如何从 Keras.layers 实现合并

Question

我一直在尝试合并以下顺序模型，但未能成功。谁能指出我的错误，谢谢

代码编译时使用"merge"但给出以下错误"TypeError: 'module' object is not callable" 但是，它甚至在使用 "Merge"

时都无法编译

我正在使用 keras 版本 2.2.0 和 python 3.6

from keras.layers import merge
def linear_model_combined(optimizer='Adadelta'):    
    modela = Sequential()
    modela.add(Flatten(input_shape=(100, 34)))
    modela.add(Dense(1024))
    modela.add(Activation('relu'))
    modela.add(Dense(512))

    modelb = Sequential()
    modelb.add(Flatten(input_shape=(100, 34)))
    modelb.add(Dense(1024))
    modelb.add(Activation('relu'))
    modelb.add(Dense(512))

    model_combined = Sequential()

    model_combined.add(Merge([modela, modelb], mode='concat'))

    model_combined.add(Activation('relu'))
    model_combined.add(Dense(256))
    model_combined.add(Activation('relu'))

    model_combined.add(Dense(4))
    model_combined.add(Activation('softmax'))

    model_combined.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model_combined

Answer 1

合并不能与顺序模型一起使用。在顺序模型中，层只能有一个输入和一个输出。你必须使用 functional API，像这样。我假设您对 modela 和 modelb 使用相同的输入层，但如果不是这样，您可以创建另一个 Input() 并将它们都作为模型的输入。

def linear_model_combined(optimizer='Adadelta'):    

    # declare input
    inlayer =Input(shape=(100, 34))
    flatten = Flatten()(inlayer)

    modela = Dense(1024)(flatten)
    modela = Activation('relu')(modela)
    modela = Dense(512)(modela)

    modelb = Dense(1024)(flatten)
    modelb = Activation('relu')(modelb)
    modelb = Dense(512)(modelb)

    model_concat = concatenate([modela, modelb])


    model_concat = Activation('relu')(model_concat)
    model_concat = Dense(256)(model_concat)
    model_concat = Activation('relu')(model_concat)

    model_concat = Dense(4)(model_concat)
    model_concat = Activation('softmax')(model_concat)

    model_combined = Model(inputs=inlayer,outputs=model_concat)

    model_combined.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return model_combined

Answer 2

keras.layers.merge 图层已弃用。如此处所述，使用 keras.layers.Concatenate(axis=-1) 代替：https://keras.io/layers/merge/#concatenate

Answer 3

老实说，我在这个问题上纠结了很久...

幸好我终于找到了万灵丹。对于想要使用 Sequential 对其原始代码进行最小更改的任何人，这里提供了解决方案：

def linear_model_combined(optimizer='Adadelta'): 
    from keras.models import Model, Sequential
    from keras.layers.core import Dense, Flatten, Activation, Dropout
    from keras.layers import add

    modela = Sequential()
    modela.add(Flatten(input_shape=(100, 34)))
    modela.add(Dense(1024))
    modela.add(Activation('relu'))
    modela.add(Dense(512))

    modelb = Sequential()
    modelb.add(Flatten(input_shape=(100, 34)))
    modelb.add(Dense(1024))
    modelb.add(Activation('relu'))
    modelb.add(Dense(512))

    merged_output = add([modela.output, modelb.output])   

    model_combined = Sequential()
    model_combined.add(Activation('relu'))
    model_combined.add(Dense(256))
    model_combined.add(Activation('relu'))
    model_combined.add(Dense(4))
    model_combined.add(Activation('softmax'))

    final_model = Model([modela.input, modelb.input], model_combined(merged_output))

    final_model.compile(loss='categorical_crossentropy', optimizer=optimizer, metrics=['accuracy'])

    return final_model

更多信息，请参考https://github.com/keras-team/keras/issues/3921#issuecomment-335457553farizrahman4u的评论。 ;)

如何从 Keras.layers 实现合并

How to implement Merge from Keras.layers

python

neural-network

python-3.x

keras

keras-layer