SVHN.py

from torchvision.datasets.vision import VisionDataset
from PIL import Image
import os
import os.path
import numpy as np


class SVHN(VisionDataset):
    """`SVHN <http://ufldl.stanford.edu/housenumbers/>`_ 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.

    """

    split_list = {
        'train': ["http://ufldl.stanford.edu/housenumbers/train_32x32.mat",
                  "merge_32x32.mat"],
        'test': ["http://ufldl.stanford.edu/housenumbers/test_32x32.mat",
                 "test_32x32.mat",]}

    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]

        # import here rather than at top of file because this is
        # an optional dependency for torchvision
        import scipy.io as sio

        # reading(loading) mat file as array
        loaded_mat = sio.loadmat(os.path.join(self.root, self.filename))

        self.data = 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]
        np.place(self.labels, self.labels == 10, 0)
        self.data = np.transpose(self.data, (3, 2, 0, 1))

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

        Returns:
            tuple: (image, target) where target is index of the target class.
        """
        img, target = self.data[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(self.data)