Python torchvision.transforms.Compose() 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):
        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_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 transform_for_train(fixed_scale = 512, rotate_prob = 15):
    """
    Options:
    1.RandomCrop
    2.CenterCrop
    3.RandomHorizontalFlip
    4.Normalize
    5.ToTensor
    6.FixedResize
    7.RandomRotate
    """
    transform_list = [] 
    #transform_list.append(FixedResize(size = (fixed_scale, fixed_scale)))
    transform_list.append(RandomSized(fixed_scale))
    transform_list.append(RandomRotate(rotate_prob))
    transform_list.append(RandomHorizontalFlip())
    #transform_list.append(Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)))
    
    transform_list.append(Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)))
    transform_list.append(ToTensor())

    return transforms.Compose(transform_list) 

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 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, 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 _get_ds_val(self, images_spec, crop=False, truncate=False):
        img_to_tensor_t = [images_loader.IndexImagesDataset.to_tensor_uint8_transform()]
        if crop:
            img_to_tensor_t.insert(0, transforms.CenterCrop(crop))
        img_to_tensor_t = transforms.Compose(img_to_tensor_t)

        fixed_first = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'fixedimg.jpg')
        if not os.path.isfile(fixed_first):
            print(f'INFO: No file found at {fixed_first}')
            fixed_first = None

        ds = images_loader.IndexImagesDataset(
                images=images_loader.ImagesCached(
                        images_spec, self.config_dl.image_cache_pkl,
                        min_size=self.config_dl.val_glob_min_size),
                to_tensor_transform=img_to_tensor_t,
                fixed_first=fixed_first)  # fix a first image to have consistency in tensor board

        if truncate:
            ds = pe.TruncatedDataset(ds, num_elemens=truncate)

        return ds 

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 getTestingData(batch_size=64):

    __imagenet_stats = {'mean': [0.485, 0.456, 0.406],
                        'std': [0.229, 0.224, 0.225]}
    # scale = random.uniform(1, 1.5)
    transformed_testing = depthDataset(csv_file='./data/nyu2_test.csv',
                                       transform=transforms.Compose([
                                           Scale(240),
                                           CenterCrop([304, 228], [152, 114]),
                                           ToTensor(is_test=True),
                                           Normalize(__imagenet_stats['mean'],
                                                     __imagenet_stats['std'])
                                       ]))

    dataloader_testing = DataLoader(transformed_testing, batch_size,
                                    shuffle=False, num_workers=4, pin_memory=False)

    return dataloader_testing 

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 __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 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 __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 __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 get_data_loader(opt):
  if opt.dset_name == 'moving_mnist':
    transform = transforms.Compose([vtransforms.ToTensor()])
    dset = MovingMNIST(opt.dset_path, opt.is_train, opt.n_frames_input,
                       opt.n_frames_output, opt.num_objects, transform)

  elif opt.dset_name == 'bouncing_balls':
    transform = transforms.Compose([vtransforms.Scale(opt.image_size),
                                    vtransforms.ToTensor()])
    dset = BouncingBalls(opt.dset_path, opt.is_train, opt.n_frames_input,
                         opt.n_frames_output, opt.image_size[0], transform)

  else:
    raise NotImplementedError

  dloader = data.DataLoader(dset, batch_size=opt.batch_size, shuffle=opt.is_train,
                            num_workers=opt.n_workers, pin_memory=True)
  return dloader 

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 main(args):
    dataset = load_config(args.dataset)

    path = dataset["common"]["dataset"]
    num_classes = len(dataset["common"]["classes"])

    train_transform = Compose([ConvertImageMode(mode="P"), MaskToTensor()])

    train_dataset = SlippyMapTiles(os.path.join(path, "training", "labels"), transform=train_transform)

    n = 0
    counts = np.zeros(num_classes, dtype=np.int64)

    loader = DataLoader(train_dataset, batch_size=1)
    for images, tile in tqdm(loader, desc="Loading", unit="image", ascii=True):
        image = torch.squeeze(images)

        image = np.array(image, dtype=np.uint8)
        n += image.shape[0] * image.shape[1]
        counts += np.bincount(image.ravel(), minlength=num_classes)

    assert n > 0, "dataset with masks must not be empty"

    # Class weighting scheme `w = 1 / ln(c + p)` see:
    # - https://arxiv.org/abs/1707.03718
    #     LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentation
    # - https://arxiv.org/abs/1606.02147
    #     ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

    probs = counts / n
    weights = 1 / np.log(1.02 + probs)

    weights.round(6, out=weights)
    print(weights.tolist()) 

def transform_tr(self, sample):
        composed_transforms = transforms.Compose([
            tr.RandomHorizontalFlip(),
            tr.RandomScaleCrop(base_size=self.args.base_size, crop_size=self.args.crop_size),
            tr.RandomGaussianBlur(),
            tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
            tr.ToTensor()])

        return composed_transforms(sample) 

def transform_val(self, sample):

        composed_transforms = transforms.Compose([
            tr.FixedResize(size=self.args.crop_size),
            tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
            tr.ToTensor()])

        return composed_transforms(sample) 

def transform_tr(self, sample):
        composed_transforms = transforms.Compose([
            tr.RandomHorizontalFlip(),
            tr.RandomScaleCrop(base_size=self.args.base_size, crop_size=self.args.crop_size),
            tr.RandomGaussianBlur(),
            tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
            tr.ToTensor()])

        return composed_transforms(sample) 

def transform_ts(self, sample):

        composed_transforms = transforms.Compose([
            tr.FixedResize(size=self.args.crop_size),
            tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
            tr.ToTensor()])

        return composed_transforms(sample) 

def transform_val(self, sample):

        composed_transforms = transforms.Compose([
            tr.FixedResize(size=self.args.crop_size),
            tr.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
            tr.ToTensor()])

        return composed_transforms(sample) 

def build_transform(self):
        """
        Creates a basic transformation that was used to train the models
        """
        cfg = self.cfg

        # we are loading images with OpenCV, so we don't need to convert them
        # to BGR, they are already! So all we need to do is to normalize
        # by 255 if we want to convert to BGR255 format, or flip the channels
        # if we want it to be in RGB in [0-1] range.
        if cfg.INPUT.TO_BGR255:
            to_bgr_transform = T.Lambda(lambda x: x * 255)
        else:
            to_bgr_transform = T.Lambda(lambda x: x[[2, 1, 0]])

        normalize_transform = T.Normalize(
            mean=cfg.INPUT.PIXEL_MEAN, std=cfg.INPUT.PIXEL_STD
        )

        transform = T.Compose(
            [
                T.ToPILImage(),
                T.Resize(self.min_image_size),
                T.ToTensor(),
                to_bgr_transform,
                normalize_transform,
            ]
        )
        return transform 

def inception_preproccess(input_size, normalize=__imagenet_stats):
    return transforms.Compose([
        transforms.RandomResizedCrop(input_size),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize(**normalize)
    ]) 

def __init__(self, loader_params, dataset_params, augmentation_params):
        super().__init__(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_inference = ImgAug(self.augmentation_params['image_augment_inference'])
        self.image_augment_with_target_inference = ImgAug(
            self.augmentation_params['image_augment_with_target_inference'])
        self.dataset = ImageSegmentationTTADataset