不能再向以前一樣使用

model.add(Merge([Model1,Model2]))

必須使用函式式

out = Concatenate()([model1.output,model2.output])

補充知識：keras 新版介面修改

1.

# b = MaxPooling2D((3,3),strides=(1,1),border_mode='valid',dim_ordering='tf')(x)

b = MaxPooling2D((3,padding='valid',data_format="channels_last")(x)

2.

from keras.layers.merge import concatenate
# x = merge([a,b],mode='concat',concat_axis=-1)
x = concatenate([a,axis=-1)

3.

from keras.engine import merge
m = merge([init,x],mode='sum')
Equivalent Keras 2.0.2 code:

from keras.layers import add
m = add([init,x])

4.

 # x = Convolution2D(32 // nb_filters_reduction_factor,3,subsample=(1,activation='relu',#     init='he_normal',dim_ordering='tf')(x)
 x = Conv2D(32 // nb_filters_reduction_factor,(3,activation="relu",padding="valid",data_format="channels_last",kernel_initializer="he_normal")(x)

1.

# b = MaxPooling2D((3,dim_ordering='tf')(x)
b = MaxPooling2D((3,data_format="channels_last")(x)

2.

from keras.layers.merge import concatenate
# x = merge([a,kernel_initializer="he_normal")(x)

以上這篇使用keras2.0 將Merge層改為函式式就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支援我們。