keras: how to predict classes in order?

Question

I'm trying to predict image classes in keras (binary classification). The model accuracy is fine, but it seems that ImageDataGenerator shuffles the input images, so I was not able to match the predicted class with the original images.

datagen = ImageDataGenerator(rescale=1./255)

generator = datagen.flow_from_directory(
        pred_data_dir,
        target_size=(img_width, img_height),
        batch_size=32,
        class_mode=None,
        shuffle=False,
        save_to_dir='images/aug'.format(feature))

print  model.predict_generator(generator, nb_input)

For example, if I have a1.jpg, a2.jpg,..., a9.jpg under pred_data_dir, I expect to get an array like

[class for a1.jpg, class for a2.jpg, ... class for a9.jpg] 

from model.predict_generator(), but actually I got something like

[class for a3.jpg, class for a8.jpg, ... class for a2.jpg]

How can I resolve the issue?

Answer 1

Look at the source code of flow_from_directory. In my case, I had to rename all images. They were named 1.jpg .. 1000.jpg, but to be in order, they had to be named 0001.jpg .. 1000.jpg. The sorting is important here.

flow_from_directory uses sorted(os.listdir(directory)), thus the sorting is not always intuitive.