无法从 'keras.layers' 导入名称 'Merge'

Question

我尝试了运行代码，但我发现 Keras 的合并层存在问题。我正在使用 python 3 和 keras 2.2.4

这是代码的代码部分


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!")

这是错误信息

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 图层：

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

或其等效的功能接口concatenate（以小写c开头）：

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

如果您对其他形式的合并感兴趣，例如加法、减法等，然后就可以使用相关图层了。有关合并层的完整列表，请参阅 documentation。

无法从 'keras.layers' 导入名称 'Merge'

Cannot import name 'Merge' from 'keras.layers'

python

keras

keras-layer