I have this model with dot product attention layer. I have commented out the part in the code. How do I use self-attention instead of the attention layer I have ? So, basically, I want to replace the commented part with self attention layer.
I am open to keras-self-attention or a manually added layer. Anything that works
# Encoder
encoder_inputs = Input(shape=(max_text_len, ))
# Embedding layer
enc_emb = Embedding(x_voc, embedding_dim,
trainable=True)(encoder_inputs)
# Encoder LSTM 1
encoder_lstm1 = Bidirectional(LSTM(latent_dim, return_sequences=True,
return_state=True, dropout=0.4,
recurrent_dropout=0.4))
(encoder_output1, forward_h1, forward_c1, backward_h1, backward_c1) = encoder_lstm1(enc_emb)
# Encoder LSTM 2
encoder_lstm2 = Bidirectional(LSTM(latent_dim, return_sequences=True,
return_state=True, dropout=0.4,
recurrent_dropout=0.4))
(encoder_output2, forward_h2, forward_c2, backward_h2, backward_c2) = encoder_lstm2(encoder_output1)
# Encoder LSTM 3
encoder_lstm3 = Bidirectional(LSTM(latent_dim, return_state=True,
return_sequences=True, dropout=0.4,
recurrent_dropout=0.4))
(encoder_outputs, forward_h, forward_c, backward_h, backward_c) = encoder_lstm3(encoder_output2)
state_h = Concatenate()([forward_h, backward_h])
state_c = Concatenate()([forward_c, backward_c])
# Set up the decoder, using encoder_states as the initial state
decoder_inputs = Input(shape=(None, ))
# Embedding layer
dec_emb_layer = Embedding(y_voc, embedding_dim, trainable=True)
dec_emb = dec_emb_layer(decoder_inputs)
# Decoder LSTM
decoder_lstm = LSTM(latent_dim*2, return_sequences=True,
return_state=True, dropout=0.4,
recurrent_dropout=0.2)
(decoder_outputs, decoder_fwd_state, decoder_back_state) = \
decoder_lstm(dec_emb, initial_state=[state_h, state_c])
#Start attention layer
# attention = dot([decoder_outputs, encoder_outputs], axes=[2, 2])
# attention = Activation('softmax')(attention)
# context = dot([attention, encoder_outputs], axes=[2,1])
# decoder_outputs = Concatenate()([context, decoder_outputs])
#End attention layer
# Dense layer
decoder_dense = TimeDistributed(Dense(y_voc, activation='softmax'))(decoder_outputs)
# Define the model
model = Model([encoder_inputs, decoder_inputs], decoder_dense)