Function read_data_sets

neural_network/input_data.py:270–342

(
    train_dir,
    fake_data=False,
    one_hot=False,
    dtype=dtypes.float32,
    reshape=True,
    validation_size=5000,
    seed=None,
    source_url=DEFAULT_SOURCE_URL,
)

@deprecated(None, "Please use alternatives such as: tensorflow_datasets.load('mnist')")
def read_data_sets(
    train_dir,
    fake_data=False,
    one_hot=False,
    dtype=dtypes.float32,
    reshape=True,
    validation_size=5000,
    seed=None,
    source_url=DEFAULT_SOURCE_URL,
):
    if fake_data:

        def fake():
            return _DataSet(
                [], [], fake_data=True, one_hot=one_hot, dtype=dtype, seed=seed
            )

        train = fake()
        validation = fake()
        test = fake()
        return _Datasets(train=train, validation=validation, test=test)

    if not source_url:  # empty string check
        source_url = DEFAULT_SOURCE_URL

    train_images_file = "train-images-idx3-ubyte.gz"
    train_labels_file = "train-labels-idx1-ubyte.gz"
    test_images_file = "t10k-images-idx3-ubyte.gz"
    test_labels_file = "t10k-labels-idx1-ubyte.gz"

    local_file = _maybe_download(
        train_images_file, train_dir, source_url + train_images_file
    )
    with gfile.Open(local_file, "rb") as f:
        train_images = _extract_images(f)

    local_file = _maybe_download(
        train_labels_file, train_dir, source_url + train_labels_file
    )
    with gfile.Open(local_file, "rb") as f:
        train_labels = _extract_labels(f, one_hot=one_hot)

    local_file = _maybe_download(
        test_images_file, train_dir, source_url + test_images_file
    )
    with gfile.Open(local_file, "rb") as f:
        test_images = _extract_images(f)

    local_file = _maybe_download(
        test_labels_file, train_dir, source_url + test_labels_file
    )
    with gfile.Open(local_file, "rb") as f:
        test_labels = _extract_labels(f, one_hot=one_hot)

    if not 0 <= validation_size <= len(train_images):
        msg = (
            "Validation size should be between 0 and "
            f"{len(train_images)}. Received: {validation_size}."