search

IntuitionEngineeringTeam / chars2vec

Character-based word embeddings model based on RNN for handling real world texts
Apache License 2.0
171 stars 37 forks source link

the use case of self.model attribute in the Chars2Vec class? #11

Open buiminhhien2k opened 3 years ago

buiminhhien2k commented 3 years ago

I quite new to this field and I just read the source code, but I am quite confused a little bit with the actual role self.model the Chars2Vec class. Can I anyone explain for me how could I use the self.model or what is the role of it there? Because I don't see any method in Chars2Vec calling this param (except the fit method).

43        model_output = keras.layers.Dense(1, activation='sigmoid')(x)
44
45        self.model = keras.models.Model(inputs=[model_input_1, model_input_2], outputs=model_output)
46        self.model.compile(optimizer='adam', loss='mae')