CODEWITHSUNDEEP
neural-networkkeraslstmrecurrent-neural-networkseq2seq
terenceflow
terenceflow

Reputation: 223

Seq2Seq Bidirectional Encoder Decoder in Keras

I am trying to implement a seq2seq encoder-decoder using Keras, with bidirectional lstm on the encoder as follows:

from keras.layers import LSTM,Bidirectional,Input,Concatenate
from keras.models import Model

n_units = 8
n_input = 1
n_output = 1

# encoder
encoder_inputs = Input(shape=(None, n_input))
encoder = Bidirectional(LSTM(n_units, return_state=True))
encoder_outputs, forward_h, forward_c, backward_h, backward_c = encoder(encoder_inputs)
state_h = Concatenate()([forward_h, backward_h])
state_c = Concatenate()([forward_c, backward_c])
encoder_states = [state_h, state_c]

# decoder
decoder_inputs = Input(shape=(None, n_output))    
decoder_lstm = LSTM(n_units*2, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs, initial_state=encoder_states)

Here is the following error I got on the last line:

ValueError: Dimensions must be equal, but are 8 and 16 for 
'lstm_2_1/MatMul_4' (op: 'MatMul') with input shapes: [?,8], [16,16].

Any ideas?

Upvotes: 3

Views: 9685

Answers (2)

Hemanth Yernagula
Hemanth Yernagula

Reputation: 1

https://stackoverflow.com/a/50820218/10706937

from keras.layers import LSTM,Bidirectional,Input,Concatenate
from keras.models import Model

n_units = 8
n_input = 1
n_output = 1

# encoder
encoder_inputs = Input(shape=(None, n_input))
encoder = Bidirectional(LSTM(n_units, return_state=True))
encoder_outputs, forward_h, forward_c, backward_h, backward_c = encoder(encoder_inputs)
state_h = Concatenate()([forward_h, backward_h])
state_c = Concatenate()([forward_c, backward_c])
encoder_states = [state_h, state_c]

# decoder
decoder_inputs = Input(shape=(None, n_output))    
decoder_lstm = LSTM(n_units*2, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs, initial_state=encoder_states)
decoder_dense = Dense(n_output, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)


# define inference encoder
encoder_model = Model(encoder_inputs, encoder_states)
# define inference decoder
decoder_state_input_h = Input(shape=(n_units*2,))
decoder_state_input_c = Input(shape=(n_units*2,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_lstm(decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model([decoder_inputs] + decoder_states_inputs, [decoder_outputs] + decoder_states)

How to remove inference encoder in the above comment. I mean how to solve the error without inference encoder

Upvotes: 0

terenceflow
terenceflow

Reputation: 223

Although the error pointed to the last line of the block in the question, however it was due to the wrong number of hidden units in the inference decoder. Solved!

Full working code:

from keras.layers import LSTM,Bidirectional,Input,Concatenate
from keras.models import Model

n_units = 8
n_input = 1
n_output = 1

# encoder
encoder_inputs = Input(shape=(None, n_input))
encoder = Bidirectional(LSTM(n_units, return_state=True))
encoder_outputs, forward_h, forward_c, backward_h, backward_c = encoder(encoder_inputs)
state_h = Concatenate()([forward_h, backward_h])
state_c = Concatenate()([forward_c, backward_c])
encoder_states = [state_h, state_c]

# decoder
decoder_inputs = Input(shape=(None, n_output))    
decoder_lstm = LSTM(n_units*2, return_sequences=True, return_state=True)
decoder_outputs, _, _ = decoder_lstm(decoder_inputs, initial_state=encoder_states)
decoder_dense = Dense(n_output, activation='softmax')
decoder_outputs = decoder_dense(decoder_outputs)
model = Model([encoder_inputs, decoder_inputs], decoder_outputs)


# define inference encoder
encoder_model = Model(encoder_inputs, encoder_states)
# define inference decoder
decoder_state_input_h = Input(shape=(n_units*2,))
decoder_state_input_c = Input(shape=(n_units*2,))
decoder_states_inputs = [decoder_state_input_h, decoder_state_input_c]
decoder_outputs, state_h, state_c = decoder_lstm(decoder_inputs, initial_state=decoder_states_inputs)
decoder_states = [state_h, state_c]
decoder_outputs = decoder_dense(decoder_outputs)
decoder_model = Model([decoder_inputs] + decoder_states_inputs, [decoder_outputs] + decoder_states)

Upvotes: 7

Related Questions