Search code examples
pythontensorflownls

Natural lagnuage generation via RNN and csv data

I'm a beginner of TensorFlow and machine learning. I'd like to ask about how I can make some code.

I'm trying to make a natural language generation program by RNN.

you can see the picture which is data, there're x, y, vocab_size and max_len each row. Is there a way to execute that code integrally? Each row has its own data, and the length of lists are different. If there's no way, do I have to execute each row separately?

enter image description here

model = Sequential()
model.add(Embedding(vocab_size, 10, input_length=max_len-1))
model.add(SimpleRNN(32))
model.add(Dense(vocab_size, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(dataset, epochs=200, verbose=2)
Solution

  • Actually just the architecture you defined earlier should be sufficient. CMIIW