如何使用flow_from_directory使用k折

Question

这是一所学校。 我已经使用datagen拆分数据集 编译和安装我的模型后，我想应用K折叠交叉验证或使用flow_from_directory使用k-fold

from tensorflow import keras
# Forming datasets
datagen = keras.preprocessing.image.ImageDataGenerator(rescale=1/255, validation_split=0.3)
# Training and validation dataset
train1 = datagen.flow_from_directory('C:/Users/hamza/Desktop/kkk/TrainD', target_size=(224,224), subset='training')
val = datagen.flow_from_directory('C:/Users/hamza/Desktop/kkk/TrainD', target_size=(224,224), subset='validation')

# Test dataset for evaluation
datagen2 = keras.preprocessing.image.ImageDataGenerator(rescale=1/255)

test = datagen2.flow_from_directory('C:/Users/hamza/Desktop/kkk/TestD')


from keras.layers import Dense,GlobalMaxPool2D,Dropout
from keras.models import Model

input_shape = (224,224,3)
# Function to initialize model (ResNet152V2)
base_model = keras.applications.MobileNetV2(input_shape=input_shape,

    include_top=False
)

base_model.trainable = False

x = base_model.output

x = GlobalMaxPool2D()(x)

x = Dense(1024, activation='relu')(x)
pred = Dense(3, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=pred)


model.summary()

from keras.optimizers import SGD
# Model Compiling
model.compile(loss='categorical_crossentropy', optimizer= SGD(lr=0.01, momentum=0.9), metrics='accuracy')

# Model Fitting

history=model.fit(train1, batch_size=32, epochs=20, validation_data=val)