無法從“keras.layers”導入名稱“Merge”

Question

我嘗試運行代碼，但我發現Keras合並層有問題。 我正在使用 python 3 和keras 2.2.4

這是代碼的 de code 部分

import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import LSTM, Embedding, TimeDistributed, Dense, RepeatVector, Merge, Activation
from keras.preprocessing import image, sequence
import cPickle as pickle


    def create_model(self, ret_model = False):

        image_model = Sequential()
        image_model.add(Dense(EMBEDDING_DIM, input_dim = 4096, activation='relu'))
        image_model.add(RepeatVector(self.max_length))

        lang_model = Sequential()
        lang_model.add(Embedding(self.vocab_size, 256, input_length=self.max_length))
        lang_model.add(LSTM(256,return_sequences=True))
        lang_model.add(TimeDistributed(Dense(EMBEDDING_DIM)))

        model = Sequential()
        model.add(Merge([image_model, lang_model], mode='concat'))
        model.add(LSTM(1000,return_sequences=False))
        model.add(Dense(self.vocab_size))
        model.add(Activation('softmax'))

        print ("Model created!")

這是錯誤信息

from keras.layers import LSTM, Embedding, TimeDistributed, Dense, RepeatVector, Merge, Activation
ImportError: cannot import name 'Merge' from 'keras.layers'

Answer 1

Keras +2 不支持Merge 。 相反，您需要使用Concatenate層：

merged = Concatenate()([x1, x2]) # NOTE: the layer is first constructed and then it's called on its input

或者它是等效的功能接口concatenate （以小寫c開頭）：

merged = concatenate([x1,x2]) # NOTE: the input of layer is passed as an argument, hence named *functional interface*

如果您對其他形式的合並感興趣，例如加法、減法等，那么您可以使用相關層。 有關合並圖層的完整列表，請參閱文檔。