Seq2seq encoder-decoder Modell-stack LSTM

Ich habe versucht, diese keras Beispiel seq2seq, encoder-decoder-Modell für Sprache übersetzung. Modell-definition:

# Define an input sequence and process it.
encoder_inputs = Input(shape=(None, num_encoder_tokens))
encoder = CuDNNLSTM(latent_dim, return_state=True)
encoder_outputs, state_h, state_c = encoder(encoder_inputs)
# We discard `encoder_outputs` and only keep the states.
encoder_states = [state_h, state_c]

# Set up the decoder, using `encoder_states` as initial state.
decoder_inputs = Input(shape=(None, num_decoder_tokens))
# We set up our decoder to return full output sequences,
# and to return internal states as well. We don't use the
# return states in the training model, but we will use them in inference.
decoder_lstm = CuDNNLSTM(latent_dim, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs,
                                     initial_state=encoder_states)
decoder_dense = Dense(num_decoder_tokens, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)

# Define the model that will turn
# `encoder_input_data` & `decoder_input_data` into `decoder_target_data`
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)

Modell erfolgreich gelernt, Englisch zu Russisch Charakter-level-übersetzung, um einige zu verlängern. Aber wie man sehen kann-encoder und-decoder besteht nur auf LSTM layer an. Der gesunde Menschenverstand stapeln viele LSTM Schichten zusammen geben würde, bessere Ergebnisse.

Is it good idea to stack LSTM layers, if yes how in this case?

0
2019-09-19 04:00:58
Quelle
0 Antworten

Sehen Sie sich andere Fragen zu Tags an