本文转载自:Siligence技术社区
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/4205github.com
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。
本文转载自:Siligence技术社区
网友评论