Multi-Scale CNN

Question

我正在尝试使网络类似于图像中的网络，但我不确定它是如何完成的。

我希望它只接收一个输入，然后将其馈送到包含卷积块的2个子网络。我写了这段代码，但是它不工作。

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'])

我得到这个错误:

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实现你可以这样做

A_inputs = keras.Input(shape=(32, 32, 3))
B_inputs = keras.Input(shape=(32, 32, 3))
branchA = Convolution2D(filters=32, kernel_size=(1, 1))(A_inputs)
branchA = BatchNormalization()(branchA)
branchA = Activation('relu')(branchA)
branchA = MaxPooling2D(pool_size=(2, 2))(branchA)
branchA = Model(inputs=A_inputs, outputs=branchA)
branchB = Convolution2D(filters=32, kernel_size=(1, 1))(B_inputs)
branchB = BatchNormalization()(branchB)
branchB = Activation('relu')(branchB)
branchB = MaxPooling2D(pool_size=(2, 2))(branchB)
branchB = Model(inputs=B_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)

这是另一个使用多个分支的教程，但使用了两个不同的输入，但大致的过程是相同的