machine-learning - 多尺度CNN

Question

我正在尝试建立一个类似于 image 中的网络，但我不确定它是如何完成的。
我希望它只接收一个输入，然后将它提供给 2 个包含卷积块的子网络。我写了这段代码，但它不起作用。

main_model = Sequential()
main_model.add(Convolution2D(filters=16, kernel_size=(2, 2), input_shape=(32, 32, 3)))
main_model.add(BatchNormalization())
main_model.add(Activation('relu'))
main_model.add(MaxPooling2D(pool_size=(2, 2)))

main_model.add(Convolution2D(filters=32, kernel_size=(2, 2)))
main_model.add(BatchNormalization())
main_model.add(Activation('relu'))
main_model.add(MaxPooling2D(pool_size=(2, 2)))

main_model.add(Convolution2D(filters=64, kernel_size=(2, 2)))
main_model.add(BatchNormalization())
main_model.add(Activation('relu'))
main_model.add(MaxPooling2D(pool_size=(2, 2)))

main_model.add(Flatten())

# lower features model - CNN2
lower_model = Sequential()
lower_model.add(Convolution2D(filters=16, kernel_size=(1, 1), input_shape=(32, 32, 3)))
lower_model.add(BatchNormalization())
lower_model.add(Activation('relu'))
lower_model.add(MaxPooling2D(pool_size=(2, 2)))
lower_model.add(Flatten())

lower_model.add(Convolution2D(filters=32, kernel_size=(1, 1)))
lower_model.add(BatchNormalization())
lower_model.add(Activation('relu'))
lower_model.add(MaxPooling2D(pool_size=(2, 2)))

lower_model.add(Convolution2D(filters=64, kernel_size=(1, 1)))
lower_model.add(BatchNormalization())
lower_model.add(Activation('relu'))
lower_model.add(MaxPooling2D(pool_size=(2, 2)))

lower_model.add(Flatten())

# merged model
merged_model = concatenate([main_model, lower_model])

final_model = Sequential()
final_model.add(merged_model)
final_model.add(Dense(32))
final_model.add(Activation('relu'))
final_model.add(Dropout(0.5))
final_model.add(Dense(1))
final_model.add(Activation('sigmoid'))

final_model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

我收到此错误:

ValueError: Input 0 of layer conv2d_4 is incompatible with the layer: expected ndim=4, found ndim=2. Full shape received: [None, 4096]

Answer 1

这可以通过使用 Keras Functional API 来实现
你可以做这样的事情

img_inputs = keras.Input(shape=(32, 32, 3))

branchA = Convolution2D(filters=32, kernel_size=(1, 1))(img_inputs)
branchA = BatchNormalization()(branchA)
branchA = Activation('relu')(branchA)
branchA = MaxPooling2D(pool_size=(2, 2))(branchA)
branchA = Model(inputs=img_inputs, outputs=branchA)

branchB = Convolution2D(filters=32, kernel_size=(1, 1))(img_inputs)
branchB = BatchNormalization()(branchB)
branchB = Activation('relu')(branchB)
branchB = MaxPooling2D(pool_size=(2, 2))(branchB)
branchB = Model(inputs=img_inputs, outputs=branchB)

#you may need to make sure output size of branchA and branchB are same size
combined = concatenate([branchA.output, branchB.output])

combined = Dense(2, activation="relu")(combined)
combined = Dense(1, activation="softmax")(combined)

model = Model(inputs=[branchA.input, branchB.input], outputs=combined)

Here是另一个使用多个分支但确实使用两个不同输入但粗略过程相同的教程