def test_generator_trane():
"""Function to test the generator for Translation distance based algorithm."""
knowledge_graph = KnowledgeGraph(dataset="freebase15k", negative_sample="uniform")
knowledge_graph.force_prepare_data()
args = KGEArgParser().get_args([])
start_time = timeit.default_timer()
config = TransEConfig(args)
gen = Generator(config=GeneratorConfig(data='train', algo='transe'), model_config=config)
print("----init time:", timeit.default_timer() - start_time)
for i in range(10):
start_time_batch = timeit.default_timer()
data = list(next(gen))
h = data[0]
r = data[1]
t = data[2]
# hr_t = data[3]
# tr_h = data[4]
print("----batch:", i, "----time:",timeit.default_timer() - start_time_batch)
print(h,r,t)
print("total time:", timeit.default_timer() - start_time)
gen.stop()
def test_generator():
import timeit
start_time = timeit.default_timer()
from config.config import TransEConfig
config = TransEConfig()
config.set_dataset("Freebase15k")
gen = Generator(config=GeneratorConfig(data='train', algo='tucker'),
model_config=config)
print("----init time:", timeit.default_timer() - start_time)
for i in range(10):
start_time_batch = timeit.default_timer()
data = list(next(gen))
# import pdb
# pdb.set_trace()
h = data[0]
r = data[1]
t = data[2]
# hr_t = data[3]
# tr_h = data[4]
print("----batch:", i, "----time:",
timeit.default_timer() - start_time_batch)
# print(h,r,t)# time.sleep(0.05)
# print("hr_hr:", hr_hr)
# print("hr_t:", hr_t)
# print("tr_tr:", tr_tr)
# print("tr_h:", tr_h)
print("total time:", timeit.default_timer() - start_time)
gen.stop()
def test_generator_proje():
"""Function to test the generator for ProjE algorithm."""
knowledge_graph = KnowledgeGraph(dataset="freebase15k", negative_sample="uniform")
knowledge_graph.force_prepare_data()
args = KGEArgParser().get_args([])
config = ProjE_pointwiseConfig(args=args)
gen = iter(Generator(config=GeneratorConfig(data='train', algo='ProjE'), model_config=config))
for i in range(1000):
data = list(next(gen))
print("----batch:", i)
hr_hr = data[0]
hr_t = data[1]
tr_tr = data[2]
tr_h = data[3]
print("hr_hr:", hr_hr)
print("hr_t:", hr_t)
print("tr_tr:", tr_tr)
print("tr_h:", tr_h)
gen.stop()
def tune_model(self):
"""Function to tune the model."""
acc = 0
generator_config = GeneratorConfig(
data=self.trainon,
algo=self.model.model_name,
batch_size=self.model.config.batch_size)
self.gen_train = Generator(config=generator_config,
model_config=self.model.config)
self.evaluator = Evaluation(model=self.model,
data_type=self.teston,
debug=self.debug,
tuning=True,
session=self.sess)
for n_iter in range(self.config.epochs):
self.train_model_epoch(n_iter)
self.gen_train.stop()
self.evaluator.test_batch(n_iter)
acc = self.evaluator.output_queue.get()
self.evaluator.stop()
self.sess.close()
tf.reset_default_graph(
) # clean the tensorflow for the next training task.
return acc
def train_model(self):
"""Function to train the model."""
loss = 0
if self.config.loadFromData:
self.load_model()
else:
generator_config = GeneratorConfig(
data=self.trainon,
algo=self.model.model_name,
batch_size=self.model.config.batch_size)
self.gen_train = Generator(config=generator_config,
model_config=self.model.config)
if not self.tuning:
self.evaluator = Evaluation(model=self.model,
data_type=self.teston,
debug=self.debug,
session=self.sess)
for n_iter in range(self.config.epochs):
loss = self.train_model_epoch(n_iter)
if not self.tuning:
self.test(n_iter)
self.gen_train.stop()
if not self.tuning:
self.evaluator.save_training_result(self.training_results)
self.evaluator.stop()
if self.config.save_model:
self.save_model()
if self.config.disp_result:
self.display()
if self.config.disp_summary:
self.summary()
self.summary_hyperparameter()
if not os.path.exists("./tmp"):
os.mkdir("./tmp")
save_path = self.saver.save(self.sess, "./tmp/model.ckpt")
self.sess.close()
tf.reset_default_graph(
) # clean the tensorflow for the next training task.
return loss
def build_model(self):
"""function to build the model"""
self.model.def_inputs()
self.model.def_parameters()
if getattr(self.model, "def_layer", None):
self.model.def_layer()
self.model.def_loss()
if not self.debug:
self.sess = tf.Session(config=self.config.gpu_config)
else:
self.sess = tf.InteractiveSession()
self.global_step = tf.Variable(0, name="global_step", trainable=False)
if self.config.optimizer == 'sgd':
optimizer = tf.train.GradientDescentOptimizer(
learning_rate=self.config.learning_rate)
elif self.config.optimizer == 'rms':
optimizer = tf.train.RMSPropOptimizer(
learning_rate=self.config.learning_rate)
elif self.config.optimizer == 'adam':
optimizer = tf.train.AdamOptimizer(
learning_rate=self.config.learning_rate)
elif self.config.optimizer == 'adagrad':
optimizer = tf.train.AdagradOptimizer(
learning_rate=self.config.learning_rate)
elif self.config.optimizer == 'adadelta':
optimizer = tf.train.AdadeltaOptimizer(
learning_rate=self.config.learning_rate)
else:
raise NotImplementedError("No support for %s optimizer" %
self.config.optimizer)
grads = optimizer.compute_gradients(self.model.loss)
self.op_train = optimizer.apply_gradients(grads,
global_step=self.global_step)
self.sess.run(tf.global_variables_initializer())
self.saver = tf.train.Saver()
if not self.tuning:
self.summary()
self.summary_hyperparameter()
self.generator_config = GeneratorConfig(
data=self.trainon,
algo=self.model.model_name,
batch_size=self.model.config.batch_size,
process_num=self.model.config.num_process_gen,
neg_rate=self.config.neg_rate)
def test_generator_trans():
gen = Generator(config=GeneratorConfig(data='test', algo='TransE'))
for i in range(1000):
data = list(next(gen))
print("----batch:", i)
ph = data[0]
pr = data[1]
pt = data[2]
# nh = data[3]
# nr = data[4]
# nt = data[5]
print("ph:", ph)
print("pr:", pr)
print("pt:", pt)
# print("nh:", nh)
# print("nr:", nr)
# print("nt:", nt)
gen.stop()
def test_generator_proje():
from config.config import ProjE_pointwiseConfig
config = ProjE_pointwiseConfig()
config.set_dataset("Freebase15k")
gen = iter(
Generator(config=GeneratorConfig(data='train', algo='ProjE'),
model_config=config))
for i in range(1000):
data = list(next(gen))
print("----batch:", i)
hr_hr = data[0]
hr_t = data[1]
tr_tr = data[2]
tr_h = data[3]
print("hr_hr:", hr_hr)
print("hr_t:", hr_t)
print("tr_tr:", tr_tr)
print("tr_h:", tr_h)