how to get the embedding matrix result following the example.py about openke HOT 4 CLOSED

I am interested in the answer of the question by @vlainic. How can we get the embeddings file from a model trained with PyTorch. Could it be an example for showing this usecase?

from openke.

I also want to know！

from openke.

(1) Set import files and OpenKE will automatically load models via tf.Saver().

con = config.Config()
con.set_in_path("./benchmarks/FB15K/")
con.set_test_flag(True)
con.set_work_threads(4)
con.set_dimension(50)
con.set_import_files("./res/model.vec.tf")
con.init()
con.set_model(models.TransE)
# Get the embeddings (numpy.array)
embeddings = con.get_parameters("numpy")
# Get the embeddings (python list)
embeddings = con.get_parameters()

(2) Read model parameters from json files and manually load parameters.

con = config.Config()
con.set_in_path("./benchmarks/FB15K/")
con.set_test_flag(True)
con.set_work_threads(4)
con.set_dimension(50)
con.init()
con.set_model(models.TransE)
f = open("./res/embedding.vec.json", "r")
embeddings = json.loads(f.read())
f.close()

(3) Manually load models via tf.Saver().

con = config.Config()
con.set_in_path("./benchmarks/FB15K/")
con.set_test_flag(True)
con.set_work_threads(4)
con.set_dimension(50)
con.init()
con.set_model(models.TransE)
con.import_variables("./res/model.vec.tf")
# Get the embeddings (numpy.array)
embeddings = con.get_parameters("numpy")
# Get the embeddings (python list)
embeddings = con.get_parameters()

(4) You can also immediately get the embeddings after train the model as follows,
...
...
...
#Models will be exported via tf.Saver() automatically.
con.set_export_files("./res/model.vec.tf", 0)
#Model parameters will be exported to json files automatically.
con.set_out_files("./res/embedding.vec.json")
#Initialize experimental settings.
con.init()
#Set the knowledge embedding model
con.set_model(models.TransE)
#Train the model.
con.run()
#Get the embeddings (numpy.array)
embeddings = con.get_parameters("numpy")
#Get the embeddings (python list)
embeddings = con.get_parameters()

from openke.

Are these solutions still valid, due to the TF -> PyTorch change? Also, there is no config.Config() in the repo.

from openke.