I have a folder with 25000 images with cats and dogs picture - how to use tf.keras.utils.image_dataset_from_directory?

I am using vats-vs-dogs data set where the subdirectories are not precreated. Only 1 folder with 25000 images. (cat.001.jpg.... etc then dog.342.jpg.... etc) all in one folder. There are no separate folders called /cats or /dogs. How to use

tf.keras.utils.image_dataset_from_directory function in such case ?

Do I need to explicitly compartmentalize all dogs in /dog and all cats into /cats and then do it ?

img_height = 300
img_width = 300
training_dir = 'drive/MyDrive/training1/dog-cat-train/train'

train_ds = tf.keras.utils.image_dataset_from_directory(
    training_dir, 
    labels='inferred',
    label_mode='categorical',
    color_mode='rgb',
    batch_size=batch_size,
    validation_split=0.2,
    crop_to_aspect_ratio=False,
    seed = 123,
    subset=training,
    image_size=(img_height, img_width))

val_ds = tf.keras.utils.image_dataset_from_directory(
    training_dir,
    labels='inferred',
    label_mode='categorical',
    color_mode='rgb',
    validation_split=0.2,
    subset=validation,
    crop_to_aspect_ratio=False,
    seed=123,
    image_size=(img_height, img_width),
    batch_size=batch_size)```