stl10.py

from __future__ import print_function
from PIL import Image
import os
import os.path
import numpy as np

from .vision import VisionDataset
from .utils import check_integrity, download_and_extract_archive


class STL10(VisionDataset):
    """`STL10 <https://cs.stanford.edu/~acoates/stl10/>`_ Dataset.

    Args:
        root (string): Root directory of dataset where directory
            ``stl10_binary`` exists.
        split (string): One of {'train', 'test', 'unlabeled', 'train+unlabeled'}.
            Accordingly dataset is selected.
        folds (int, optional): One of {0-9} or None.
            For training, loads one of the 10 pre-defined folds of 1k samples for the
             standard evaluation procedure. If no value is passed, loads the 5k samples.
        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.
        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.

    """
    base_folder = 'stl10_binary'
    url = "http://ai.stanford.edu/~acoates/stl10/stl10_binary.tar.gz"
    filename = "stl10_binary.tar.gz"
    tgz_md5 = '91f7769df0f17e558f3565bffb0c7dfb'
    class_names_file = 'class_names.txt'
    folds_list_file = 'fold_indices.txt'
    train_list = [
        ['train_X.bin', '918c2871b30a85fa023e0c44e0bee87f'],
        ['train_y.bin', '5a34089d4802c674881badbb80307741'],
        ['unlabeled_X.bin', '5242ba1fed5e4be9e1e742405eb56ca4']
    ]

    test_list = [
        ['test_X.bin', '7f263ba9f9e0b06b93213547f721ac82'],
        ['test_y.bin', '36f9794fa4beb8a2c72628de14fa638e']
    ]
    splits = ('train', 'train+unlabeled', 'unlabeled', 'test')

    def __init__(self, root, split='train', folds=None, transform=None,
                 target_transform=None, download=False):
        if split not in self.splits:
            raise ValueError('Split "{}" not found. Valid splits are: {}'.format(
                split, ', '.join(self.splits),
            ))
        super(STL10, self).__init__(root, transform=transform,
                                    target_transform=target_transform)
        self.split = split  # train/test/unlabeled set
        self.folds = folds  # one of the 10 pre-defined folds or the full dataset

        if download:
            self.download()

        if not self._check_integrity():
            raise RuntimeError(
                'Dataset not found or corrupted. '
                'You can use download=True to download it')

        # now load the picked numpy arrays
        if self.split == 'train':
            self.data, self.labels = self.__loadfile(
                self.train_list[0][0], self.train_list[1][0])
            self.__load_folds(folds)

        elif self.split == 'train+unlabeled':
            self.data, self.labels = self.__loadfile(
                self.train_list[0][0], self.train_list[1][0])
            self.__load_folds(folds)
            unlabeled_data, _ = self.__loadfile(self.train_list[2][0])
            self.data = np.concatenate((self.data, unlabeled_data))
            self.labels = np.concatenate(
                (self.labels, np.asarray([-1] * unlabeled_data.shape[0])))

        elif self.split == 'unlabeled':
            self.data, _ = self.__loadfile(self.train_list[2][0])
            self.labels = np.asarray([-1] * self.data.shape[0])
        else:  # self.split == 'test':
            self.data, self.labels = self.__loadfile(
                self.test_list[0][0], self.test_list[1][0])

        class_file = os.path.join(
            self.root, self.base_folder, self.class_names_file)
        if os.path.isfile(class_file):
            with open(class_file) as f:
                self.classes = f.read().splitlines()

    def __getitem__(self, index):
        """
        Args:
            index (int): Index

        Returns:
            tuple: (image, target) where target is index of the target class.
        """
        if self.labels is not None:
            img, target = self.data[index], int(self.labels[index])
        else:
            img, target = self.data[index], None

        # doing this so that it is consistent with all other datasets
        # to return a PIL Image
        img = Image.fromarray(np.transpose(img, (1, 2, 0)))

        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):
        return self.data.shape[0]

    def __loadfile(self, data_file, labels_file=None):
        labels = None
        if labels_file:
            path_to_labels = os.path.join(
                self.root, self.base_folder, labels_file)
            with open(path_to_labels, 'rb') as f:
                labels = np.fromfile(f, dtype=np.uint8) - 1  # 0-based

        path_to_data = os.path.join(self.root, self.base_folder, data_file)
        with open(path_to_data, 'rb') as f:
            # read whole file in uint8 chunks
            everything = np.fromfile(f, dtype=np.uint8)
            images = np.reshape(everything, (-1, 3, 96, 96))
            images = np.transpose(images, (0, 1, 3, 2))

        return images, labels

    def _check_integrity(self):
        root = self.root
        for fentry in (self.train_list + self.test_list):
            filename, md5 = fentry[0], fentry[1]
            fpath = os.path.join(root, self.base_folder, filename)
            if not check_integrity(fpath, md5):
                return False
        return True

    def download(self):
        if self._check_integrity():
            print('Files already downloaded and verified')
            return
        download_and_extract_archive(self.url, self.root, filename=self.filename, md5=self.tgz_md5)

    def extra_repr(self):
        return "Split: {split}".format(**self.__dict__)

    def __load_folds(self, folds):
        # loads one of the folds if specified
        if isinstance(folds, int):
            if folds >= 0 and folds < 10:
                path_to_folds = os.path.join(
                    self.root, self.base_folder, self.folds_list_file)
                with open(path_to_folds, 'r') as f:
                    str_idx = f.read().splitlines()[folds]
                    list_idx = np.fromstring(str_idx, dtype=np.uint8, sep=' ')
                    self.data, self.labels = self.data[list_idx, :, :, :], self.labels[list_idx]
            else:
                raise ValueError('Folds "{}" not found. Valid splits are: 0-9.'.format(folds))