Skip to content

food101

load_data

Load and return the Food-101 dataset.

Food-101 dataset is a collection of images from 101 food categories. Sourced from http://data.vision.ee.ethz.ch/cvl/food-101.tar.gz

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[CSVDataset, CSVDataset]

(train_data, test_data)
Source code in fastestimator/fastestimator/dataset/data/food101.py 
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
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
def load_data(root_dir: Optional[str] = None) -> Tuple[CSVDataset, CSVDataset]:
    """Load and return the Food-101 dataset.

    Food-101 dataset is a collection of images from 101 food categories.
    Sourced from http://data.vision.ee.ethz.ch/cvl/food-101.tar.gz

    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', 'Food_101')
    else:
        root_dir = os.path.join(os.path.abspath(root_dir), 'Food_101')
    os.makedirs(root_dir, exist_ok=True)

    image_compressed_path = os.path.join(root_dir, 'food-101.tar.gz')
    image_extracted_path = os.path.join(root_dir, 'food-101')

    train_csv_path = os.path.join(root_dir, 'train.csv')
    test_csv_path = os.path.join(root_dir, 'test.csv')

    if not os.path.exists(image_extracted_path):
        # download
        if not os.path.exists(image_compressed_path):
            print("Downloading data to {}".format(root_dir))
            wget.download('http://data.vision.ee.ethz.ch/cvl/food-101.tar.gz', root_dir, bar=bar_custom)

        # extract
        print("\nExtracting files ...")
        with tarfile.open(image_compressed_path) as img_tar:
            img_tar.extractall(root_dir)

    labels = open(os.path.join(root_dir, "food-101/meta/classes.txt"), "r").read().split()
    label_dict = {labels[i]: i for i in range(len(labels))}

    if not os.path.exists(train_csv_path):
        train_images = open(os.path.join(root_dir, "food-101/meta/train.txt"), "r").read().split()
        random.shuffle(train_images)
        _create_csv(train_images, label_dict, train_csv_path)
    if not os.path.exists(test_csv_path):
        test_images = open(os.path.join(root_dir, "food-101/meta/test.txt"), "r").read().split()
        random.shuffle(test_images)
        _create_csv(test_images, label_dict, test_csv_path)

    return CSVDataset(train_csv_path), CSVDataset(test_csv_path)