使用 RNN 切换 CNN 层

Question

如果我有这些层用于 CNN

img_shape = (256, 256, 3)
model = keras.Sequential(name='RGBimg_Classify_Net')
model.add(keras.layers.Conv2D(
    128, 3, input_shape=(img_shape), activation='relu'))
model.add(keras.layers.MaxPool2D())
model.add(keras.layers.Conv2D(128, 3, strides=(2, 2), activation='relu'))
model.add(keras.layers.MaxPool2D())
model.add(keras.layers.BatchNormalization())
model.add(keras.layers.Conv2D(64, 3, strides=(2, 2), activation='relu'))
model.add(keras.layers.MaxPool2D())
model.add(keras.layers.Flatten())
model.add(keras.layers.Dropout(0.2))
model.add(keras.layers.Dense(1024, activation='relu'))
model.add(keras.layers.Dense(512, activation='relu'))
model.add(keras.layers.Dense(len(classes), activation='softmax'))

除了将主神经网络切换到循环神经网络之外，我还能做些什么来保持尽可能多的东西不变？