如何加载多个训练和有效性数据来训练和验证keras模型

from keras.models import Sequential
from keras.layers import Dense
from keras.preprocessing.image import ImageDataGenerator

# 准备数据集
train_data_dir = 'path/to/train/data'
validation_data_dir = 'path/to/validation/data'

# 加载数据集
train_datagen = ImageDataGenerator(rescale=1./255)
validation_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
        train_data_dir,
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

validation_generator = validation_datagen.flow_from_directory(
        validation_data_dir,
        target_size=(150, 150),
        batch_size=32,
        class_mode='binary')

# 创建模型
model = Sequential()
model.add(Dense(64, activation='relu', input_dim=100))
model.add(Dense(1, activation='sigmoid'))

# 编译模型
model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

# 训练模型
model.fit_generator(
        train_generator,
        steps_per_epoch=2000,
        epochs=50,
        validation_data=validation_generator,
        validation_steps=800)