Skip to content

omniglot

load_data ΒΆ

Load and return the Omniglot dataset.

Parameters:

Name Type Description Default
root_dir Optional[str]

The path to store the downloaded data. When path is not provided, the data will be saved into fastestimator_data under the user's home directory.

 None

Returns:

Type Description
Tuple[SiameseDirDataset, SiameseDirDataset]

(train_data, eval_data)
Source code in fastestimator/fastestimator/dataset/data/omniglot.py 
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
def load_data(root_dir: Optional[str] = None) -> Tuple[SiameseDirDataset, SiameseDirDataset]:
    """Load and return the Omniglot dataset.

    Args:
        root_dir: The path to store the downloaded data. When `path` is not provided, the data will be saved into
            `fastestimator_data` under the user's home directory.

    Returns:
        (train_data, eval_data)
    """
    if root_dir is None:
        root_dir = os.path.join(str(Path.home()), 'fastestimator_data', 'Omniglot')
    else:
        root_dir = os.path.join(os.path.abspath(root_dir), 'Omniglot')
    os.makedirs(root_dir, exist_ok=True)

    train_path = os.path.join(root_dir, 'images_background')
    eval_path = os.path.join(root_dir, 'images_evaluation')
    train_zip = os.path.join(root_dir, 'images_background.zip')
    eval_zip = os.path.join(root_dir, 'images_evaluation.zip')

    files = [(train_path, train_zip, 'https://github.com/brendenlake/omniglot/raw/master/python/images_background.zip'),
             (eval_path, eval_zip, 'https://github.com/brendenlake/omniglot/raw/master/python/images_evaluation.zip')]

    for data_path, data_zip, download_link in files:
        if not os.path.exists(data_path):
            # Download
            if not os.path.exists(data_zip):
                print("Downloading data: {}".format(data_zip))
                wget.download(download_link, data_zip, bar=bar_custom)
            # Extract
            print("Extracting data: {}".format(data_path))
            with zipfile.ZipFile(data_zip, 'r') as zip_file:
                zip_file.extractall(root_dir)

    return SiameseDirDataset(train_path), SiameseDirDataset(eval_path)