使用model.fit_generator时如何应用K-fold交叉验证

Question

使用model.fit_generator时如何应用K-fold交叉验证.我正在向我的网络提供培训和验证数据.我知道从这里使用sklearn.model_selection.Kfold ,但不知道如何应用于我的模型.我的模型的一些块是:

train_generator = train_datagen.flow_from_directory('train',  
        target_size=(50, 50),  batch_size=batch_size,
        class_mode='binary',color_mode='grayscale')  

validation_generator = test_datagen.flow_from_directory('test',
        target_size=(50, 50),batch_size=batch_size,
        class_mode='binary',color_mode='grayscale')

model.fit_generator(
        train_generator,steps_per_epoch=250 ,epochs=40,
        validation_data=validation_generator,
        validation_steps=21 )