Skip to content

usps

load_data

Load and return the USPS 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[LabeledDirDataset, LabeledDirDataset]

(train_data, test_data)
Source code in fastestimator\fastestimator\dataset\data\usps.py 
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
def load_data(root_dir: Optional[str] = None) -> Tuple[LabeledDirDataset, LabeledDirDataset]:
    """Load and return the USPS 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, test_data)
    """
    home = str(Path.home())

    if root_dir is None:
        root_dir = os.path.join(home, 'fastestimator_data', 'USPS')
    else:
        root_dir = os.path.join(os.path.abspath(root_dir), 'USPS')
    os.makedirs(root_dir, exist_ok=True)

    # download data to memory
    train_compressed_path = os.path.join(root_dir, "zip.train.gz")
    test_compressed_path = os.path.join(root_dir, "zip.test.gz")
    train_base_path = os.path.join(root_dir, "train")
    test_base_path = os.path.join(root_dir, "test")

    if not os.path.exists(train_base_path):
        if not os.path.exists(train_compressed_path):
            print("Downloading train data to {}".format(root_dir))
            wget.download('http://statweb.stanford.edu/~tibs/ElemStatLearn/datasets/zip.train.gz',
                          root_dir,
                          bar=bar_custom)
        train_images, train_labels = _extract_images_labels(train_compressed_path)
        _write_data(train_images, train_labels, train_base_path, "train")

    if not os.path.exists(test_base_path):
        if not os.path.exists(test_compressed_path):
            print("Downloading test data to {}".format(root_dir))
            wget.download('http://statweb.stanford.edu/~tibs/ElemStatLearn/datasets/zip.test.gz',
                          root_dir,
                          bar=bar_custom)
        test_images, test_labels = _extract_images_labels(test_compressed_path)
        _write_data(test_images, test_labels, test_base_path, "test")

    # make datasets
    return LabeledDirDataset(train_base_path, file_extension=".png"), LabeledDirDataset(test_base_path,
                                                                                        file_extension=".png")