合並不同的CNN模型

Question

我們是數據科學的新手，我們正在嘗試合並兩個不同的 CNN 模型（一個有 2 個班級，另一個有 3 個班級）。 模型的代碼是：

性別模型

    #initialize the model along with the input shape
    model = Sequential()
    inputShape = (height, width, depth)
    chanDim = -1
   
    if K.image_data_format() == 'channels_first':
        inputShape = (depth, height, width)
        chanDim = 1
       
    # CONV -> RELU -> MAXPOOL
    model.add(Convolution2D(64, (3,3), padding='same', input_shape=inputShape))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(MaxPooling2D(pool_size=(3,3)))
    model.add(Dropout(0.25))
   
    # (CONV -> RELU)*2 -> AVGPOOL
    model.add(Convolution2D(128, (3,3), padding='same'))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(Convolution2D(128, (3,3), padding='same'))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(AveragePooling2D(pool_size=(3,3) ))
    model.add(Dropout(0.25))
   
    # CONV -> RELU -> MAXPOOL
    model.add(Convolution2D(256, (3,3), padding='same'))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(MaxPooling2D(pool_size=(3,3)))
    model.add(Dropout(0.25))
   
    # CONV -> RELU -> AVGPOOL
    model.add(Convolution2D(512, (3,3), padding='same'))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(AveragePooling2D(pool_size=(3,3)))
    model.add(Dropout(0.25))
   
    # DENSE -> RELU
    model.add(Flatten())
    model.add(Dense(1024))
    model.add(Activation('relu'))
    model.add(BatchNormalization())
    model.add(Dropout(0.25))
   
    # DENSE -> RELU
    model.add(Dense(512))
    model.add(Activation('relu'))
    model.add(BatchNormalization())
    model.add(Dropout(0.25))
   
    # sigmoid -> just to check the accuracy with this (softmax would work too)
    model.add(Dense(classes))
    model.add(Activation('sigmoid'))
   
    return model
model = build(img_size, img_size, 3, 2)
model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

種族模型：

    #initialize the model along with the input shape
    model = Sequential()
    inputShape = (height, width, depth)
    chanDim = -1
   
    if K.image_data_format() == 'channels_first':
        inputShape = (depth, height, width)
        chanDim = 1
       
    # CONV -> RELU -> MAXPOOL
    model.add(Convolution2D(64, (3,3), padding='same', input_shape=inputShape))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(MaxPooling2D(pool_size=(3,3)))
    model.add(Dropout(0.25))
   
    # (CONV -> RELU)*2 -> AVGPOOL
    model.add(Convolution2D(128, (3,3), padding='same'))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(Convolution2D(128, (3,3), padding='same'))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(AveragePooling2D(pool_size=(3,3) ))
    model.add(Dropout(0.25))
   
    # CONV -> RELU -> MAXPOOL
    model.add(Convolution2D(256, (3,3), padding='same'))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(MaxPooling2D(pool_size=(3,3)))
    model.add(Dropout(0.25))
   
    # CONV -> RELU -> AVGPOOL
    model.add(Convolution2D(512, (3,3), padding='same'))
    model.add(Activation('relu'))
    model.add(BatchNormalization(axis=chanDim))
    model.add(AveragePooling2D(pool_size=(3,3)))
    model.add(Dropout(0.25))
   
    # DENSE -> RELU
    model.add(Flatten())
    model.add(Dense(1024))
    model.add(Activation('relu'))
    model.add(BatchNormalization())
    model.add(Dropout(0.25))
   
    # DENSE -> RELU
    model.add(Dense(512))
    model.add(Activation('relu'))
    model.add(BatchNormalization())
    model.add(Dropout(0.25))
   
    # softmax
    model.add(Dense(classes))
    model.add(Activation('softmax'))
   
    return model
model = build(img_size, img_size, 3, 3)
model.compile(loss= 'categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

我們嘗試將模型與 concatenate keras 函數合並，但未能理解如何合並具有不同類數的兩個模型。 我們的目標是：給定一張照片，我們想同時預測性別和種族。感謝您的關注。

Answer 1

讓我們調用第一個模型model_1和第二個模型model_2 。 您需要做的第一步是將模型的輸入更改為一些通用輸入。

inputs = keras.layers.Input(shape=inputShape)

outputs_1 = model_1(inputs)
outputs_2 = model_2(inputs

接下來使用這些輸入和輸出創建一個模型

new_model = keras.Model(inputs=inputs, outputs=[outputs_1, outputs_2])

現在模型有一個輸入和兩個輸出。 您可以從單個輸入中獲得兩個預測。

修復名稱沖突

如果模型具有相同的名稱和/或模型的圖層具有同名的圖層，請使用以下代碼重命名模型和模型的圖層。

model_1._name = "model_1_"+model_1.name
model_2._name = "model_2_"+model_2.name

for layer in model_1.layers:
    layer._name = "model_1_layer_"+layer.name

for layer in model_2.layers:
    layer._name = "model_2_layer_"+layer.name