Source code for torchvision.datasets.svhn

from __future__ import print_function
from .vision import VisionDataset
from PIL import Image
import os
import os.path
import numpy as np
from .utils import download_url, check_integrity

[docs]class SVHN(VisionDataset): """`SVHN <>`_ Dataset. Note: The SVHN dataset assigns the label `10` to the digit `0`. However, in this Dataset, we assign the label `0` to the digit `0` to be compatible with PyTorch loss functions which expect the class labels to be in the range `[0, C-1]` Args: root (string): Root directory of dataset where directory ``SVHN`` exists. split (string): One of {'train', 'test', 'extra'}. Accordingly dataset is selected. 'extra' is Extra training set. 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. """ url = "" filename = "" file_md5 = "" split_list = { 'train': ["", "train_32x32.mat", "e26dedcc434d2e4c54c9b2d4a06d8373"], 'test': ["", "test_32x32.mat", "eb5a983be6a315427106f1b164d9cef3"], 'extra': ["", "extra_32x32.mat", "a93ce644f1a588dc4d68dda5feec44a7"]} def __init__(self, root, split='train', transform=None, target_transform=None, download=False): super(SVHN, self).__init__(root) self.transform = transform self.target_transform = target_transform self.split = split # training set or test set or extra set if self.split not in self.split_list: raise ValueError('Wrong split entered! Please use split="train" ' 'or split="extra" or split="test"') self.url = self.split_list[split][0] self.filename = self.split_list[split][1] self.file_md5 = self.split_list[split][2] if download: if not self._check_integrity(): raise RuntimeError('Dataset not found or corrupted.' + ' You can use download=True to download it') # import here rather than at top of file because this is # an optional dependency for torchvision import as sio # reading(loading) mat file as array loaded_mat = sio.loadmat(os.path.join(self.root, self.filename)) = loaded_mat['X'] # loading from the .mat file gives an np array of type np.uint8 # converting to np.int64, so that we have a LongTensor after # the conversion from the numpy array # the squeeze is needed to obtain a 1D tensor self.labels = loaded_mat['y'].astype(np.int64).squeeze() # the svhn dataset assigns the class label "10" to the digit 0 # this makes it inconsistent with several loss functions # which expect the class labels to be in the range [0, C-1], self.labels == 10, 0) = np.transpose(, (3, 2, 0, 1))
[docs] def __getitem__(self, index): """ Args: index (int): Index Returns: tuple: (image, target) where target is index of the target class. """ img, target =[index], int(self.labels[index]) # 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 len( def _check_integrity(self): root = self.root md5 = self.split_list[self.split][2] fpath = os.path.join(root, self.filename) return check_integrity(fpath, md5) def download(self): md5 = self.split_list[self.split][2] download_url(self.url, self.root, self.filename, md5) def extra_repr(self): return "Split: {split}".format(**self.__dict__)


Access comprehensive developer documentation for PyTorch

View Docs


Get in-depth tutorials for beginners and advanced developers

View Tutorials


Find development resources and get your questions answered

View Resources