Python torchvision.transforms.RandomHorizontalFlip() Examples

def load_data(root_path, dir, batch_size, phase):
    transform_dict = {
        'src': transforms.Compose(
        [transforms.RandomResizedCrop(224),
         transforms.RandomHorizontalFlip(),
         transforms.ToTensor(),
         transforms.Normalize(mean=[0.485, 0.456, 0.406],
                              std=[0.229, 0.224, 0.225]),
         ]),
        'tar': transforms.Compose(
        [transforms.Resize(224),
         transforms.ToTensor(),
         transforms.Normalize(mean=[0.485, 0.456, 0.406],
                              std=[0.229, 0.224, 0.225]),
         ])}
    data = datasets.ImageFolder(root=root_path + dir, transform=transform_dict[phase])
    data_loader = torch.utils.data.DataLoader(data, batch_size=batch_size, shuffle=True, drop_last=False, num_workers=4)
    return data_loader 

def load_training(root_path, dir, batch_size, kwargs):

    transform = transforms.Compose(
        [transforms.Resize([256, 256]),
         transforms.RandomCrop(224),
         transforms.RandomHorizontalFlip(),
         transforms.ToTensor()])
    data = datasets.ImageFolder(root=root_path + dir, transform=transform)
    train_loader = torch.utils.data.DataLoader(data, batch_size=batch_size, shuffle=True, drop_last=True, **kwargs)
    return train_loader 

def data_loader(root, batch_size=256, workers=1, pin_memory=True):
    traindir = os.path.join(root, 'ILSVRC2012_img_train')
    valdir = os.path.join(root, 'ILSVRC2012_img_val')
    normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225])

    train_dataset = datasets.ImageFolder(
        traindir,
        transforms.Compose([
            transforms.RandomResizedCrop(224),
            transforms.RandomHorizontalFlip(),
            transforms.ToTensor(),
            normalize
        ])
    )
    val_dataset = datasets.ImageFolder(
        valdir,
        transforms.Compose([
            transforms.Resize(256),
            transforms.CenterCrop(224),
            transforms.ToTensor(),
            normalize
        ])
    )

    train_loader = torch.utils.data.DataLoader(
        train_dataset,
        batch_size=batch_size,
        shuffle=True,
        num_workers=workers,
        pin_memory=pin_memory,
        sampler=None
    )
    val_loader = torch.utils.data.DataLoader(
        val_dataset,
        batch_size=batch_size,
        shuffle=False,
        num_workers=workers,
        pin_memory=pin_memory
    )
    return train_loader, val_loader 

def main():
    best_acc = 0

    device = 'cuda' if torch.cuda.is_available() else 'cpu'

    print('==> Preparing data..')
    transforms_train = transforms.Compose([
        transforms.RandomCrop(32, padding=4),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])

    dataset_train = CIFAR10(root='../data', train=True, download=True, 
                            transform=transforms_train)

    train_loader = DataLoader(dataset_train, batch_size=args.batch_size, 
                              shuffle=True, num_workers=args.num_worker)

    # there are 10 classes so the dataset name is cifar-10
    classes = ('plane', 'car', 'bird', 'cat', 'deer', 
               'dog', 'frog', 'horse', 'ship', 'truck')

    print('==> Making model..')

    net = pyramidnet()
    net = nn.DataParallel(net)
    net = net.to(device)
    num_params = sum(p.numel() for p in net.parameters() if p.requires_grad)
    print('The number of parameters of model is', num_params)

    criterion = nn.CrossEntropyLoss()
    optimizer = optim.Adam(net.parameters(), lr=args.lr)
    # optimizer = optim.SGD(net.parameters(), lr=args.lr, 
    #                       momentum=0.9, weight_decay=1e-4)
    
    train(net, criterion, optimizer, train_loader, device) 

def get_rot_train_transformers(args):
    size = args.img_transform.random_resize_crop.size
    scale = args.img_transform.random_resize_crop.scale
    img_tr = [transforms.RandomResizedCrop((int(size[0]), int(size[1])), (scale[0], scale[1]))]
    if args.img_transform.random_horiz_flip > 0.0:
        img_tr.append(transforms.RandomHorizontalFlip(args.img_transform.random_horiz_flip))
    if args.img_transform.jitter > 0.0:
        img_tr.append(transforms.ColorJitter(
            brightness=args.img_transform.jitter, contrast=args.img_transform.jitter,
            saturation=args.jitter, hue=min(0.5, args.jitter)))

    mean = args.normalize.mean
    std = args.normalize.std
    img_tr += [transforms.ToTensor(), transforms.Normalize(mean=mean, std=std)]

    return transforms.Compose(img_tr) 

def load_train(root_path, dir, batch_size, phase):
    transform_dict = {
        'src': transforms.Compose(
            [transforms.RandomResizedCrop(224),
             transforms.RandomHorizontalFlip(),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ]),
        'tar': transforms.Compose(
            [transforms.Resize(224),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ])}
    data = datasets.ImageFolder(root=root_path + dir, transform=transform_dict[phase])
    train_size = int(0.8 * len(data))
    test_size = len(data) - train_size
    data_train, data_val = torch.utils.data.random_split(data, [train_size, test_size])
    train_loader = torch.utils.data.DataLoader(data_train, batch_size=batch_size, shuffle=True, drop_last=False, num_workers=4)
    val_loader = torch.utils.data.DataLoader(data_val, batch_size=batch_size, shuffle=True, drop_last=False, num_workers=4)
    return train_loader, val_loader 

def load_data(data_folder, batch_size, train, kwargs):
    transform = {
        'train': transforms.Compose(
            [transforms.Resize([256, 256]),
                transforms.RandomCrop(224),
                transforms.RandomHorizontalFlip(),
                transforms.ToTensor(),
                transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225])]),
        'test': transforms.Compose(
            [transforms.Resize([224, 224]),
                transforms.ToTensor(),
                transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225])])
        }
    data = datasets.ImageFolder(root = data_folder, transform=transform['train' if train else 'test'])
    data_loader = torch.utils.data.DataLoader(data, batch_size=batch_size, shuffle=True, **kwargs, drop_last = True if train else False)
    return data_loader 

def load_imageclef_test(root_path, domain, batch_size, phase):
    transform_dict = {
        'src': transforms.Compose(
            [transforms.Resize((256,256)),
             transforms.RandomCrop(224),
             transforms.RandomHorizontalFlip(),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ]),
        'tar': transforms.Compose(
            [transforms.Resize((224, 224)),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ])}
    data = ImageCLEF(root_dir=root_path, domain=domain, transform=transform_dict[phase])
    data_loader = torch.utils.data.DataLoader(data, batch_size=batch_size, shuffle=True, drop_last=False, num_workers=4)
    return data_loader 

def transform(is_train=True, normalize=True):
    """
    Returns a transform object
    """
    filters = []
    filters.append(Scale(256))

    if is_train:
        filters.append(RandomCrop(224))
    else:
        filters.append(CenterCrop(224))

    if is_train:
        filters.append(RandomHorizontalFlip())

    filters.append(ToTensor())
    if normalize:
        filters.append(Normalize(mean=[0.485, 0.456, 0.406],
                                 std=[0.229, 0.224, 0.225]))
    return Compose(filters) 

def _data_transforms_cifar10(cutout_size):
    CIFAR_MEAN = [0.49139968, 0.48215827, 0.44653124]
    CIFAR_STD = [0.24703233, 0.24348505, 0.26158768]

    train_transform = transforms.Compose([
        transforms.RandomCrop(32, padding=4),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize(CIFAR_MEAN, CIFAR_STD),
    ])
    if cutout_size is not None:
        train_transform.transforms.append(Cutout(cutout_size))

    valid_transform = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize(CIFAR_MEAN, CIFAR_STD),
        ])
    return train_transform, valid_transform 

def preprocess(self):
        if self.train:
            return transforms.Compose([
                transforms.RandomResizedCrop(self.image_size),
                transforms.RandomHorizontalFlip(),
                transforms.ColorJitter(brightness=0.4, contrast=0.4, saturation=0.4, hue=0.2),
                transforms.ToTensor(),
                transforms.Normalize(self.mean, self.std),
            ])
        else:
            return transforms.Compose([
                transforms.Resize((int(self.image_size / 0.875), int(self.image_size / 0.875))),
                transforms.CenterCrop(self.image_size),
                transforms.ToTensor(),
                transforms.Normalize(self.mean, self.std),
            ]) 

def im_detect_bbox_hflip(model, images, target_scale, target_max_size, device):
    """
    Performs bbox detection on the horizontally flipped image.
    Function signature is the same as for im_detect_bbox.
    """
    transform = TT.Compose([
        T.Resize(target_scale, target_max_size),
        TT.RandomHorizontalFlip(1.0),
        TT.ToTensor(),
        T.Normalize(
            mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD, to_bgr255=cfg.INPUT.TO_BGR255
        )
    ])
    images = [transform(image) for image in images]
    images = to_image_list(images, cfg.DATALOADER.SIZE_DIVISIBILITY)
    boxlists = model(images.to(device))

    # Invert the detections computed on the flipped image
    boxlists_inv = [boxlist.transpose(0) for boxlist in boxlists]
    return boxlists_inv 

def __init__(self, noisy_dir, crop_size, upscale_factor=4, cropped=False, flips=False, rotations=False, **kwargs):
        super(TrainDataset, self).__init__()
        # get all directories used for training
        if isinstance(noisy_dir, str):
            noisy_dir = [noisy_dir]
        self.files = []
        for n_dir in noisy_dir:
            self.files += [join(n_dir, x) for x in listdir(n_dir) if utils.is_image_file(x)]
        # intitialize image transformations and variables
        self.input_transform = T.Compose([
            T.RandomVerticalFlip(0.5 if flips else 0.0),
            T.RandomHorizontalFlip(0.5 if flips else 0.0),
            T.RandomCrop(crop_size)
        ])
        self.crop_transform = T.RandomCrop(crop_size // upscale_factor)
        self.upscale_factor = upscale_factor
        self.cropped = cropped
        self.rotations = rotations 

def __init__(self, path, classes, stage='train'):
        self.data = []
        for i, c in enumerate(classes):
            cls_path = osp.join(path, c)
            images = os.listdir(cls_path)
            for image in images:
                self.data.append((osp.join(cls_path, image), i))

        normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                         std=[0.229, 0.224, 0.225])
        
        if stage == 'train':
            self.transforms = transforms.Compose([transforms.RandomResizedCrop(224),
                                                  transforms.RandomHorizontalFlip(),
                                                  transforms.ToTensor(),
                                                  normalize])
        if stage == 'test':
            self.transforms = transforms.Compose([transforms.Resize(256),
                                                  transforms.CenterCrop(224),
                                                  transforms.ToTensor(),
                                                  normalize]) 

def __init__(self, patches, use_cache, augment_data):
        super(PatchDataset, self).__init__()
        self.patches = patches
        self.crop = CenterCrop(config.CROP_SIZE)

        if augment_data:
            self.random_transforms = [RandomRotation((90, 90)), RandomVerticalFlip(1.0), RandomHorizontalFlip(1.0),
                                      (lambda x: x)]
            self.get_aug_transform = (lambda: random.sample(self.random_transforms, 1)[0])
        else:
            # Transform does nothing. Not sure if horrible or very elegant...
            self.get_aug_transform = (lambda: (lambda x: x))

        if use_cache:
            self.load_patch = data_manager.load_cached_patch
        else:
            self.load_patch = data_manager.load_patch

        print('Dataset ready with {} tuples.'.format(len(patches))) 

def load_imageclef_train(root_path, domain, batch_size, phase):
    transform_dict = {
        'src': transforms.Compose(
            [transforms.Resize((256, 256)),
             transforms.RandomCrop(224),
             transforms.RandomHorizontalFlip(),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ]),
        'tar': transforms.Compose(
            [transforms.Resize((224, 224)),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ])}
    data = ImageCLEF(root_dir=root_path, domain=domain, transform=transform_dict[phase])
    train_size = int(0.8 * len(data))
    test_size = len(data) - train_size
    data_train, data_val = torch.utils.data.random_split(data, [train_size, test_size])
    train_loader = torch.utils.data.DataLoader(data_train, batch_size=batch_size, shuffle=True, drop_last=False,
                                               num_workers=4)
    val_loader = torch.utils.data.DataLoader(data_val, batch_size=batch_size, shuffle=True, drop_last=False,
                                             num_workers=4)
    return train_loader, val_loader 

def load_data(data_folder, batch_size, phase='train', train_val_split=True, train_ratio=.8):
    transform_dict = {
        'train': transforms.Compose(
            [transforms.Resize(256),
             transforms.RandomCrop(224),
             transforms.RandomHorizontalFlip(),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ]),
        'test': transforms.Compose(
            [transforms.Resize(224),
             transforms.ToTensor(),
             transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                  std=[0.229, 0.224, 0.225]),
             ])}

    data = datasets.ImageFolder(root=data_folder, transform=transform_dict[phase])
    if phase == 'train':
        if train_val_split:
            train_size = int(train_ratio * len(data))
            test_size = len(data) - train_size
            data_train, data_val = torch.utils.data.random_split(data, [train_size, test_size])
            train_loader = torch.utils.data.DataLoader(data_train, batch_size=batch_size, shuffle=True, drop_last=True,
                                                    num_workers=4)
            val_loader = torch.utils.data.DataLoader(data_val, batch_size=batch_size, shuffle=False, drop_last=False,
                                                num_workers=4)
            return [train_loader, val_loader]
        else:
            train_loader = torch.utils.data.DataLoader(data, batch_size=batch_size, shuffle=True, drop_last=True,
                                                    num_workers=4)
            return train_loader
    else: 
        test_loader = torch.utils.data.DataLoader(data, batch_size=batch_size, shuffle=False, drop_last=False,
                                                    num_workers=4)
        return test_loader

## Below are for ImageCLEF datasets 

def init_dataset():
    transform_train = transforms.Compose(
        [transforms.Resize(256),
         transforms.RandomCrop(227),
         transforms.RandomHorizontalFlip(),
         transforms.ToTensor(),
         transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])
    transform_test = transforms.Compose(
        [transforms.Resize(227),
         transforms.ToTensor(),
         transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])
    trainset = datasets.CIFAR10(root='./data', train=True, download=True,
                                transform=transform_train)
    trainloader = torch.utils.data.DataLoader(trainset, batch_size=128,
                                              shuffle=True, num_workers=0)

    testset = datasets.CIFAR10(root='./data', train=False, download=True,
                               transform=transform_test)
    testloader = torch.utils.data.DataLoader(testset, batch_size=100,
                                             shuffle=True, num_workers=0)
    return trainloader, testloader 

def get_jig_train_transformers(args):
    size = args.img_transform.random_resize_crop.size
    scale = args.img_transform.random_resize_crop.scale
    img_tr = [transforms.RandomResizedCrop((int(size[0]), int(size[1])), (scale[0], scale[1]))]
    if args.img_transform.random_horiz_flip > 0.0:
        img_tr.append(transforms.RandomHorizontalFlip(args.img_transform.random_horiz_flip))
    if args.img_transform.jitter > 0.0:
        img_tr.append(transforms.ColorJitter(
            brightness=args.img_transform.jitter, contrast=args.img_transform.jitter,
            saturation=args.jitter, hue=min(0.5, args.jitter)))

    tile_tr = []
    if args.jig_transform.tile_random_grayscale:
        tile_tr.append(transforms.RandomGrayscale(args.jig_transform.tile_random_grayscale))
    mean = args.normalize.mean
    std = args.normalize.std
    tile_tr = tile_tr + [transforms.ToTensor(), transforms.Normalize(mean=mean, std=std)]

    return transforms.Compose(img_tr), transforms.Compose(tile_tr) 

def cifar10():
    transform_train = transforms.Compose([
        transforms.RandomCrop(32, padding=4),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
    ])
    transform_test = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
    ])
    trainset = MyCIFAR10.CIFAR10(root='./data', train=True, download=True, transform=transform_train, seed=0)
    valset = MyCIFAR10.CIFAR10(root='./data', train=True, download=True, transform=transform_test, seed=0)
    testset = MyCIFAR10.CIFAR10(root='./data', train=False, download=True, transform=transform_test, seed=0)
    net_func = MyNet.CifarAE
    return net_func, trainset, valset, testset 

def cifar10():
    transform_train = transforms.Compose([
        transforms.RandomCrop(32, padding=4),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
    ])
    transform_test = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
    ])
    trainset = MyCIFAR10.CIFAR10(root='./data', train=True, download=True, transform=transform_train, seed=0)
    valset = MyCIFAR10.CIFAR10(root='./data', train=True, download=True, transform=transform_test, seed=0)
    testset = MyCIFAR10.CIFAR10(root='./data', train=False, download=True, transform=transform_test, seed=0)
    net_func = MyNet.CifarNet
    return net_func, trainset, valset, testset 

def cifar10_train_transform(ds_metainfo,
                            mean_rgb=(0.4914, 0.4822, 0.4465),
                            std_rgb=(0.2023, 0.1994, 0.2010),
                            jitter_param=0.4):
    assert (ds_metainfo is not None)
    assert (ds_metainfo.input_image_size[0] == 32)
    return transforms.Compose([
        transforms.RandomCrop(
            size=32,
            padding=4),
        transforms.RandomHorizontalFlip(),
        transforms.ColorJitter(
            brightness=jitter_param,
            contrast=jitter_param,
            saturation=jitter_param),
        transforms.ToTensor(),
        transforms.Normalize(
            mean=mean_rgb,
            std=std_rgb)
    ]) 

def make(sz_resize = 256, sz_crop = 227, mean = [104, 117, 128],
        std = [1, 1, 1], rgb_to_bgr = True, is_train = True,
        intensity_scale = None):
    return transforms.Compose([
        RGBToBGR() if rgb_to_bgr else Identity(),
        transforms.RandomResizedCrop(sz_crop) if is_train else Identity(),
        transforms.Resize(sz_resize) if not is_train else Identity(),
        transforms.CenterCrop(sz_crop) if not is_train else Identity(),
        transforms.RandomHorizontalFlip() if is_train else Identity(),
        transforms.ToTensor(),
        ScaleIntensities(
            *intensity_scale) if intensity_scale is not None else Identity(),
        transforms.Normalize(
            mean=mean,
            std=std,
        )
    ]) 

def __init__(
        self,
        crop_size: int = ImagenetConstants.CROP_SIZE,
        mean: List[float] = ImagenetConstants.MEAN,
        std: List[float] = ImagenetConstants.STD,
    ):
        """The constructor method of ImagenetAugmentTransform class.

        Args:
            crop_size: expected output size per dimension after random cropping
            mean: a 3-tuple denoting the pixel RGB mean
            std: a 3-tuple denoting the pixel RGB standard deviation

        """
        self.transform = transforms.Compose(
            [
                transforms.RandomResizedCrop(crop_size),
                transforms.RandomHorizontalFlip(),
                transforms.ToTensor(),
                transforms.Normalize(mean=mean, std=std),
            ]
        ) 

def im_detect_bbox_hflip(model, images, target_scale, target_max_size, device):
    """
    Performs bbox detection on the horizontally flipped image.
    Function signature is the same as for im_detect_bbox.
    """
    transform = TT.Compose([
        T.Resize(target_scale, target_max_size),
        TT.RandomHorizontalFlip(1.0),
        TT.ToTensor(),
        T.Normalize(
            mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD, to_bgr255=cfg.INPUT.TO_BGR255
        )
    ])
    images = [transform(image) for image in images]
    images = to_image_list(images, cfg.DATALOADER.SIZE_DIVISIBILITY)
    boxlists = model(images.to(device))

    # Invert the detections computed on the flipped image
    boxlists_inv = [boxlist.transpose(0) for boxlist in boxlists]
    return boxlists_inv 

def get_transform(opt):
    transform_list = []
    if opt.resize_or_crop == 'resize_and_crop':
        osize = [opt.loadSize, opt.loadSize]
        transform_list.append(transforms.Scale(osize, Image.BICUBIC))
        transform_list.append(transforms.RandomCrop(opt.fineSize))
    elif opt.resize_or_crop == 'crop':
        transform_list.append(transforms.RandomCrop(opt.fineSize))
    elif opt.resize_or_crop == 'scale_width':
        transform_list.append(transforms.Lambda(
            lambda img: __scale_width(img, opt.fineSize)))
    elif opt.resize_or_crop == 'scale_width_and_crop':
        transform_list.append(transforms.Lambda(
            lambda img: __scale_width(img, opt.loadSize)))
        transform_list.append(transforms.RandomCrop(opt.fineSize))

    if opt.isTrain and not opt.no_flip:
        transform_list.append(transforms.RandomHorizontalFlip())

    transform_list += [transforms.ToTensor(),
                       transforms.Normalize((0.5, 0.5, 0.5),
                                            (0.5, 0.5, 0.5))]
    return transforms.Compose(transform_list) 

def __init__(self, root_path="CACD2000/", label_path="data/label.npy", name_path="data/name.npy", train_mode = "train"):
        """
        Initialize some variables
        Load labels & names
        define transform
        """
        self.root_path = root_path
        self.image_labels = np.load(label_path)
        self.image_names = np.load(name_path)
        self.train_mode = train_mode
        self.transform = {
            'train': transforms.Compose([                
                transforms.Resize(224),
                transforms.RandomHorizontalFlip(),
                transforms.ToTensor(),
 #               transforms.Normalize([0.656,0.487,0.411], [1., 1., 1.])
            ]),
            'val': transforms.Compose([
                transforms.Resize(224),
                transforms.ToTensor(),
 #               transforms.Normalize([0.656,0.487,0.411], [1., 1., 1.])
            ]),
        } 

def __init__(self, args, train=True):
        self.root_dir = args.data
        root_dir = self.root_dir
        if train:
            self.data_set_list = os.path.join(root_dir,
                                              args.trainset_image_list)
        else:
            self.data_set_list = os.path.join(root_dir, args.testset_image_list)

        self.categ_dict = get_class_names(
            os.path.join(root_dir, 'ClassName.txt'))

        self.data_set_list = parse_file(self.data_set_list, self.categ_dict)

        self.args = args
        self.read_features = args.read_features

        self.features_dir = args.features_dir
        if train:
            self.transform = transforms.Compose([
                transforms.RandomSizedCrop(args.image_size),
                transforms.RandomHorizontalFlip(),
                transforms.Scale((args.image_size, args.image_size)),
                transforms.ToTensor(),
                transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225]),
            ])
        else:
            self.transform = transforms.Compose([
                transforms.Scale((args.image_size, args.image_size)),
                transforms.ToTensor(),
                transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225]),
            ]) 

def cifar100(n_labels, data_root='./data-local/cifar100/'):
    channel_stats = dict(mean = [0.5071, 0.4867, 0.4408],
                         std = [0.2675, 0.2565, 0.2761])
    train_transform = transforms.Compose([
        transforms.Pad(2, padding_mode='reflect'),
        transforms.ColorJitter(brightness=0.4, contrast=0.4,
                               saturation=0.4, hue=0.1),
        transforms.RandomCrop(32),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize(**channel_stats)
    ])
    eval_transform = transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize(**channel_stats)
    ])
    trainset = tv.datasets.CIFAR100(data_root, train=True, download=True,
                                   transform=train_transform)
    evalset = tv.datasets.CIFAR100(data_root, train=False, download=True,
                                   transform=eval_transform)
    num_classes = 100
    label_per_class = n_labels // num_classes
    labeled_idxs, unlabed_idxs = split_relabel_data(
                                    np.array(trainset.train_labels),
                                    trainset.train_labels,
                                    label_per_class,
                                    num_classes)
    return {
        'trainset': trainset,
        'evalset': evalset,
        'labeled_idxs': labeled_idxs,
        'unlabeled_idxs': unlabed_idxs,
        'num_classes': num_classes
    } 

def get_data(split_id, data_dir, img_size, scale_size, batch_size,
             workers, train_list, val_list):
    root = data_dir

    normalizer = T.Normalize(mean=[0.485, 0.456, 0.406],
                             std=[0.229, 0.224, 0.225])  # RGB imagenet

    # with data augmentation 
    train_transformer = T.Compose([
        T.RandomResizedCrop(img_size),
        T.RandomHorizontalFlip(),
        T.ToTensor(),   # [0, 255] to [0.0, 1.0]
        normalizer,     #  normalize each channel of the input
     ])

    test_transformer = T.Compose([
        T.Resize(scale_size),
        T.CenterCrop(img_size),
        T.ToTensor(),
        normalizer,
    ])

    train_loader = DataLoader(
        Preprocessor(train_list, root=root,
                     transform=train_transformer),
        batch_size=batch_size, num_workers=workers,
        sampler=RandomSampler(train_list),
        pin_memory=True, drop_last=False)

    val_loader = DataLoader(
        Preprocessor(val_list, root=root,
                     transform=test_transformer),
        batch_size=batch_size, num_workers=workers,
        shuffle=False, pin_memory=True)

    return train_loader, val_loader