use attention_3d_block in many to many mapping about keras-attention HOT 7 CLOSED

The Seq2seq framework includes a ready made attention model which does the same.

    input_text = ['** 的 首都 是 北京'
                  , '日本 的 首都 是 东京'
                  , '美国 的 首都 是 华盛顿'
                  , '英国 的 首都 是 伦敦'
                  , '德国 的 首都 是 柏林']
    
    tar_text = ['Beijing is the capital of China'
                , 'Tokyo is the capital of Japan'
                , 'Washington is the capital of the United States'
                , 'London is the capital of England'
                , 'Berlin is the capital of Germany']
                
    input_list = []
    tar_list = []
    END = ' EOS'
    for tmp_input in input_text:
        tmp_input = tmp_input+END
        input_list.append(tokenize(tmp_input))
    for tmp_tar in tar_text:
        tmp_tar = tmp_tar+END
        tar_list.append(tokenize(tmp_tar))
    vocab = sorted(reduce(lambda x, y: x | y, (set(tmp_list) for tmp_list in input_list + tar_list)))

    vocab_size = len(vocab) + 1  # keras embedding need len(vocab)+1
    input_maxlen = max(map(len, (x for x in input_list)))
    tar_maxlen = max(map(len, (x for x in tar_list)))
    output_dim = vocab_size
    hidden_dim = 1000
    INPUT_DIM = hidden_dim #senten length
    TIME_STEPS = input_maxlen #

    word_to_idx = dict((c, i + 1) for i, c in enumerate(vocab))  
    idx_to_word = dict((i + 1, c) for i, c in enumerate(vocab))  

    inputs_train, tars_train = vectorize_stories(input_list, tar_list, word_to_idx, input_maxlen, tar_maxlen, vocab_size)
    #inputs_trains shape is (5,6) and tars_tratin shape is (5,9,30)

def model_attention_applied_before_lstm():
    inputs = Input(shape=(input_maxlen,))
    embed = Embedding(input_dim=vocab_size,
                              output_dim=620,
                              input_length=input_maxlen)(inputs)
    attention_mul = LSTM(hidden_dim, return_sequences=True)(embed)    
    attention_mul = attention_3d_block(attention_mul)
    attention_mul = LSTM(500, return_sequences=True)(attention_mul)
    output = TimeDistributed(Dense(output_dim, activation='sigmoid'),input_shape=(tar_maxlen, output_dim))(attention_mul)
    #output = TimeDistributed(Dense(output_dim))(output)
    #output = Dense(output_dim, activation='sigmoid')(attention_mul)
    #output = RepeatVector(tar_maxlen)(output)
    #output = Permute((tar_maxlen,output_dim),name='reshapeLayer')(output)
    output = Activation('softmax')(output)
    model = Model(input=[inputs], output=output)
    return model

    m = model_attention_applied_before_lstm()
    m.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
    print(m.summary())

    m.fit(inputs_train, tars_train, epochs=10, batch_size=3, validation_split=0.1)