pytorch 定义自己的数据集

class MNIST(data.Dataset):
    def __init__(self, root, train=True, transform=None, target_transform=None, download=False):
        self.root = root
        self.transform = transform
        self.target_transform = target_transform
        self.train = train  # training set or test set

        if download:
            self.download()

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

        if self.train:
            self.train_data, self.train_labels = torch.load(
                os.path.join(root, self.processed_folder, self.training_file))
        else:
            self.test_data, self.test_labels = torch.load(os.path.join(root, self.processed_folder, self.test_file))

    def __getitem__(self, index):
        if self.train:
            img, target = self.train_data[index], self.train_labels[index]
        else:
            img, target = self.test_data[index], self.test_labels[index]

        # doing this so that it is consistent with all other datasets
        # to return a PIL Image
        img = Image.fromarray(img.numpy(), mode='L')

        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):
        if self.train:
            return 60000
        else:
            return 10000

链接:https://www.pytorchtutorial.com/pytorch-note4-input-data-pipeline/