How to know ImageDataGenerator() assigns which label to which image class?

Question

For binary classification of cats and dogs images, my directory structure is train_dir/cats and train_dir/dogs.

train_datagen = ImageDataGenerator(rescale=1/255)

        train_generator = train_datagen.flow_from_directory(
        '/train_dir/',  # This is the source directory for training images
        target_size=(300, 300),  # All images will be resized to 150x150
        batch_size=128,
        # Since we use binary_crossentropy loss, we need binary labels
        class_mode='binary')

        model.predict(images, batch_size=10)

How to know the probability return by model.predict() belongs to which class? is Cat=1 or dog=1? I read somewhere that for multiclass classification returned probabilities are in alphabetical order of class names. But I think that is not the case for binary classification.

Answer 1

You need to access class_indices variable associated with each ImageDataGenerator class. Just print train_generator.class_indices to see which class is given which label.