How to add attention layer to seq2seq model on Keras

user_6478704 0
Viewed 1389

Based on this article, I wrote this model:

enc_in=Input(shape=(None,in_alphabet_len))
lstm=LSTM(lstm_dim,return_sequences=True,return_state=True,use_bias=False)
enc_out,h,c=lstm(enc_in)
dec_in=Input(shape=(None,in_alphabet_len))
decoder,_,_=LSTM(decoder_dim,return_sequences=True,return_state=True)(dec_in,initial_state=[h,c])
decoder=Dense(units=in_alphabet_len,activation='softmax')(decoder)
model=Model([enc_in,dec_in],decoder)

How can I add attention layer to this model before decoder?

attention-model lstm keras deep-learning nlp
1 Answers

You can use this repo,

  1. you will need to pip install keras-self-attention
  2. import layer from keras_self_attention import SeqSelfAttention
    • if you want to use tf.keras not keras, add the following before the import os.environ['TF_KERAS'] = '1'
    • Make sure if you are using keras to omit the previous flag as it will cause inconsistencies

  3. Since you are using keras functional API, 

    enc_out, h, c = lstm()(enc_in)
att = SeqSelfAttention()(enc_out)
dec_in = Input(shape=(None, in_alphabet_len))(att)

    I hope this answers your question, and future readers

user_82795930
Related