Keras: problem using ImageDataGenerator and KFold for fit_generator

Question

flow_from_directory (directory): This takes up a directory but does not accept split training images.

sklearn.model_selection.KFold: Provides split image indexes. They can be used in fit (), but not in fit_generator ()

How can I use KFold with ImageDataGenerator? Is it there?

Answer 1

, , flow_from_directory. . /, //, , , os Python.

Answer 2

, 2 , - :

from keras.utils import to_categorical  

train_y = to_categorical(train_y, num_classes=2)
test_y = to_categorical(test_y, num_classes=2)

aug = ImageDataGenerator(...) #your ImageDataGenerator

Model = model.fit_generator(aug.flow(train_x,tain_y, batch_size=32), 
            validation_data=(test_x,test_y))