How to use the fastai.vision.ImageList.from_folder function in fastai

def test_wrong_order():
    this_tests('na')
    path = untar_data(URLs.MNIST_TINY)
    with pytest.raises(Exception, match="Your data isn't split*"):
        ImageList.from_folder(path).label_from_folder().split_by_folder()

def tiny_ic_data(tiny_ic_data_path):
    """ Returns tiny ic data bunch """
    return (
        ImageList.from_folder(tiny_ic_data_path)
        .split_by_rand_pct(valid_pct=0.2, seed=10)
        .label_from_folder()
        .transform(size=299)
        .databunch(bs=16)
        .normalize(imagenet_stats)
    )

#
# Once complete, update the `DATA_PATH` variable to point to `out_dir` so that this notebook uses these resized images.
#

# ## Training <a name="training"></a>
#
# We'll now re-apply the same steps we did in the [01_training_introduction](01_training_introduction.ipynb) notebook here.

# Load the data:

# In[8]:


label_list = (
    (
        ImageList.from_folder(Path(DATA_PATH))
        .split_by_rand_pct(valid_pct=0.2, seed=10)
        .label_from_folder()
    )
    if not multilabel
    else (
        ImageList.from_csv(Path(DATA_PATH), "labels.csv", folder="images")
        .split_by_rand_pct(valid_pct=0.2, seed=10)
        .label_from_df(label_delim=" ")
    )
)


# In[9]:


data = (

# ```
#
# We have already set the data to this format structure.

# # Load Images
#
# In `fastai`, an `ImageDataBunch` can easily use multiple images (mini-batches) during training time. We create the `ImageDataBunch` by using [data_block apis](https://docs.fast.ai/data_block.html).
#
# For training and validation, we randomly split the data in an `8:2` ratio, holding 80% of the data for training and 20% for validation.
#

# In[5]:


data = (
    ImageList.from_folder(path)
    .split_by_rand_pct(valid_pct=0.2, seed=10)
    .label_from_folder()
    .transform(size=IMAGE_SIZE)
    .databunch(bs=BATCH_SIZE)
    .normalize(imagenet_stats)
)


# We examine some sample data using the `databunch` we created.

# In[6]:


data.show_batch(rows=3, figsize=(15, 11))

Create ImageDataBunch and return it. TODO in future version is to allow
        users to pass in their own image bunch or their own Transformation
        objects (instead of using fastai's )

        Args:
            path (Union[Path, str]): path to data to create databunch with
            transform (bool): a flag to set fastai default transformations (get_transforms())
            im_size (int): image size of databunch
            bs (int): batch size of databunch
        Returns:
            ImageDataBunch
        """
        path = path if type(path) is Path else Path(path)
        tfms = get_transforms() if transform else None
        return (
            ImageList.from_folder(path)
            .split_by_rand_pct(valid_pct=0.33)
            .label_from_folder()
            .transform(tfms=tfms, size=im_size)
            .databunch(bs=bs, num_workers=db_num_workers())
            .normalize(imagenet_stats)
        )