Source code for torchvision.datasets.stl10

from __future__ import print_function
import as data
from PIL import Image
import os
import os.path
import errno
import numpy as np
import sys
from .cifar import CIFAR10

[docs]class STL10(CIFAR10): """`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. 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 = "" filename = "stl10_binary.tar.gz" tgz_md5 = '91f7769df0f17e558f3565bffb0c7dfb' class_names_file = 'class_names.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'] ] def __init__(self, root, split='train', transform=None, target_transform=None, download=False): self.root = os.path.expanduser(root) self.transform = transform self.target_transform = target_transform self.split = split # train/test/unlabeled set if 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.labels = self.__loadfile( self.train_list[0][0], self.train_list[1][0]) elif self.split == 'train+unlabeled':, self.labels = self.__loadfile( self.train_list[0][0], self.train_list[1][0]) unlabeled_data, _ = self.__loadfile(self.train_list[2][0]) = np.concatenate((, unlabeled_data)) self.labels = np.concatenate( (self.labels, np.asarray([-1] * unlabeled_data.shape[0]))) elif self.split == 'unlabeled':, _ = self.__loadfile(self.train_list[2][0]) self.labels = np.asarray([-1] *[0]) else: # self.split == 'test':, 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 =
[docs] 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 =[index], int(self.labels[index]) else: img, target =[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[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