How to use file_paths on a tensorflow TakeDataset?

Question

I am trying to build a image classifier using a dataset of images, split between two directories, one for each class.

data_dir = 'experimental.data'
batch_size = 9
img_size = (160, 160)

train_ds = tf.keras.utils.image_dataset_from_directory(
    data_dir,
    validation_split=0.2,
    subset="training",
    seed=123,
    shuffle=True,
    image_size=img_size,
    batch_size=batch_size)

val_ds = tf.keras.utils.image_dataset_from_directory(
    data_dir,
    validation_split=0.2,
    subset="validation",
    seed=123,
    shuffle=True,
    image_size=img_size,
    batch_size=batch_size)

class_names = train_ds.class_names
print(class_names)

['false', 'true']

val_batches = tf.data.experimental.cardinality(val_ds)
test_ds = val_ds.take(val_batches // 5)
val_ds = val_ds.skip(val_batches // 5)

When I get to predicting on my test/new images, I want to map the image paths to a pandas dataframe, along with predictions, so I can the use python to create a directory with a copy of the classed images.

file_paths = train_ds.file_paths

Calling the file_paths argument works fine on the train dataset, however after splitting the test/val datasets with skip/take, I get an error.

file_paths = test_ds.file_paths

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-129-3a6769d8217f> in <module>
----> 1 file_paths = test_ds.file_paths

AttributeError: 'TakeDataset' object has no attribute 'file_paths'

Is there a way to make this work using file_paths?