Python torchvision.transforms.Normalize() 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 __init__(self, args, train=True):
        self.root_dir = args.data

        if train:
            self.data_set_list = train_set_list
        elif args.use_test_for_val:
            self.data_set_list = test_set_list
        else:
            self.data_set_list = val_set_list

        self.data_set_list = ['%06d.png' % (x) for x in self.data_set_list]
        self.args = args
        self.read_features = args.read_features

        self.features_dir = args.features_dir
        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]),
        ])
        self.transform_segmentation = transforms.Compose([
            transforms.Scale((args.segmentation_size, args.segmentation_size)),
            transforms.ToTensor(),
        ]) 

def __init__(self):
        self.batch_size = 64
        self.test_batch_size = 100
        self.learning_rate = 0.01
        self.sgd_momentum = 0.9
        self.log_interval = 100
        # Fetch MNIST data set.
        self.train_loader = torch.utils.data.DataLoader(
            datasets.MNIST('/tmp/mnist/data', train=True, download=True, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,))
                ])),
            batch_size=self.batch_size,
            shuffle=True)
        self.test_loader = torch.utils.data.DataLoader(
            datasets.MNIST('/tmp/mnist/data', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,))
                ])),
            batch_size=self.test_batch_size,
            shuffle=True)
        self.network = Net()

    # Train the network for several epochs, validating after each epoch. 

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 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_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 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_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 __init__(self, train_mode, loader_params, dataset_params, augmentation_params):
        super().__init__(train_mode, loader_params, dataset_params, augmentation_params)

        self.image_transform = transforms.Compose([transforms.Grayscale(num_output_channels=3),
                                                   transforms.ToTensor(),
                                                   transforms.Normalize(mean=self.dataset_params.MEAN,
                                                                        std=self.dataset_params.STD),
                                                   ])
        self.mask_transform = transforms.Compose([transforms.Lambda(to_array),
                                                  transforms.Lambda(to_tensor),
                                                  ])

        self.image_augment_train = ImgAug(self.augmentation_params['image_augment_train'])
        self.image_augment_with_target_train = ImgAug(self.augmentation_params['image_augment_with_target_train'])
        self.image_augment_inference = ImgAug(self.augmentation_params['image_augment_inference'])
        self.image_augment_with_target_inference = ImgAug(
            self.augmentation_params['image_augment_with_target_inference'])

        if self.dataset_params.target_format == 'png':
            self.dataset = ImageSegmentationPngDataset
        elif self.dataset_params.target_format == 'json':
            self.dataset = ImageSegmentationJsonDataset
        else:
            raise Exception('files must be png or json') 

def __init__(self, train_mode, loader_params, dataset_params, augmentation_params):
        super().__init__(train_mode, loader_params, dataset_params, augmentation_params)

        self.image_transform = transforms.Compose([transforms.Resize((self.dataset_params.h, self.dataset_params.w)),
                                                   transforms.Grayscale(num_output_channels=3),
                                                   transforms.ToTensor(),
                                                   transforms.Normalize(mean=self.dataset_params.MEAN,
                                                                        std=self.dataset_params.STD),
                                                   ])
        self.mask_transform = transforms.Compose([transforms.Resize((self.dataset_params.h, self.dataset_params.w),
                                                                    interpolation=0),
                                                  transforms.Lambda(to_array),
                                                  transforms.Lambda(to_tensor),
                                                  ])

        self.image_augment_train = ImgAug(self.augmentation_params['image_augment_train'])
        self.image_augment_with_target_train = ImgAug(self.augmentation_params['image_augment_with_target_train'])

        if self.dataset_params.target_format == 'png':
            self.dataset = ImageSegmentationPngDataset
        elif self.dataset_params.target_format == 'json':
            self.dataset = ImageSegmentationJsonDataset
        else:
            raise Exception('files must be png or json') 

def __init__(self, loader_params, dataset_params, augmentation_params):
        super().__init__(loader_params, dataset_params, augmentation_params)

        self.image_transform = transforms.Compose([transforms.Resize((self.dataset_params.h, self.dataset_params.w)),
                                                   transforms.Grayscale(num_output_channels=3),
                                                   transforms.ToTensor(),
                                                   transforms.Normalize(mean=self.dataset_params.MEAN,
                                                                        std=self.dataset_params.STD),
                                                   ])
        self.mask_transform = transforms.Compose([transforms.Resize((self.dataset_params.h, self.dataset_params.w),
                                                                    interpolation=0),
                                                  transforms.Lambda(to_array),
                                                  transforms.Lambda(to_tensor),
                                                  ])

        self.dataset = ImageSegmentationTTADataset 

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 __init__(self):
        self.batch_size = 64
        self.test_batch_size = 100
        self.learning_rate = 0.0025
        self.sgd_momentum = 0.9
        self.log_interval = 100
        # Fetch MNIST data set.
        self.train_loader = torch.utils.data.DataLoader(
            datasets.MNIST('/tmp/mnist/data', train=True, download=True, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,))
                ])),
            batch_size=self.batch_size,
            shuffle=True)
        self.test_loader = torch.utils.data.DataLoader(
            datasets.MNIST('/tmp/mnist/data', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,))
                ])),
            batch_size=self.test_batch_size,
            shuffle=True)
        self.network = Net()

    # Train the network for one or more epochs, validating after each epoch. 

def __init__(self):
        self.batch_size = 64
        self.test_batch_size = 100
        self.learning_rate = 0.0025
        self.sgd_momentum = 0.9
        self.log_interval = 100
        # Fetch MNIST data set.
        self.train_loader = torch.utils.data.DataLoader(
            datasets.MNIST('/tmp/mnist/data', train=True, download=True, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,))
                ])),
            batch_size=self.batch_size,
            shuffle=True)
        self.test_loader = torch.utils.data.DataLoader(
            datasets.MNIST('/tmp/mnist/data', train=False, transform=transforms.Compose([
                transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,))
                ])),
            batch_size=self.test_batch_size,
            shuffle=True)
        self.network = Net()

    # Train the network for one or more epochs, validating after each epoch. 

def loaders_mnist(dataset, batch_size=64, cuda=0,
                  train_size=50000, val_size=10000, test_size=10000,
                  test_batch_size=1000, **kwargs):

    assert dataset == 'mnist'
    root = '{}/{}'.format(os.environ['VISION_DATA'], dataset)

    # Data loading code
    normalize = transforms.Normalize(mean=(0.1307,),
                                     std=(0.3081,))

    transform = transforms.Compose([transforms.ToTensor(), normalize])

    # define two datasets in order to have different transforms
    # on training and validation
    dataset_train = datasets.MNIST(root=root, train=True, transform=transform)
    dataset_val = datasets.MNIST(root=root, train=True, transform=transform)
    dataset_test = datasets.MNIST(root=root, train=False, transform=transform)

    return create_loaders(dataset_train, dataset_val,
                          dataset_test, train_size, val_size, test_size,
                          batch_size=batch_size,
                          test_batch_size=test_batch_size,
                          cuda=cuda, num_workers=0) 

def segment(self, image):
        # don't track tensors with autograd during prediction
        with torch.no_grad():
            mean, std = [0.485, 0.456, 0.406], [0.229, 0.224, 0.225]

            transform = Compose([ConvertImageMode(mode="RGB"), ImageToTensor(), Normalize(mean=mean, std=std)])
            image = transform(image)

            batch = image.unsqueeze(0).to(self.device)

            output = self.net(batch)

            output = output.cpu().data.numpy()
            output = output.squeeze(0)

            mask = output.argmax(axis=0).astype(np.uint8)

            mask = Image.fromarray(mask, mode="P")

            palette = make_palette(*self.dataset["common"]["colors"])
            mask.putpalette(palette)

            return mask 

def get_usps(train, get_dataset=False, batch_size=cfg.batch_size):
    """Get USPS dataset loader."""
    # image pre-processing
    pre_process = transforms.Compose([transforms.ToTensor(),
                                      transforms.Normalize(
                                          mean=cfg.dataset_mean,
                                          std=cfg.dataset_std)])

    # dataset and data loader
    usps_dataset = USPS(root=cfg.data_root,
                        train=train,
                        transform=pre_process,
                        download=True)

    if get_dataset:
        return usps_dataset
    else:
        usps_data_loader = torch.utils.data.DataLoader(
            dataset=usps_dataset,
            batch_size=batch_size,
            shuffle=True)
        return usps_data_loader 

def get_mnist_m(train, get_dataset=False, batch_size=cfg.batch_size):
    """Get MNIST-M dataset loader."""
    # image pre-processing
    pre_process = transforms.Compose([transforms.ToTensor(),
                                      transforms.Normalize(
                                          mean=cfg.dataset_mean,
                                          std=cfg.dataset_std)])

    # dataset and data loader
    mnist_m_dataset = MNIST_M(root=cfg.data_root,
                              train=train,
                              transform=pre_process,
                              download=True)

    if get_dataset:
        return mnist_m_dataset
    else:
        mnist_m_data_loader = torch.utils.data.DataLoader(
            dataset=mnist_m_dataset,
            batch_size=batch_size,
            shuffle=True)
        return mnist_m_data_loader 

def get_svhn(train, get_dataset=False, batch_size=cfg.batch_size):
    """Get SVHN dataset loader."""
    # image pre-processing
    pre_process = transforms.Compose([transforms.ToTensor(),
                                      transforms.Normalize(
                                          mean=cfg.dataset_mean,
                                          std=cfg.dataset_std)])

    # dataset and data loader
    svhn_dataset = datasets.SVHN(root=cfg.data_root,
                                 split='train' if train else 'test',
                                 transform=pre_process,
                                 download=True)

    if get_dataset:
        return svhn_dataset
    else:
        svhn_data_loader = torch.utils.data.DataLoader(
            dataset=svhn_dataset,
            batch_size=batch_size,
            shuffle=True)
        return svhn_data_loader 

def get_mnist(train, get_dataset=False, batch_size=cfg.batch_size):
    """Get MNIST dataset loader."""
    # image pre-processing
    convert_to_3_channels = transforms.Lambda(
        lambda x: torch.cat([x, x, x], 0))
    pre_process = transforms.Compose([transforms.ToTensor(),
                                      transforms.Normalize(
                                          mean=cfg.dataset_mean,
                                          std=cfg.dataset_std),
                                      convert_to_3_channels])

    # dataset and data loader
    mnist_dataset = datasets.MNIST(root=cfg.data_root,
                                   train=train,
                                   transform=pre_process,
                                   download=True)

    if get_dataset:
        return mnist_dataset
    else:
        mnist_data_loader = torch.utils.data.DataLoader(
            dataset=mnist_dataset,
            batch_size=batch_size,
            shuffle=True)
        return mnist_data_loader 

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 get_transform(params, image_size, num_channels):
    # Transforms for PIL Images: Gray <-> RGB
    Gray2RGB = transforms.Lambda(lambda x: x.convert('RGB'))
    RGB2Gray = transforms.Lambda(lambda x: x.convert('L'))

    transform = []
    # Does size request match original size?
    if not image_size == params.image_size:
        transform.append(transforms.Resize(image_size))
   
    # Does number of channels requested match original?
    if not num_channels == params.num_channels:
        if num_channels == 1:
            transform.append(RGB2Gray)
        elif num_channels == 3:
            transform.append(Gray2RGB)
        else:
            print('NumChannels should be 1 or 3', num_channels)
            raise Exception

    transform += [transforms.ToTensor(), 
            transforms.Normalize((params.mean,), (params.std,))]

    return transforms.Compose(transform) 

def get_transform(data_name, split_name, opt):
    normalizer = transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                      std=[0.229, 0.224, 0.225])
    t_list = []
    if split_name == 'train':
        t_list = [transforms.RandomSizedCrop(opt.crop_size),
                  transforms.RandomHorizontalFlip()]
    elif split_name == 'val':
        t_list = [transforms.Scale(256), transforms.CenterCrop(224)]
    elif split_name == 'test':
        t_list = [transforms.Scale(256), transforms.CenterCrop(224)]

    t_end = [transforms.ToTensor(), normalizer]
    transform = transforms.Compose(t_list + t_end)
    return transform 

def build_image_transforms(self):
        self.image_transform = transforms.Compose([
            transforms.Resize((224, 224)),
            transforms.ToTensor(),
            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
        ]) 

def __init__(self, config):
        self.config = config

        if config.data_mode == "imgs":
            transform = v_transforms.Compose(
                [v_transforms.ToTensor(),
                 v_transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))])

            dataset = v_datasets.ImageFolder(self.config.data_folder, transform=transform)

            self.dataset_len = len(dataset)

            self.num_iterations = (self.dataset_len + config.batch_size - 1) // config.batch_size

            self.loader = DataLoader(dataset,
                                     batch_size=config.batch_size,
                                     shuffle=True,
                                     num_workers=config.data_loader_workers,
                                     pin_memory=config.pin_memory)
        elif config.data_mode == "numpy":
            raise NotImplementedError("This mode is not implemented YET")
        else:
            raise Exception("Please specify in the json a specified mode in data_mode") 

def __init__(self, args, train=True):
        root_dir = args.data
        if train:
            json_file = os.path.join(root_dir, 'train.json')
        elif args.use_test_for_val:
            json_file = os.path.join(root_dir, 'test.json')
        else:
            json_file = os.path.join(root_dir, 'val.json')

        self.num_classes = args.num_classes
        self.sequence_length = args.sequence_length
        self.experiment_type = args.experiment_type
        self.regression = args.regression

        self.read_features = args.read_features
        self.frames_metadata, self.idx_to_fid, self.centroids = _read_labels(
            json_file, args.imus, args.sequence_length)

        self.root_dir = root_dir
        self.features_dir = args.features_dir
        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 __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 __init__(self, args, train=True):
        root_dir = args.data
        if train or args.read_feature_and_image:
            json_file = os.path.join(root_dir, 'train.json')
        elif args.use_test_for_val:
            json_file = os.path.join(root_dir, 'test.json')
        else:
            json_file = os.path.join(root_dir, 'val.json')

        self.num_classes = args.num_classes
        self.sequence_length = args.sequence_length
        self.experiment_type = args.experiment_type
        self.regression = args.regression
        self.args = args

        self.read_features = args.read_features
        self.frames_metadata, self.idx_to_fid, self.centroids = _read_labels(
            json_file, args.imus, args.sequence_length)

        self.root_dir = root_dir
        self.features_dir = args.features_dir
        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 load_data(domain, root_dir, batch_size):
    src_train_img, src_train_label, src_test_img, src_test_label = load_dataset(domain['src'], root_dir)
    tar_train_img, tar_train_label, tar_test_img, tar_test_label = load_dataset(domain['tar'], root_dir)
    transform = transforms.Compose([
        transforms.Resize(32),
        transforms.ToTensor(),
        transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
    ])
    data_src_train, data_src_test = GetDataset(src_train_img, src_train_label,
                                               transform), GetDataset(src_test_img,
                                                                      src_test_label,
                                                                      transform)
    data_tar_train, data_tar_test = GetDataset(tar_train_img, tar_train_label,
                                               transform), GetDataset(tar_test_img,
                                                                      tar_test_label,
                                                                      transform)
    dataloaders = {}
    dataloaders['src'] = torch.utils.data.DataLoader(data_src_train, batch_size=batch_size, shuffle=True,
                                                     drop_last=False,
                                                     num_workers=4)
    dataloaders['val'] = torch.utils.data.DataLoader(data_src_test, batch_size=batch_size, shuffle=True,
                                                     drop_last=False,
                                                     num_workers=4)
    dataloaders['tar'] = torch.utils.data.DataLoader(data_tar_train, batch_size=batch_size, shuffle=True,
                                                     drop_last=False,
                                                     num_workers=4)
    return dataloaders