nn.py 文件源码

def lstm_attention_combine_train(X_train_list,y_train,vocab_size):
    N=len(X_train_list)

    X_train_list = [sequence.pad_sequences(x_train, maxlen=MAX_LEN) for x_train in X_train_list]

    input_list=[]
    out_list=[]
    for i in range(N):
        input,out=get_embedding_input_output('f%d' %i,vocab_size)
        input_list.append(input)
        out_list.append(out)

    x = merge(out_list,mode='concat')

    lstm_out = LSTM(HIDDEN_SIZE, return_sequences=True)(x)

    x = lstm_out
    for i in range(10):
        att = TimeDistributed(Dense(1))(x)
        att = Flatten()(att)
        att = Activation(activation="softmax")(att)
        att = RepeatVector(HIDDEN_SIZE)(att)
        att = Permute((2,1))(att)
        x = att

    mer = merge([att, lstm_out], "mul")
    mer = merge([mer, out_list[-1]], 'mul')
    hid = AveragePooling1D(pool_length=2)(mer)
    hid = Flatten()(hid)

    #hid = merge([hid,out_list[-1]], mode='concat')

    main_loss = Dense(1, activation='sigmoid', name='main_output')(hid)

    model = Model(input=input_list, output=main_loss)

    model.compile(loss='binary_crossentropy', optimizer='rmsprop')
    model.fit(X_train_list, y_train, batch_size=BATCH_SIZE, nb_epoch=EPOCHS)

    return model