Skip to content

cifair100

load_data

Load and return the ciFAIR100 dataset.

This is the cifar100 dataset but with test set duplicates removed and replaced. See https://arxiv.org/pdf/1902.00423.pdf or https://cvjena.github.io/cifair/ for details. Cite the paper if you use the dataset.

Parameters:

Name Type Description Default
image_key str

The key for image.

 'x'
label_key str

The key for label.

 'y'
label_mode str

Either "fine" for 100 classes or "coarse" for 20 classes.

 'fine'

Returns:

Type Description
Tuple[NumpyDataset, NumpyDataset]

(train_data, test_data)

Raises:

Type Description
ValueError

If the label_mode is invalid.
Source code in fastestimator\fastestimator\dataset\data\cifair100.py 
25
26
27
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
64
65
66
67
68
69
70
71
72
73
74
def load_data(image_key: str = "x",
              label_key: str = "y",
              label_mode: str = "fine") -> Tuple[NumpyDataset, NumpyDataset]:
    """Load and return the ciFAIR100 dataset.

    This is the cifar100 dataset but with test set duplicates removed and replaced. See
    https://arxiv.org/pdf/1902.00423.pdf or https://cvjena.github.io/cifair/ for details. Cite the paper if you use the
    dataset.

    Args:
        image_key: The key for image.
        label_key: The key for label.
        label_mode: Either "fine" for 100 classes or "coarse" for 20 classes.

    Returns:
        (train_data, test_data)

    Raises:
        ValueError: If the label_mode is invalid.
    """
    if label_mode not in ['fine', 'coarse']:
        raise ValueError("label_mode must be one of either 'fine' or 'coarse'.")

    dirname = 'ciFAIR-100'
    archive_name = 'ciFAIR-100.zip'
    origin = 'https://github.com/cvjena/cifair/releases/download/v1.0/ciFAIR-100.zip'
    md5_hash = 'ddc236ab4b12eeb8b20b952614861a33'

    path = get_file(archive_name, origin=origin, file_hash=md5_hash, hash_algorithm='md5', extract=True,
                    archive_format='zip')
    path = os.path.join(os.path.dirname(path), dirname)

    fpath = os.path.join(path, 'train')
    x_train, y_train = _load_batch(fpath, label_key=label_mode + '_labels')

    fpath = os.path.join(path, 'test')
    x_test, y_test = _load_batch(fpath, label_key=label_mode + '_labels')

    y_train = np.reshape(y_train, (len(y_train), 1))
    y_test = np.reshape(y_test, (len(y_test), 1))

    x_train = x_train.transpose((0, 2, 3, 1))
    x_test = x_test.transpose((0, 2, 3, 1))

    x_test = x_test.astype(x_train.dtype)
    y_test = y_test.astype(y_train.dtype)

    train_data = NumpyDataset({image_key: x_train, label_key: y_train})
    test_data = NumpyDataset({image_key: x_test, label_key: y_test})
    return train_data, test_data