
order=flags_obj.order,
use_id=flags_obj.use_id,
metric=flags_obj.metric,
embedding_dim=flags_obj.embedding_dim)
params = {
'train_node_type': euler_graph.all_node_type,
'batch_size': flags_obj.batch_size,
'optimizer': flags_obj.optimizer,
'learning_rate': flags_obj.learning_rate,
'log_steps': flags_obj.log_steps,
'model_dir': flags_obj.model_dir,
'id_file': euler_graph.id_file,
'infer_dir': flags_obj.model_dir,
'total_step': num_steps
}
config = tf.estimator.RunConfig(log_step_count_steps=None)
model_estimator = NodeEstimator(model, params, config)
if flags_obj.run_mode == 'train':
model_estimator.train()
elif flags_obj.run_mode == 'evaluate':
model_estimator.evaluate()
elif flags_obj.run_mode == 'infer':
model_estimator.infer()
else:
raise ValueError('Run mode not exist!')