控制Keras层中的信息流和选通因子

对于闸门(自动分数g):

from keras.models import Model
from keras.layers import *

inputTensor = Input(someInputShape)

#the actual value
valueTensor = CreateSomeLayer(parameters)(inputTensor)

#the gate - this is the value of 'g', from zero to 1
gateTensor = AnotherLayer(matchingParameters, activation='sigmoid')(inputTensor)

#value * gate = fraction g
fractionG = Lambda(lambda x: x[0]*x[1])([valueTensor,gateTensor])

#value - fraction = 1 - g
complement = Lambda(lambda x: x[0] - x[1])([valueTensor,fractionG])

#each tensor may go into individual layers and follow individual paths:
immediateNextOutput = ImmediateNextLayer(params)(fractionG)
oneOfTheForwardOutputs = OneOfTheForwardLayers(params)(complement)

#keep going, make one or more outputs, and create your model:
model = Model(inputs=inputTensor, outputs=outputTensorOrListOfOutputTensors)    

#concat
joinedTensor = Concatenate(axis=optionalAxis)([input1,input2])

#add
joinedTensor = Add()([input1,input2])

#etc.....

nextLayerOut = TheLayer(parameters)(joinedTensor)

如果要手动控制“g”:

gateTensor 由用户定义:

import keras.backend as K

gateTensor = Input(tensor=K.variable([g]))

创建模型时,将此张量作为输入传递。(因为它是一个 tensor 输入,它不会改变您使用 fit 方法)。

model = Model(inputs=[inputTensor,gateTensor], outputs=outputTensorOrListOfOutputTensors)