from .vision import VisionDataset
import warnings
from PIL import Image
import os
import os.path
import numpy as np
import torch
import codecs
import string
import gzip
import lzma
from typing import Any, Callable, Dict, IO, List, Optional, Tuple, Union
from .utils import download_url, download_and_extract_archive, extract_archive, \
verify_str_arg
[docs]class MNIST(VisionDataset):
"""`MNIST <http://yann.lecun.com/exdb/mnist/>`_ Dataset.
Args:
root (string): Root directory of dataset where ``MNIST/processed/training.pt``
and ``MNIST/processed/test.pt`` exist.
train (bool, optional): If True, creates dataset from ``training.pt``,
otherwise from ``test.pt``.
download (bool, optional): If true, downloads the dataset from the internet and
puts it in root directory. If dataset is already downloaded, it is not
downloaded again.
transform (callable, optional): A function/transform that takes in an PIL image
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the
target and transforms it.
"""
resources = [
("http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz", "f68b3c2dcbeaaa9fbdd348bbdeb94873"),
("http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz", "d53e105ee54ea40749a09fcbcd1e9432"),
("http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz", "9fb629c4189551a2d022fa330f9573f3"),
("http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz", "ec29112dd5afa0611ce80d1b7f02629c")
]
training_file = 'training.pt'
test_file = 'test.pt'
classes = ['0 - zero', '1 - one', '2 - two', '3 - three', '4 - four',
'5 - five', '6 - six', '7 - seven', '8 - eight', '9 - nine']
@property
def train_labels(self):
warnings.warn("train_labels has been renamed targets")
return self.targets
@property
def test_labels(self):
warnings.warn("test_labels has been renamed targets")
return self.targets
@property
def train_data(self):
warnings.warn("train_data has been renamed data")
return self.data
@property
def test_data(self):
warnings.warn("test_data has been renamed data")
return self.data
def __init__(
self,
root: str,
train: bool = True,
transform: Optional[Callable] = None,
target_transform: Optional[Callable] = None,
download: bool = False,
) -> None:
super(MNIST, self).__init__(root, transform=transform,
target_transform=target_transform)
self.train = train # training set or test set
if download:
self.download()
if not self._check_exists():
raise RuntimeError('Dataset not found.' +
' You can use download=True to download it')
if self.train:
data_file = self.training_file
else:
data_file = self.test_file
self.data, self.targets = torch.load(os.path.join(self.processed_folder, data_file))
def __getitem__(self, index: int) -> Tuple[Any, Any]:
"""
Args:
index (int): Index
Returns:
tuple: (image, target) where target is index of the target class.
"""
img, target = self.data[index], int(self.targets[index])
# doing this so that it is consistent with all other datasets
# to return a PIL Image
img = Image.fromarray(img.numpy(), mode='L')
if self.transform is not None:
img = self.transform(img)
if self.target_transform is not None:
target = self.target_transform(target)
return img, target
def __len__(self) -> int:
return len(self.data)
@property
def raw_folder(self) -> str:
return os.path.join(self.root, self.__class__.__name__, 'raw')
@property
def processed_folder(self) -> str:
return os.path.join(self.root, self.__class__.__name__, 'processed')
@property
def class_to_idx(self) -> Dict[str, int]:
return {_class: i for i, _class in enumerate(self.classes)}
def _check_exists(self) -> bool:
return (os.path.exists(os.path.join(self.processed_folder,
self.training_file)) and
os.path.exists(os.path.join(self.processed_folder,
self.test_file)))
def download(self) -> None:
"""Download the MNIST data if it doesn't exist in processed_folder already."""
if self._check_exists():
return
os.makedirs(self.raw_folder, exist_ok=True)
os.makedirs(self.processed_folder, exist_ok=True)
# download files
for url, md5 in self.resources:
filename = url.rpartition('/')[2]
download_and_extract_archive(url, download_root=self.raw_folder, filename=filename, md5=md5)
# process and save as torch files
print('Processing...')
training_set = (
read_image_file(os.path.join(self.raw_folder, 'train-images-idx3-ubyte')),
read_label_file(os.path.join(self.raw_folder, 'train-labels-idx1-ubyte'))
)
test_set = (
read_image_file(os.path.join(self.raw_folder, 't10k-images-idx3-ubyte')),
read_label_file(os.path.join(self.raw_folder, 't10k-labels-idx1-ubyte'))
)
with open(os.path.join(self.processed_folder, self.training_file), 'wb') as f:
torch.save(training_set, f)
with open(os.path.join(self.processed_folder, self.test_file), 'wb') as f:
torch.save(test_set, f)
print('Done!')
def extra_repr(self) -> str:
return "Split: {}".format("Train" if self.train is True else "Test")
[docs]class FashionMNIST(MNIST):
"""`Fashion-MNIST <https://github.com/zalandoresearch/fashion-mnist>`_ Dataset.
Args:
root (string): Root directory of dataset where ``FashionMNIST/processed/training.pt``
and ``FashionMNIST/processed/test.pt`` exist.
train (bool, optional): If True, creates dataset from ``training.pt``,
otherwise from ``test.pt``.
download (bool, optional): If true, downloads the dataset from the internet and
puts it in root directory. If dataset is already downloaded, it is not
downloaded again.
transform (callable, optional): A function/transform that takes in an PIL image
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the
target and transforms it.
"""
resources = [
("http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-images-idx3-ubyte.gz",
"8d4fb7e6c68d591d4c3dfef9ec88bf0d"),
("http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/train-labels-idx1-ubyte.gz",
"25c81989df183df01b3e8a0aad5dffbe"),
("http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-images-idx3-ubyte.gz",
"bef4ecab320f06d8554ea6380940ec79"),
("http://fashion-mnist.s3-website.eu-central-1.amazonaws.com/t10k-labels-idx1-ubyte.gz",
"bb300cfdad3c16e7a12a480ee83cd310")
]
classes = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal',
'Shirt', 'Sneaker', 'Bag', 'Ankle boot']
[docs]class KMNIST(MNIST):
"""`Kuzushiji-MNIST <https://github.com/rois-codh/kmnist>`_ Dataset.
Args:
root (string): Root directory of dataset where ``KMNIST/processed/training.pt``
and ``KMNIST/processed/test.pt`` exist.
train (bool, optional): If True, creates dataset from ``training.pt``,
otherwise from ``test.pt``.
download (bool, optional): If true, downloads the dataset from the internet and
puts it in root directory. If dataset is already downloaded, it is not
downloaded again.
transform (callable, optional): A function/transform that takes in an PIL image
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the
target and transforms it.
"""
resources = [
("http://codh.rois.ac.jp/kmnist/dataset/kmnist/train-images-idx3-ubyte.gz", "bdb82020997e1d708af4cf47b453dcf7"),
("http://codh.rois.ac.jp/kmnist/dataset/kmnist/train-labels-idx1-ubyte.gz", "e144d726b3acfaa3e44228e80efcd344"),
("http://codh.rois.ac.jp/kmnist/dataset/kmnist/t10k-images-idx3-ubyte.gz", "5c965bf0a639b31b8f53240b1b52f4d7"),
("http://codh.rois.ac.jp/kmnist/dataset/kmnist/t10k-labels-idx1-ubyte.gz", "7320c461ea6c1c855c0b718fb2a4b134")
]
classes = ['o', 'ki', 'su', 'tsu', 'na', 'ha', 'ma', 'ya', 're', 'wo']
[docs]class EMNIST(MNIST):
"""`EMNIST <https://www.westernsydney.edu.au/bens/home/reproducible_research/emnist>`_ Dataset.
Args:
root (string): Root directory of dataset where ``EMNIST/processed/training.pt``
and ``EMNIST/processed/test.pt`` exist.
split (string): The dataset has 6 different splits: ``byclass``, ``bymerge``,
``balanced``, ``letters``, ``digits`` and ``mnist``. This argument specifies
which one to use.
train (bool, optional): If True, creates dataset from ``training.pt``,
otherwise from ``test.pt``.
download (bool, optional): If true, downloads the dataset from the internet and
puts it in root directory. If dataset is already downloaded, it is not
downloaded again.
transform (callable, optional): A function/transform that takes in an PIL image
and returns a transformed version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform that takes in the
target and transforms it.
"""
# Updated URL from https://www.nist.gov/node/1298471/emnist-dataset since the
# _official_ download link
# https://cloudstor.aarnet.edu.au/plus/s/ZNmuFiuQTqZlu9W/download
# is (currently) unavailable
url = 'http://www.itl.nist.gov/iaui/vip/cs_links/EMNIST/gzip.zip'
md5 = "58c8d27c78d21e728a6bc7b3cc06412e"
splits = ('byclass', 'bymerge', 'balanced', 'letters', 'digits', 'mnist')
# Merged Classes assumes Same structure for both uppercase and lowercase version
_merged_classes = set(['C', 'I', 'J', 'K', 'L', 'M', 'O', 'P', 'S', 'U', 'V', 'W', 'X', 'Y', 'Z'])
_all_classes = set(list(string.digits + string.ascii_letters))
classes_split_dict = {
'byclass': list(_all_classes),
'bymerge': sorted(list(_all_classes - _merged_classes)),
'balanced': sorted(list(_all_classes - _merged_classes)),
'letters': list(string.ascii_lowercase),
'digits': list(string.digits),
'mnist': list(string.digits),
}
def __init__(self, root: str, split: str, **kwargs: Any) -> None:
self.split = verify_str_arg(split, "split", self.splits)
self.training_file = self._training_file(split)
self.test_file = self._test_file(split)
super(EMNIST, self).__init__(root, **kwargs)
self.classes = self.classes_split_dict[self.split]
@staticmethod
def _training_file(split) -> str:
return 'training_{}.pt'.format(split)
@staticmethod
def _test_file(split) -> str:
return 'test_{}.pt'.format(split)
def download(self) -> None:
"""Download the EMNIST data if it doesn't exist in processed_folder already."""
import shutil
if self._check_exists():
return
os.makedirs(self.raw_folder, exist_ok=True)
os.makedirs(self.processed_folder, exist_ok=True)
# download files
print('Downloading and extracting zip archive')
download_and_extract_archive(self.url, download_root=self.raw_folder, filename="emnist.zip",
remove_finished=True, md5=self.md5)
gzip_folder = os.path.join(self.raw_folder, 'gzip')
for gzip_file in os.listdir(gzip_folder):
if gzip_file.endswith('.gz'):
extract_archive(os.path.join(gzip_folder, gzip_file), gzip_folder)
# process and save as torch files
for split in self.splits:
print('Processing ' + split)
training_set = (
read_image_file(os.path.join(gzip_folder, 'emnist-{}-train-images-idx3-ubyte'.format(split))),
read_label_file(os.path.join(gzip_folder, 'emnist-{}-train-labels-idx1-ubyte'.format(split)))
)
test_set = (
read_image_file(os.path.join(gzip_folder, 'emnist-{}-test-images-idx3-ubyte'.format(split))),
read_label_file(os.path.join(gzip_folder, 'emnist-{}-test-labels-idx1-ubyte'.format(split)))
)
with open(os.path.join(self.processed_folder, self._training_file(split)), 'wb') as f:
torch.save(training_set, f)
with open(os.path.join(self.processed_folder, self._test_file(split)), 'wb') as f:
torch.save(test_set, f)
shutil.rmtree(gzip_folder)
print('Done!')
[docs]class QMNIST(MNIST):
"""`QMNIST <https://github.com/facebookresearch/qmnist>`_ Dataset.
Args:
root (string): Root directory of dataset whose ``processed''
subdir contains torch binary files with the datasets.
what (string,optional): Can be 'train', 'test', 'test10k',
'test50k', or 'nist' for respectively the mnist compatible
training set, the 60k qmnist testing set, the 10k qmnist
examples that match the mnist testing set, the 50k
remaining qmnist testing examples, or all the nist
digits. The default is to select 'train' or 'test'
according to the compatibility argument 'train'.
compat (bool,optional): A boolean that says whether the target
for each example is class number (for compatibility with
the MNIST dataloader) or a torch vector containing the
full qmnist information. Default=True.
download (bool, optional): If true, downloads the dataset from
the internet and puts it in root directory. If dataset is
already downloaded, it is not downloaded again.
transform (callable, optional): A function/transform that
takes in an PIL image and returns a transformed
version. E.g, ``transforms.RandomCrop``
target_transform (callable, optional): A function/transform
that takes in the target and transforms it.
train (bool,optional,compatibility): When argument 'what' is
not specified, this boolean decides whether to load the
training set ot the testing set. Default: True.
"""
subsets = {
'train': 'train',
'test': 'test',
'test10k': 'test',
'test50k': 'test',
'nist': 'nist'
}
resources: Dict[str, List[Tuple[str, str]]] = { # type: ignore[assignment]
'train': [('https://raw.githubusercontent.com/facebookresearch/qmnist/master/qmnist-train-images-idx3-ubyte.gz',
'ed72d4157d28c017586c42bc6afe6370'),
('https://raw.githubusercontent.com/facebookresearch/qmnist/master/qmnist-train-labels-idx2-int.gz',
'0058f8dd561b90ffdd0f734c6a30e5e4')],
'test': [('https://raw.githubusercontent.com/facebookresearch/qmnist/master/qmnist-test-images-idx3-ubyte.gz',
'1394631089c404de565df7b7aeaf9412'),
('https://raw.githubusercontent.com/facebookresearch/qmnist/master/qmnist-test-labels-idx2-int.gz',
'5b5b05890a5e13444e108efe57b788aa')],
'nist': [('https://raw.githubusercontent.com/facebookresearch/qmnist/master/xnist-images-idx3-ubyte.xz',
'7f124b3b8ab81486c9d8c2749c17f834'),
('https://raw.githubusercontent.com/facebookresearch/qmnist/master/xnist-labels-idx2-int.xz',
'5ed0e788978e45d4a8bd4b7caec3d79d')]
}
classes = ['0 - zero', '1 - one', '2 - two', '3 - three', '4 - four',
'5 - five', '6 - six', '7 - seven', '8 - eight', '9 - nine']
def __init__(
self, root: str, what: Optional[str] = None, compat: bool = True,
train: bool = True, **kwargs: Any
) -> None:
if what is None:
what = 'train' if train else 'test'
self.what = verify_str_arg(what, "what", tuple(self.subsets.keys()))
self.compat = compat
self.data_file = what + '.pt'
self.training_file = self.data_file
self.test_file = self.data_file
super(QMNIST, self).__init__(root, train, **kwargs)
def download(self) -> None:
"""Download the QMNIST data if it doesn't exist in processed_folder already.
Note that we only download what has been asked for (argument 'what').
"""
if self._check_exists():
return
os.makedirs(self.raw_folder, exist_ok=True)
os.makedirs(self.processed_folder, exist_ok=True)
split = self.resources[self.subsets[self.what]]
files = []
# download data files if not already there
for url, md5 in split:
filename = url.rpartition('/')[2]
file_path = os.path.join(self.raw_folder, filename)
if not os.path.isfile(file_path):
download_url(url, root=self.raw_folder, filename=filename, md5=md5)
files.append(file_path)
# process and save as torch files
print('Processing...')
data = read_sn3_pascalvincent_tensor(files[0])
assert(data.dtype == torch.uint8)
assert(data.ndimension() == 3)
targets = read_sn3_pascalvincent_tensor(files[1]).long()
assert(targets.ndimension() == 2)
if self.what == 'test10k':
data = data[0:10000, :, :].clone()
targets = targets[0:10000, :].clone()
if self.what == 'test50k':
data = data[10000:, :, :].clone()
targets = targets[10000:, :].clone()
with open(os.path.join(self.processed_folder, self.data_file), 'wb') as f:
torch.save((data, targets), f)
def __getitem__(self, index: int) -> Tuple[Any, Any]:
# redefined to handle the compat flag
img, target = self.data[index], self.targets[index]
img = Image.fromarray(img.numpy(), mode='L')
if self.transform is not None:
img = self.transform(img)
if self.compat:
target = int(target[0])
if self.target_transform is not None:
target = self.target_transform(target)
return img, target
def extra_repr(self) -> str:
return "Split: {}".format(self.what)
def get_int(b: bytes) -> int:
return int(codecs.encode(b, 'hex'), 16)
def open_maybe_compressed_file(path: Union[str, IO]) -> Union[IO, gzip.GzipFile]:
"""Return a file object that possibly decompresses 'path' on the fly.
Decompression occurs when argument `path` is a string and ends with '.gz' or '.xz'.
"""
if not isinstance(path, torch._six.string_classes):
return path
if path.endswith('.gz'):
return gzip.open(path, 'rb')
if path.endswith('.xz'):
return lzma.open(path, 'rb')
return open(path, 'rb')
SN3_PASCALVINCENT_TYPEMAP = {
8: (torch.uint8, np.uint8, np.uint8),
9: (torch.int8, np.int8, np.int8),
11: (torch.int16, np.dtype('>i2'), 'i2'),
12: (torch.int32, np.dtype('>i4'), 'i4'),
13: (torch.float32, np.dtype('>f4'), 'f4'),
14: (torch.float64, np.dtype('>f8'), 'f8')
}
def read_sn3_pascalvincent_tensor(path: Union[str, IO], strict: bool = True) -> torch.Tensor:
"""Read a SN3 file in "Pascal Vincent" format (Lush file 'libidx/idx-io.lsh').
Argument may be a filename, compressed filename, or file object.
"""
# read
with open_maybe_compressed_file(path) as f:
data = f.read()
# parse
magic = get_int(data[0:4])
nd = magic % 256
ty = magic // 256
assert nd >= 1 and nd <= 3
assert ty >= 8 and ty <= 14
m = SN3_PASCALVINCENT_TYPEMAP[ty]
s = [get_int(data[4 * (i + 1): 4 * (i + 2)]) for i in range(nd)]
parsed = np.frombuffer(data, dtype=m[1], offset=(4 * (nd + 1)))
assert parsed.shape[0] == np.prod(s) or not strict
return torch.from_numpy(parsed.astype(m[2], copy=False)).view(*s)
def read_label_file(path: str) -> torch.Tensor:
with open(path, 'rb') as f:
x = read_sn3_pascalvincent_tensor(f, strict=False)
assert(x.dtype == torch.uint8)
assert(x.ndimension() == 1)
return x.long()
def read_image_file(path: str) -> torch.Tensor:
with open(path, 'rb') as f:
x = read_sn3_pascalvincent_tensor(f, strict=False)
assert(x.dtype == torch.uint8)
assert(x.ndimension() == 3)
return x
