Source code for torchvision.datasets.svhn

from .vision import VisionDataset
from PIL import Image
import os
import os.path
import numpy as np
from typing import Any, Callable, Optional, Tuple
from .utils import download_url, check_integrity, verify_str_arg

[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]` .. warning:: This class needs `scipy <>`_ to load data from `.mat` format. 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. """ split_list = { 'train': ["", "train_32x32.mat", "e26dedcc434d2e4c54c9b2d4a06d8373"], 'test': ["", "test_32x32.mat", "eb5a983be6a315427106f1b164d9cef3"], 'extra': ["", "extra_32x32.mat", "a93ce644f1a588dc4d68dda5feec44a7"]} def __init__( self, root: str, split: str = "train", transform: Optional[Callable] = None, target_transform: Optional[Callable] = None, download: bool = False, ) -> None: super(SVHN, self).__init__(root, transform=transform, target_transform=target_transform) self.split = verify_str_arg(split, "split", tuple(self.split_list.keys())) 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: int) -> Tuple[Any, Any]: """ 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) -> int: return len( def _check_integrity(self) -> bool: 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) -> None: md5 = self.split_list[self.split][2] download_url(self.url, self.root, self.filename, md5) def extra_repr(self) -> str: 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