def train_TransE(target_folder):
con = Config()
# Input training files from benchmarks/FB15K/ folder.
con.set_in_path(target_folder+'/')
con.set_log_on(1) # set to 1 to print the loss
con.set_work_threads(30)
con.set_train_times(2000)
con.set_nbatches(50)
con.set_alpha(0.001)
con.set_margin(1.0)
con.set_bern(0)
con.set_dimension(50)
con.set_ent_neg_rate(1)
con.set_rel_neg_rate(0)
con.set_opt_method("SGD")
# Models will be exported via tf.Saver() automatically.
con.set_export_files(target_folder+"/model.vec.tf", steps=50)
# Model parameters will be exported to json files automatically.
con.set_out_files(target_folder + "/embedding.vec.json")
# Initialize experimental settings.
con.init()
# Set the knowledge embedding model
# print(con.get_parameter_lists())
con.set_model(TransE)
# Train the model.
# print(con.get_parameter_lists())
# print(con.get_parameters())
con.run()
# embeddings = con.get_parameters()
# print(con.get_parameter_lists())
# print(con.trainModel.ent_embeddings)
# print(con.trainModel.rel_embeddings)
# print(con.trainModel.parameter_lists)
# # we need to convert the embedding to txt
with open(target_folder + "/embedding.vec.json", "r") as f:
dic = json.load(f)
#
# print('dic:')
# print(embeddings)
# for key in embeddings:
# print(key)
#
ent_embs, rel_embs = dic['ent_embeddings'], dic['rel_embeddings']
with open(target_folder+'/entity_vector.json', 'w') as f:
json.dump(ent_embs, f)
with open(target_folder+'/relation_vector.json', 'w') as f:
json.dump(rel_embs, f)
def run():
opt_method = args.opt_method
int_pretrain = args.pretrain
if int_pretrain == 1:
pretrain = True
elif int_pretrain == 0:
pretrain = False
else:
raise ValueError('arg "pretrain" must be 0 or 1')
# Download and preprocess ConcepNet
config = Config()
config.set_in_path("./openke_data/")
config.set_log_on(1) # set to 1 to print the loss
config.set_work_threads(30)
config.set_train_times(1000) # number of iterations
config.set_nbatches(512) # batch size
config.set_alpha(0.001) # learning rate
config.set_bern(0)
config.set_dimension(100)
config.set_margin(1.0)
config.set_ent_neg_rate(1)
config.set_rel_neg_rate(0)
config.set_opt_method(opt_method)
'''revision starts'''
config.set_pretrain(pretrain)
# Save the graph embedding every {number} iterations
# OUTPUT_PATH = "./openke_data/embs/glove_initialized/"
if pretrain:
OUTPUT_PATH = "./openke_data/embs/glove_initialized/glove."
else:
OUTPUT_PATH = "./openke_data/embs/xavier_initialized/"
'''revision ends'''
# Model parameters will be exported via torch.save() automatically.
config.set_export_files(OUTPUT_PATH + "transe." + opt_method + ".tf",
steps=500)
# Model parameters will be exported to json files automatically.
# (Might cause IOError if the file is too large)
config.set_out_files(OUTPUT_PATH + "transe." + opt_method + ".vec.json")
print("Opt-method: %s" % opt_method)
print("Pretrain: %d" % pretrain)
config.init()
config.set_model(models.TransE)
print("Begin training TransE")
config.run()
def init_predict(hs, ts, rs):
'''
# (1) Set import files and OpenKE will automatically load models via tf.Saver().
con = Config()
# con.set_in_path("OpenKE/benchmarks/FB15K/")
con.set_in_path("openke_data/")
# con.set_test_link_prediction(True)
con.set_test_triple_classification(True)
con.set_work_threads(8)
con.set_dimension(100)
# con.set_import_files("OpenKE/res/model.vec.tf")
con.set_import_files("openke_data/embs/glove_initialized/glove.transe.SGD.pt")
con.init()
con.set_model(models.TransE)
con.test()
con.predict_triple(hs, ts, rs)
# con.show_link_prediction(2,1)
# con.show_triple_classification(2,1,3)
'''
# (2) Read model parameters from json files and manually load parameters.
con = Config()
con.set_in_path("./openke_data/")
con.set_test_triple_classification(True)
con.set_work_threads(8)
con.set_dimension(100)
con.init()
con.set_model(models.TransE)
f = open("./openke_data/embs/glove_initialized/glove.transe.SGD.vec.json",
"r")
content = json.loads(f.read())
f.close()
con.set_parameters(content)
con.test()
def run():
# Download and preprocess ConcepNet
csv_path = download_concepnet()
tuples_directory = csv_to_tuples(csv_path)
config = Config()
config.set_in_path(f'{tuples_directory}/')
#config.set_in_path(r'/Users/ashishnagar/code/knowledge-enabled-textual-entailment/kg-embeddings/OpenKE/benchmarks/FB15K/')
print(tuples_directory)
config.set_log_on(1) # set to 1 to print the loss
config.set_work_threads(8)
config.set_train_times(500) # number of iterations
config.set_nbatches(300) # batch size
config.set_alpha(0.001) # learning rate
config.set_bern(0)
config.set_dimension(100)
config.set_margin(1.0)
config.set_ent_neg_rate(1)
config.set_rel_neg_rate(0)
config.set_opt_method("SGD")
OUTPUT_PATH = APP_ROOT / "../data/embeddings/conceptnet/"
if not OUTPUT_PATH.exists():
OUTPUT_PATH.mkdir()
OUTPUT_PATH = str(OUTPUT_PATH)
# Model parameters will be exported via torch.save() automatically.
config.set_export_files(OUTPUT_PATH + "/transh.pt")
# Model parameters will be exported to json files automatically.
# (Might cause IOError if the file is too large)
config.set_out_files(OUTPUT_PATH + "/transh_embedding.vec.json")
config.init()
# Save the graph embedding every {number} iterations
config.set_export_steps(20)
config.set_model(models.TransH)
logger.info("Begin training with {}".format(config.__dict__))
config.run()
def run():
opt_method = args.opt_method
int_pretrain = args.pretrain
if int_pretrain == 1:
pretrain = True
elif int_pretrain == 0:
pretrain = False
else:
raise ValueError('arg "pretrain" must be 0 or 1')
config = Config()
config.set_in_path("../dataset/")
config.set_log_on(1) # set to 1 to print the loss
config.set_work_threads(30)
config.set_train_times(10000) # number of iterations
config.set_nbatches(512) # batch size
config.set_alpha(0.001) # learning rate
config.set_bern(0)
config.set_dimension(100)
config.set_margin(1.0)
config.set_ent_neg_rate(1)
config.set_rel_neg_rate(0)
config.set_opt_method(opt_method)
'''revision starts'''
config.set_pretrain(pretrain)
OUTPUT_PATH = "../dataset/emb_init/"
'''revision ends'''
# Model parameters will be exported via torch.save() automatically.
config.set_export_files(OUTPUT_PATH + 'transe.' + opt_method + '.tf',
steps=500)
# Model parameters will be exported to json files automatically.
config.set_out_files(OUTPUT_PATH + "transe." + opt_method + ".vec.json")
print("Opt-method: %s" % opt_method)
print("Pretrain: %d" % pretrain)
config.init()
config.set_model(models.TransE)
print("Begin training TransE")
config.run()
def train(config_data):
#os.environ['CUDA_VISIBLE_DEVICES']= config_data["gpu_number"]
con = Config()
if "use_gpu" in config_data.keys():
if config_data["use_gpu"] == "True":
con.set_use_gpu(True)
else:
con.set_use_gpu(False)
else:
con.set_use_gpu(False)
con.set_in_path(config_data["input_dir"] + "/")
con.set_work_threads(20)
## epoch
con.set_train_times(int(config_data["epochs"]))
## batch size
con.set_nbatches(int(config_data["batch_size"]))
## learning rate
con.set_alpha(float(config_data["learning_rate"]))
con.set_bern(0)
## embedding dimension
con.set_dimension(int(config_data["embedding_dimension"]))
con.set_margin(1.0)
con.set_ent_neg_rate(1)
con.set_rel_neg_rate(0)
con.set_opt_method(config_data["optimizer"])
con.set_save_steps(100)
con.set_valid_steps(100)
con.set_early_stopping_patience(10)
con.set_checkpoint_dir("checkpoint")
con.set_result_dir(config_data["output_dir"])
con.set_test_link(True)
con.set_test_triple(True)
con.init()
con.set_train_model(TransE)
con.train()