深度学习模型改进：更复杂的卷积神经网络架构

model = keras.Sequential([ data_augmentation, layers.experimental.preprocessing.Rescaling(1./255), layers.Conv2D(64, 3, padding='same', activation='relu', input_shape=input_shape), layers.BatchNormalization(), layers.Conv2D(64, 3, padding='same', activation='relu'), layers.BatchNormalization(), layers.MaxPooling2D(), layers.Dropout(0.2), layers.Conv2D(128, 3, padding='same', activation='relu'), layers.BatchNormalization(), layers.Conv2D(128, 3, padding='same', activation='relu'), layers.BatchNormalization(), layers.MaxPooling2D(), layers.Dropout(0.3), layers.Conv2D(256, 3, padding='same', activation='relu'), layers.BatchNormalization(), layers.Conv2D(256, 3, padding='same', activation='relu'), layers.BatchNormalization(), layers.MaxPooling2D(), layers.Dropout(0.4), layers.Flatten(), layers.Dense(512, activation='relu'), layers.BatchNormalization(), layers.Dropout(0.5), layers.Dense(256, activation='relu'), layers.BatchNormalization(), layers.Dropout(0.5), layers.Dense(len(class_names), activation='softmax') ])