keras实现多个模型融合(非keras自带模型,这里以3个自己的模型为例)

发布于 2019-06-11 17:48:05

该代码可以实现类似图片的效果,多个模型采用第一个输入。
图片来源:https://github.com/keras-team/keras/issues/4205

model2点击并拖拽以移动​
1111.png

step 1:重新定义模型(这是我自己的模型,你们可以用你们自己的),与预训练不一样,这里定义模型inp要采用公共的,代码如下:

def get_model(inp):#重新建立模型,与原来不一样的是这里inp是传入
    n_classes = 10
    #inp=Input(shape=(120,39))#原来的inp是函数里,传入可以三个公用
    reshape=Reshape((1,120,39))(inp)
 #   pre=ZeroPadding2D(padding=(1, 1))(reshape)
    # 1
    #reshape=BatchNormalization()(reshape)
    conv1=Convolution2D(32, 3, 3, border_mode='same',init='glorot_uniform')(reshape)
    #model.add(Activation('relu'))
    l1=PReLU()(conv1)
    l1=BatchNormalization()(l1)

    conv2=ZeroPadding2D(padding=(1, 1))(l1)
    conv2=Convolution2D(32, 3, 3, border_mode='same',init='glorot_uniform')(conv2)
    #model.add(Activation('relu'))
    l2=PReLU()(conv2)
    l2=BatchNormalization()(l2)

    m2=AveragePooling2D((3, 3), strides=(3, 3))(l2)
    d2=Dropout(0.25)(m2)
    # 2
    conv3=ZeroPadding2D(padding=(1, 1))(d2)
    conv3=Convolution2D(64, 3, 3, border_mode='same',init='glorot_uniform')(conv3)
    #model.add(Activation('relu'))
    l3=PReLU()(conv3)
    l3=BatchNormalization()(l3)

    conv4=ZeroPadding2D(padding=(1, 1))(l3)
    conv4=Convolution2D(64, 3, 3, border_mode='same',init='glorot_uniform')(conv4)
    #model.add(Activation('relu'))
    l4=PReLU()(conv4)
    l4=BatchNormalization()(l4)

    m4=AveragePooling2D((3, 3), strides=(3, 3))(l4)
    d4=Dropout(0.25)(m4)
    
    g=GlobalAveragePooling2D()(d4)
#4
#    conv4=Convolution2D(32, 3, 3, border_mode='same',init='glorot_uniform')(d3)
#    conv4=BatchNormalization()(conv4)
#    #model.add(Activation('relu'))
#    l4=LeakyReLU(alpha=0.33)(conv4)
#    m4=MaxPooling2D((2, 2))(l4)
#    d4=Dropout(0.25)(m4)
    
    #f=Flatten()(g)
    Den=Dense(1024)(g)
    #model.add(Activation('relu'))
    ld=PReLU()(Den)
    ld=Dropout(0.5)(ld)
    result=Dense(n_classes, activation='softmax')(ld)



    model=Model(input=inp,outputs=result)
    return model

step2:加载模型参数,融合模型,代码如下:

def merge_model():
    inp=Input(shape=(120,39))#融合主要就是Input是同样的,所以重新建立模型
    model1=get_model(inp)
    model2=get_model(inp)
    model3=get_model(inp)
    model1.load_weights(model_path+"CNN_mfcc1.h5")#加载各自权重
    model2.load_weights(model_path+"CNN_mfcc2.h5")#加载各自权重
    model3.load_weights(model_path+"CNN_mfcc3.h5")#加载各自权重
    
    r1=model1.output#获得输出
    r2=model2.output
    r3=model3.output
    
    x=concatenate([r1,r2,r3],axis=1)#拼接输出,融合成功
    model=Model(input=inp,outputs=x)
    return model

step3:根据自己的需要修改模型,我这里只是添加全连接层做分类,代码如下:

def modify():#这里修改模型
    origin_model=merge_model()
    for layer in origin_model.layers:
        layer.trainable = False#原来的不训练
        
    inp=origin_model.input
    x=origin_model.output
    
    den=Dense(200,name="fine_dense")(x)
    l=PReLU()(den)
    l=Dropout(0.5)(l)
    result=Dense(10,activation="softmax")(l)
    
    model=Model(input=inp,outputs=result)
    model.summary()
    #编译model
    adam = keras.optimizers.Adam(lr = 0.0005, beta_1=0.95, beta_2=0.999,epsilon=1e-08)
    #adam = keras.optimizers.Adam(lr = 0.001, beta_1=0.95, beta_2=0.999,epsilon=1e-08)
    #sgd = keras.optimizers.SGD(lr = 0.001, decay = 1e-06, momentum = 0.9, nesterov = False)

    #reduce_lr = ReduceLROnPlateau(monitor = 'loss', factor = 0.1, patience = 2,verbose = 1, min_lr = 0.00000001, mode = 'min')
    model.compile(loss='categorical_crossentropy', optimizer=adam, metrics=['accuracy'])

    
    return model

大家可以通过自己的需要修改,有疑问的请评论。

0 评论

发布
问题