Question

我们是数据科学的新手，我们正在尝试合并两种不同的CNN模型（一个具有2个班级，另一个具有3个班级）。模型的代码是：

性别模型

    #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'])

种族模型：

    #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'])

我们尝试将模型与串联的keras函数合并，但未能取消描述如何合并具有不同类数的两个模型。我们的目标是：给定一张照片，我们希望同时预测性别和种族感谢您的关注。

Answer 1

我们叫第一个模型PS C:\Users\USER\OneDrive\Documents\Projects\Vagrant2> vagrant package --base Vagrant2_default_1598799939605_1106 ==> Vagrant2_default_1598799939605_1106: Exporting VM... ==> Vagrant2_default_1598799939605_1106: Compressing package to: C:/Users/USER/OneDrive/Documents/Projects/Vagrant2/package.box和第二个模型model_1。您需要做的第一步是将模型的输入更改为一些通用输入。

model_2

下一步，使用这些输入和输出创建模型

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

outputs_1 = model_1(inputs)
outputs_2 = model_2(inputs

现在，模型具有一个输入和两个输出。您可以从单个输入获得两个预测。

修复名称冲突

如果模型具有相同的名称和/或模型的层具有相同的名称，请使用以下代码重命名模型和模型的层。

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

合并不同的CNN模型

1 个答案:

修复名称冲突