InstruceBLIP

lavis/common/annotator/uniformer/mmseg/core/seg/sampler/ohem_pixel_sampler.py

+import torch
+import torch.nn.functional as F
+
+from ..builder import PIXEL_SAMPLERS
+from .base_pixel_sampler import BasePixelSampler
+
+
+@PIXEL_SAMPLERS.register_module()
+class OHEMPixelSampler(BasePixelSampler):
+    """Online Hard Example Mining Sampler for segmentation.
+
+    Args:
+        context (nn.Module): The context of sampler, subclass of
+            :obj:`BaseDecodeHead`.
+        thresh (float, optional): The threshold for hard example selection.
+            Below which, are prediction with low confidence. If not
+            specified, the hard examples will be pixels of top ``min_kept``
+            loss. Default: None.
+        min_kept (int, optional): The minimum number of predictions to keep.
+            Default: 100000.
+    """
+
+    def __init__(self, context, thresh=None, min_kept=100000):
+        super(OHEMPixelSampler, self).__init__()
+        self.context = context
+        assert min_kept > 1
+        self.thresh = thresh
+        self.min_kept = min_kept
+
+    def sample(self, seg_logit, seg_label):
+        """Sample pixels that have high loss or with low prediction confidence.
+
+        Args:
+            seg_logit (torch.Tensor): segmentation logits, shape (N, C, H, W)
+            seg_label (torch.Tensor): segmentation label, shape (N, 1, H, W)
+
+        Returns:
+            torch.Tensor: segmentation weight, shape (N, H, W)
+        """
+        with torch.no_grad():
+            assert seg_logit.shape[2:] == seg_label.shape[2:]
+            assert seg_label.shape[1] == 1
+            seg_label = seg_label.squeeze(1).long()
+            batch_kept = self.min_kept * seg_label.size(0)
+            valid_mask = seg_label != self.context.ignore_index
+            seg_weight = seg_logit.new_zeros(size=seg_label.size())
+            valid_seg_weight = seg_weight[valid_mask]
+            if self.thresh is not None:
+                seg_prob = F.softmax(seg_logit, dim=1)
+
+                tmp_seg_label = seg_label.clone().unsqueeze(1)
+                tmp_seg_label[tmp_seg_label == self.context.ignore_index] = 0
+                seg_prob = seg_prob.gather(1, tmp_seg_label).squeeze(1)
+                sort_prob, sort_indices = seg_prob[valid_mask].sort()
+
+                if sort_prob.numel() > 0:
+                    min_threshold = sort_prob[min(batch_kept,
+                                                  sort_prob.numel() - 1)]
+                else:
+                    min_threshold = 0.0
+                threshold = max(min_threshold, self.thresh)
+                valid_seg_weight[seg_prob[valid_mask] < threshold] = 1.
+            else:
+                losses = self.context.loss_decode(
+                    seg_logit,
+                    seg_label,
+                    weight=None,
+                    ignore_index=self.context.ignore_index,
+                    reduction_override='none')
+                # faster than topk according to https://github.com/pytorch/pytorch/issues/22812  # noqa
+                _, sort_indices = losses[valid_mask].sort(descending=True)
+                valid_seg_weight[sort_indices[:batch_kept]] = 1.
+
+            seg_weight[valid_mask] = valid_seg_weight
+
+            return seg_weight

lavis/common/annotator/uniformer/mmseg/core/utils/__init__.py

+from .misc import add_prefix
+
+__all__ = ['add_prefix']

lavis/common/annotator/uniformer/mmseg/core/utils/misc.py

+def add_prefix(inputs, prefix):
+    """Add prefix for dict.
+
+    Args:
+        inputs (dict): The input dict with str keys.
+        prefix (str): The prefix to add.
+
+    Returns:
+
+        dict: The dict with keys updated with ``prefix``.
+    """
+
+    outputs = dict()
+    for name, value in inputs.items():
+        outputs[f'{prefix}.{name}'] = value
+
+    return outputs

lavis/common/annotator/uniformer/mmseg/datasets/__init__.py

+from .ade import ADE20KDataset
+from .builder import DATASETS, PIPELINES, build_dataloader, build_dataset
+from .chase_db1 import ChaseDB1Dataset
+from .cityscapes import CityscapesDataset
+from .custom import CustomDataset
+from .dataset_wrappers import ConcatDataset, RepeatDataset
+from .drive import DRIVEDataset
+from .hrf import HRFDataset
+from .pascal_context import PascalContextDataset, PascalContextDataset59
+from .stare import STAREDataset
+from .voc import PascalVOCDataset
+
+__all__ = [
+    'CustomDataset', 'build_dataloader', 'ConcatDataset', 'RepeatDataset',
+    'DATASETS', 'build_dataset', 'PIPELINES', 'CityscapesDataset',
+    'PascalVOCDataset', 'ADE20KDataset', 'PascalContextDataset',
+    'PascalContextDataset59', 'ChaseDB1Dataset', 'DRIVEDataset', 'HRFDataset',
+    'STAREDataset'
+]

lavis/common/annotator/uniformer/mmseg/datasets/ade.py

+from .builder import DATASETS
+from .custom import CustomDataset
+
+
+@DATASETS.register_module()
+class ADE20KDataset(CustomDataset):
+    """ADE20K dataset.
+
+    In segmentation map annotation for ADE20K, 0 stands for background, which
+    is not included in 150 categories. ``reduce_zero_label`` is fixed to True.
+    The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is fixed to
+    '.png'.
+    """
+    CLASSES = (
+        'wall', 'building', 'sky', 'floor', 'tree', 'ceiling', 'road', 'bed ',
+        'windowpane', 'grass', 'cabinet', 'sidewalk', 'person', 'earth',
+        'door', 'table', 'mountain', 'plant', 'curtain', 'chair', 'car',
+        'water', 'painting', 'sofa', 'shelf', 'house', 'sea', 'mirror', 'rug',
+        'field', 'armchair', 'seat', 'fence', 'desk', 'rock', 'wardrobe',
+        'lamp', 'bathtub', 'railing', 'cushion', 'base', 'box', 'column',
+        'signboard', 'chest of drawers', 'counter', 'sand', 'sink',
+        'skyscraper', 'fireplace', 'refrigerator', 'grandstand', 'path',
+        'stairs', 'runway', 'case', 'pool table', 'pillow', 'screen door',
+        'stairway', 'river', 'bridge', 'bookcase', 'blind', 'coffee table',
+        'toilet', 'flower', 'book', 'hill', 'bench', 'countertop', 'stove',
+        'palm', 'kitchen island', 'computer', 'swivel chair', 'boat', 'bar',
+        'arcade machine', 'hovel', 'bus', 'towel', 'light', 'truck', 'tower',
+        'chandelier', 'awning', 'streetlight', 'booth', 'television receiver',
+        'airplane', 'dirt track', 'apparel', 'pole', 'land', 'bannister',
+        'escalator', 'ottoman', 'bottle', 'buffet', 'poster', 'stage', 'van',
+        'ship', 'fountain', 'conveyer belt', 'canopy', 'washer', 'plaything',
+        'swimming pool', 'stool', 'barrel', 'basket', 'waterfall', 'tent',
+        'bag', 'minibike', 'cradle', 'oven', 'ball', 'food', 'step', 'tank',
+        'trade name', 'microwave', 'pot', 'animal', 'bicycle', 'lake',
+        'dishwasher', 'screen', 'blanket', 'sculpture', 'hood', 'sconce',
+        'vase', 'traffic light', 'tray', 'ashcan', 'fan', 'pier', 'crt screen',
+        'plate', 'monitor', 'bulletin board', 'shower', 'radiator', 'glass',
+        'clock', 'flag')
+
+    PALETTE = [[120, 120, 120], [180, 120, 120], [6, 230, 230], [80, 50, 50],
+               [4, 200, 3], [120, 120, 80], [140, 140, 140], [204, 5, 255],
+               [230, 230, 230], [4, 250, 7], [224, 5, 255], [235, 255, 7],
+               [150, 5, 61], [120, 120, 70], [8, 255, 51], [255, 6, 82],
+               [143, 255, 140], [204, 255, 4], [255, 51, 7], [204, 70, 3],
+               [0, 102, 200], [61, 230, 250], [255, 6, 51], [11, 102, 255],
+               [255, 7, 71], [255, 9, 224], [9, 7, 230], [220, 220, 220],
+               [255, 9, 92], [112, 9, 255], [8, 255, 214], [7, 255, 224],
+               [255, 184, 6], [10, 255, 71], [255, 41, 10], [7, 255, 255],
+               [224, 255, 8], [102, 8, 255], [255, 61, 6], [255, 194, 7],
+               [255, 122, 8], [0, 255, 20], [255, 8, 41], [255, 5, 153],
+               [6, 51, 255], [235, 12, 255], [160, 150, 20], [0, 163, 255],
+               [140, 140, 140], [250, 10, 15], [20, 255, 0], [31, 255, 0],
+               [255, 31, 0], [255, 224, 0], [153, 255, 0], [0, 0, 255],
+               [255, 71, 0], [0, 235, 255], [0, 173, 255], [31, 0, 255],
+               [11, 200, 200], [255, 82, 0], [0, 255, 245], [0, 61, 255],
+               [0, 255, 112], [0, 255, 133], [255, 0, 0], [255, 163, 0],
+               [255, 102, 0], [194, 255, 0], [0, 143, 255], [51, 255, 0],
+               [0, 82, 255], [0, 255, 41], [0, 255, 173], [10, 0, 255],
+               [173, 255, 0], [0, 255, 153], [255, 92, 0], [255, 0, 255],
+               [255, 0, 245], [255, 0, 102], [255, 173, 0], [255, 0, 20],
+               [255, 184, 184], [0, 31, 255], [0, 255, 61], [0, 71, 255],
+               [255, 0, 204], [0, 255, 194], [0, 255, 82], [0, 10, 255],
+               [0, 112, 255], [51, 0, 255], [0, 194, 255], [0, 122, 255],
+               [0, 255, 163], [255, 153, 0], [0, 255, 10], [255, 112, 0],
+               [143, 255, 0], [82, 0, 255], [163, 255, 0], [255, 235, 0],
+               [8, 184, 170], [133, 0, 255], [0, 255, 92], [184, 0, 255],
+               [255, 0, 31], [0, 184, 255], [0, 214, 255], [255, 0, 112],
+               [92, 255, 0], [0, 224, 255], [112, 224, 255], [70, 184, 160],
+               [163, 0, 255], [153, 0, 255], [71, 255, 0], [255, 0, 163],
+               [255, 204, 0], [255, 0, 143], [0, 255, 235], [133, 255, 0],
+               [255, 0, 235], [245, 0, 255], [255, 0, 122], [255, 245, 0],
+               [10, 190, 212], [214, 255, 0], [0, 204, 255], [20, 0, 255],
+               [255, 255, 0], [0, 153, 255], [0, 41, 255], [0, 255, 204],
+               [41, 0, 255], [41, 255, 0], [173, 0, 255], [0, 245, 255],
+               [71, 0, 255], [122, 0, 255], [0, 255, 184], [0, 92, 255],
+               [184, 255, 0], [0, 133, 255], [255, 214, 0], [25, 194, 194],
+               [102, 255, 0], [92, 0, 255]]
+
+    def __init__(self, **kwargs):
+        super(ADE20KDataset, self).__init__(
+            img_suffix='.jpg',
+            seg_map_suffix='.png',
+            reduce_zero_label=True,
+            **kwargs)

lavis/common/annotator/uniformer/mmseg/datasets/builder.py

+import copy
+import platform
+import random
+from functools import partial
+
+import numpy as np
+from annotator.uniformer.mmcv.parallel import collate
+from annotator.uniformer.mmcv.runner import get_dist_info
+from annotator.uniformer.mmcv.utils import Registry, build_from_cfg
+from annotator.uniformer.mmcv.utils.parrots_wrapper import DataLoader, PoolDataLoader
+from torch.utils.data import DistributedSampler
+
+if platform.system() != 'Windows':
+    # https://github.com/pytorch/pytorch/issues/973
+    import resource
+    rlimit = resource.getrlimit(resource.RLIMIT_NOFILE)
+    hard_limit = rlimit[1]
+    soft_limit = min(4096, hard_limit)
+    resource.setrlimit(resource.RLIMIT_NOFILE, (soft_limit, hard_limit))
+
+DATASETS = Registry('dataset')
+PIPELINES = Registry('pipeline')
+
+
+def _concat_dataset(cfg, default_args=None):
+    """Build :obj:`ConcatDataset by."""
+    from .dataset_wrappers import ConcatDataset
+    img_dir = cfg['img_dir']
+    ann_dir = cfg.get('ann_dir', None)
+    split = cfg.get('split', None)
+    num_img_dir = len(img_dir) if isinstance(img_dir, (list, tuple)) else 1
+    if ann_dir is not None:
+        num_ann_dir = len(ann_dir) if isinstance(ann_dir, (list, tuple)) else 1
+    else:
+        num_ann_dir = 0
+    if split is not None:
+        num_split = len(split) if isinstance(split, (list, tuple)) else 1
+    else:
+        num_split = 0
+    if num_img_dir > 1:
+        assert num_img_dir == num_ann_dir or num_ann_dir == 0
+        assert num_img_dir == num_split or num_split == 0
+    else:
+        assert num_split == num_ann_dir or num_ann_dir <= 1
+    num_dset = max(num_split, num_img_dir)
+
+    datasets = []
+    for i in range(num_dset):
+        data_cfg = copy.deepcopy(cfg)
+        if isinstance(img_dir, (list, tuple)):
+            data_cfg['img_dir'] = img_dir[i]
+        if isinstance(ann_dir, (list, tuple)):
+            data_cfg['ann_dir'] = ann_dir[i]
+        if isinstance(split, (list, tuple)):
+            data_cfg['split'] = split[i]
+        datasets.append(build_dataset(data_cfg, default_args))
+
+    return ConcatDataset(datasets)
+
+
+def build_dataset(cfg, default_args=None):
+    """Build datasets."""
+    from .dataset_wrappers import ConcatDataset, RepeatDataset
+    if isinstance(cfg, (list, tuple)):
+        dataset = ConcatDataset([build_dataset(c, default_args) for c in cfg])
+    elif cfg['type'] == 'RepeatDataset':
+        dataset = RepeatDataset(
+            build_dataset(cfg['dataset'], default_args), cfg['times'])
+    elif isinstance(cfg.get('img_dir'), (list, tuple)) or isinstance(
+            cfg.get('split', None), (list, tuple)):
+        dataset = _concat_dataset(cfg, default_args)
+    else:
+        dataset = build_from_cfg(cfg, DATASETS, default_args)
+
+    return dataset
+
+
+def build_dataloader(dataset,
+                     samples_per_gpu,
+                     workers_per_gpu,
+                     num_gpus=1,
+                     dist=True,
+                     shuffle=True,
+                     seed=None,
+                     drop_last=False,
+                     pin_memory=True,
+                     dataloader_type='PoolDataLoader',
+                     **kwargs):
+    """Build PyTorch DataLoader.
+
+    In distributed training, each GPU/process has a dataloader.
+    In non-distributed training, there is only one dataloader for all GPUs.
+
+    Args:
+        dataset (Dataset): A PyTorch dataset.
+        samples_per_gpu (int): Number of training samples on each GPU, i.e.,
+            batch size of each GPU.
+        workers_per_gpu (int): How many subprocesses to use for data loading
+            for each GPU.
+        num_gpus (int): Number of GPUs. Only used in non-distributed training.
+        dist (bool): Distributed training/test or not. Default: True.
+        shuffle (bool): Whether to shuffle the data at every epoch.
+            Default: True.
+        seed (int | None): Seed to be used. Default: None.
+        drop_last (bool): Whether to drop the last incomplete batch in epoch.
+            Default: False
+        pin_memory (bool): Whether to use pin_memory in DataLoader.
+            Default: True
+        dataloader_type (str): Type of dataloader. Default: 'PoolDataLoader'
+        kwargs: any keyword argument to be used to initialize DataLoader
+
+    Returns:
+        DataLoader: A PyTorch dataloader.
+    """
+    rank, world_size = get_dist_info()
+    if dist:
+        sampler = DistributedSampler(
+            dataset, world_size, rank, shuffle=shuffle)
+        shuffle = False
+        batch_size = samples_per_gpu
+        num_workers = workers_per_gpu
+    else:
+        sampler = None
+        batch_size = num_gpus * samples_per_gpu
+        num_workers = num_gpus * workers_per_gpu
+
+    init_fn = partial(
+        worker_init_fn, num_workers=num_workers, rank=rank,
+        seed=seed) if seed is not None else None
+
+    assert dataloader_type in (
+        'DataLoader',
+        'PoolDataLoader'), f'unsupported dataloader {dataloader_type}'
+
+    if dataloader_type == 'PoolDataLoader':
+        dataloader = PoolDataLoader
+    elif dataloader_type == 'DataLoader':
+        dataloader = DataLoader
+    print("shuffle")
+    print(shuffle)
+    data_loader = dataloader(
+        dataset,
+        batch_size=batch_size,
+        sampler=sampler,
+        num_workers=num_workers,
+        collate_fn=partial(collate, samples_per_gpu=samples_per_gpu),
+        pin_memory=pin_memory,
+        shuffle=shuffle,
+        worker_init_fn=init_fn,
+        drop_last=drop_last,
+        **kwargs)
+
+    return data_loader
+
+
+def worker_init_fn(worker_id, num_workers, rank, seed):
+    """Worker init func for dataloader.
+
+    The seed of each worker equals to num_worker * rank + worker_id + user_seed
+
+    Args:
+        worker_id (int): Worker id.
+        num_workers (int): Number of workers.
+        rank (int): The rank of current process.
+        seed (int): The random seed to use.
+    """
+
+    worker_seed = num_workers * rank + worker_id + seed
+    np.random.seed(worker_seed)
+    random.seed(worker_seed)

lavis/common/annotator/uniformer/mmseg/datasets/chase_db1.py

+import os.path as osp
+
+from .builder import DATASETS
+from .custom import CustomDataset
+
+
+@DATASETS.register_module()
+class ChaseDB1Dataset(CustomDataset):
+    """Chase_db1 dataset.
+
+    In segmentation map annotation for Chase_db1, 0 stands for background,
+    which is included in 2 categories. ``reduce_zero_label`` is fixed to False.
+    The ``img_suffix`` is fixed to '.png' and ``seg_map_suffix`` is fixed to
+    '_1stHO.png'.
+    """
+
+    CLASSES = ('background', 'vessel')
+
+    PALETTE = [[120, 120, 120], [6, 230, 230]]
+
+    def __init__(self, **kwargs):
+        super(ChaseDB1Dataset, self).__init__(
+            img_suffix='.png',
+            seg_map_suffix='_1stHO.png',
+            reduce_zero_label=False,
+            **kwargs)
+        assert osp.exists(self.img_dir)

lavis/common/annotator/uniformer/mmseg/datasets/cityscapes.py

+import os.path as osp
+import tempfile
+
+import annotator.uniformer.mmcv as mmcv
+import numpy as np
+from annotator.uniformer.mmcv.utils import print_log
+from PIL import Image
+
+from .builder import DATASETS
+from .custom import CustomDataset
+
+
+@DATASETS.register_module()
+class CityscapesDataset(CustomDataset):
+    """Cityscapes dataset.
+
+    The ``img_suffix`` is fixed to '_leftImg8bit.png' and ``seg_map_suffix`` is
+    fixed to '_gtFine_labelTrainIds.png' for Cityscapes dataset.
+    """
+
+    CLASSES = ('road', 'sidewalk', 'building', 'wall', 'fence', 'pole',
+               'traffic light', 'traffic sign', 'vegetation', 'terrain', 'sky',
+               'person', 'rider', 'car', 'truck', 'bus', 'train', 'motorcycle',
+               'bicycle')
+
+    PALETTE = [[128, 64, 128], [244, 35, 232], [70, 70, 70], [102, 102, 156],
+               [190, 153, 153], [153, 153, 153], [250, 170, 30], [220, 220, 0],
+               [107, 142, 35], [152, 251, 152], [70, 130, 180], [220, 20, 60],
+               [255, 0, 0], [0, 0, 142], [0, 0, 70], [0, 60, 100],
+               [0, 80, 100], [0, 0, 230], [119, 11, 32]]
+
+    def __init__(self, **kwargs):
+        super(CityscapesDataset, self).__init__(
+            img_suffix='_leftImg8bit.png',
+            seg_map_suffix='_gtFine_labelTrainIds.png',
+            **kwargs)
+
+    @staticmethod
+    def _convert_to_label_id(result):
+        """Convert trainId to id for cityscapes."""
+        if isinstance(result, str):
+            result = np.load(result)
+        import cityscapesscripts.helpers.labels as CSLabels
+        result_copy = result.copy()
+        for trainId, label in CSLabels.trainId2label.items():
+            result_copy[result == trainId] = label.id
+
+        return result_copy
+
+    def results2img(self, results, imgfile_prefix, to_label_id):
+        """Write the segmentation results to images.
+
+        Args:
+            results (list[list | tuple | ndarray]): Testing results of the
+                dataset.
+            imgfile_prefix (str): The filename prefix of the png files.
+                If the prefix is "somepath/xxx",
+                the png files will be named "somepath/xxx.png".
+            to_label_id (bool): whether convert output to label_id for
+                submission
+
+        Returns:
+            list[str: str]: result txt files which contains corresponding
+            semantic segmentation images.
+        """
+        mmcv.mkdir_or_exist(imgfile_prefix)
+        result_files = []
+        prog_bar = mmcv.ProgressBar(len(self))
+        for idx in range(len(self)):
+            result = results[idx]
+            if to_label_id:
+                result = self._convert_to_label_id(result)
+            filename = self.img_infos[idx]['filename']
+            basename = osp.splitext(osp.basename(filename))[0]
+
+            png_filename = osp.join(imgfile_prefix, f'{basename}.png')
+
+            output = Image.fromarray(result.astype(np.uint8)).convert('P')
+            import cityscapesscripts.helpers.labels as CSLabels
+            palette = np.zeros((len(CSLabels.id2label), 3), dtype=np.uint8)
+            for label_id, label in CSLabels.id2label.items():
+                palette[label_id] = label.color
+
+            output.putpalette(palette)
+            output.save(png_filename)
+            result_files.append(png_filename)
+            prog_bar.update()
+
+        return result_files
+
+    def format_results(self, results, imgfile_prefix=None, to_label_id=True):
+        """Format the results into dir (standard format for Cityscapes
+        evaluation).
+
+        Args:
+            results (list): Testing results of the dataset.
+            imgfile_prefix (str | None): The prefix of images files. It
+                includes the file path and the prefix of filename, e.g.,
+                "a/b/prefix". If not specified, a temp file will be created.
+                Default: None.
+            to_label_id (bool): whether convert output to label_id for
+                submission. Default: False
+
+        Returns:
+            tuple: (result_files, tmp_dir), result_files is a list containing
+                the image paths, tmp_dir is the temporal directory created
+                for saving json/png files when img_prefix is not specified.
+        """
+
+        assert isinstance(results, list), 'results must be a list'
+        assert len(results) == len(self), (
+            'The length of results is not equal to the dataset len: '
+            f'{len(results)} != {len(self)}')
+
+        if imgfile_prefix is None:
+            tmp_dir = tempfile.TemporaryDirectory()
+            imgfile_prefix = tmp_dir.name
+        else:
+            tmp_dir = None
+        result_files = self.results2img(results, imgfile_prefix, to_label_id)
+
+        return result_files, tmp_dir
+
+    def evaluate(self,
+                 results,
+                 metric='mIoU',
+                 logger=None,
+                 imgfile_prefix=None,
+                 efficient_test=False):
+        """Evaluation in Cityscapes/default protocol.
+
+        Args:
+            results (list): Testing results of the dataset.
+            metric (str | list[str]): Metrics to be evaluated.
+            logger (logging.Logger | None | str): Logger used for printing
+                related information during evaluation. Default: None.
+            imgfile_prefix (str | None): The prefix of output image file,
+                for cityscapes evaluation only. It includes the file path and
+                the prefix of filename, e.g., "a/b/prefix".
+                If results are evaluated with cityscapes protocol, it would be
+                the prefix of output png files. The output files would be
+                png images under folder "a/b/prefix/xxx.png", where "xxx" is
+                the image name of cityscapes. If not specified, a temp file
+                will be created for evaluation.
+                Default: None.
+
+        Returns:
+            dict[str, float]: Cityscapes/default metrics.
+        """
+
+        eval_results = dict()
+        metrics = metric.copy() if isinstance(metric, list) else [metric]
+        if 'cityscapes' in metrics:
+            eval_results.update(
+                self._evaluate_cityscapes(results, logger, imgfile_prefix))
+            metrics.remove('cityscapes')
+        if len(metrics) > 0:
+            eval_results.update(
+                super(CityscapesDataset,
+                      self).evaluate(results, metrics, logger, efficient_test))
+
+        return eval_results
+
+    def _evaluate_cityscapes(self, results, logger, imgfile_prefix):
+        """Evaluation in Cityscapes protocol.
+
+        Args:
+            results (list): Testing results of the dataset.
+            logger (logging.Logger | str | None): Logger used for printing
+                related information during evaluation. Default: None.
+            imgfile_prefix (str | None): The prefix of output image file
+
+        Returns:
+            dict[str: float]: Cityscapes evaluation results.
+        """
+        try:
+            import cityscapesscripts.evaluation.evalPixelLevelSemanticLabeling as CSEval  # noqa
+        except ImportError:
+            raise ImportError('Please run "pip install cityscapesscripts" to '
+                              'install cityscapesscripts first.')
+        msg = 'Evaluating in Cityscapes style'
+        if logger is None:
+            msg = '\n' + msg
+        print_log(msg, logger=logger)
+
+        result_files, tmp_dir = self.format_results(results, imgfile_prefix)
+
+        if tmp_dir is None:
+            result_dir = imgfile_prefix
+        else:
+            result_dir = tmp_dir.name
+
+        eval_results = dict()
+        print_log(f'Evaluating results under {result_dir} ...', logger=logger)
+
+        CSEval.args.evalInstLevelScore = True
+        CSEval.args.predictionPath = osp.abspath(result_dir)
+        CSEval.args.evalPixelAccuracy = True
+        CSEval.args.JSONOutput = False
+
+        seg_map_list = []
+        pred_list = []
+
+        # when evaluating with official cityscapesscripts,
+        # **_gtFine_labelIds.png is used
+        for seg_map in mmcv.scandir(
+                self.ann_dir, 'gtFine_labelIds.png', recursive=True):
+            seg_map_list.append(osp.join(self.ann_dir, seg_map))
+            pred_list.append(CSEval.getPrediction(CSEval.args, seg_map))
+
+        eval_results.update(
+            CSEval.evaluateImgLists(pred_list, seg_map_list, CSEval.args))
+
+        if tmp_dir is not None:
+            tmp_dir.cleanup()
+
+        return eval_results

lavis/common/annotator/uniformer/mmseg/datasets/custom.py

+import os
+import os.path as osp
+from collections import OrderedDict
+from functools import reduce
+
+import annotator.uniformer.mmcv as mmcv
+import numpy as np
+from annotator.uniformer.mmcv.utils import print_log
+from prettytable import PrettyTable
+from torch.utils.data import Dataset
+
+from annotator.uniformer.mmseg.core import eval_metrics
+from annotator.uniformer.mmseg.utils import get_root_logger
+from .builder import DATASETS
+from .pipelines import Compose
+
+
+@DATASETS.register_module()
+class CustomDataset(Dataset):
+    """Custom dataset for semantic segmentation. An example of file structure
+    is as followed.
+
+    .. code-block:: none
+
+        ├── data
+        │   ├── my_dataset
+        │   │   ├── img_dir
+        │   │   │   ├── train
+        │   │   │   │   ├── xxx{img_suffix}
+        │   │   │   │   ├── yyy{img_suffix}
+        │   │   │   │   ├── zzz{img_suffix}
+        │   │   │   ├── val
+        │   │   ├── ann_dir
+        │   │   │   ├── train
+        │   │   │   │   ├── xxx{seg_map_suffix}
+        │   │   │   │   ├── yyy{seg_map_suffix}
+        │   │   │   │   ├── zzz{seg_map_suffix}
+        │   │   │   ├── val
+
+    The img/gt_semantic_seg pair of CustomDataset should be of the same
+    except suffix. A valid img/gt_semantic_seg filename pair should be like
+    ``xxx{img_suffix}`` and ``xxx{seg_map_suffix}`` (extension is also included
+    in the suffix). If split is given, then ``xxx`` is specified in txt file.
+    Otherwise, all files in ``img_dir/``and ``ann_dir`` will be loaded.
+    Please refer to ``docs/tutorials/new_dataset.md`` for more details.
+
+
+    Args:
+        pipeline (list[dict]): Processing pipeline
+        img_dir (str): Path to image directory
+        img_suffix (str): Suffix of images. Default: '.jpg'
+        ann_dir (str, optional): Path to annotation directory. Default: None
+        seg_map_suffix (str): Suffix of segmentation maps. Default: '.png'
+        split (str, optional): Split txt file. If split is specified, only
+            file with suffix in the splits will be loaded. Otherwise, all
+            images in img_dir/ann_dir will be loaded. Default: None
+        data_root (str, optional): Data root for img_dir/ann_dir. Default:
+            None.
+        test_mode (bool): If test_mode=True, gt wouldn't be loaded.
+        ignore_index (int): The label index to be ignored. Default: 255
+        reduce_zero_label (bool): Whether to mark label zero as ignored.
+            Default: False
+        classes (str | Sequence[str], optional): Specify classes to load.
+            If is None, ``cls.CLASSES`` will be used. Default: None.
+        palette (Sequence[Sequence[int]]] | np.ndarray | None):
+            The palette of segmentation map. If None is given, and
+            self.PALETTE is None, random palette will be generated.
+            Default: None
+    """
+
+    CLASSES = None
+
+    PALETTE = None
+
+    def __init__(self,
+                 pipeline,
+                 img_dir,
+                 img_suffix='.jpg',
+                 ann_dir=None,
+                 seg_map_suffix='.png',
+                 split=None,
+                 data_root=None,
+                 test_mode=False,
+                 ignore_index=255,
+                 reduce_zero_label=False,
+                 classes=None,
+                 palette=None):
+        self.pipeline = Compose(pipeline)
+        self.img_dir = img_dir
+        self.img_suffix = img_suffix
+        self.ann_dir = ann_dir
+        self.seg_map_suffix = seg_map_suffix
+        self.split = split
+        self.data_root = data_root
+        self.test_mode = test_mode
+        self.ignore_index = ignore_index
+        self.reduce_zero_label = reduce_zero_label
+        self.label_map = None
+        self.CLASSES, self.PALETTE = self.get_classes_and_palette(
+            classes, palette)
+
+        # join paths if data_root is specified
+        if self.data_root is not None:
+            if not osp.isabs(self.img_dir):
+                self.img_dir = osp.join(self.data_root, self.img_dir)
+            if not (self.ann_dir is None or osp.isabs(self.ann_dir)):
+                self.ann_dir = osp.join(self.data_root, self.ann_dir)
+            if not (self.split is None or osp.isabs(self.split)):
+                self.split = osp.join(self.data_root, self.split)
+
+        # load annotations
+        self.img_infos = self.load_annotations(self.img_dir, self.img_suffix,
+                                               self.ann_dir,
+                                               self.seg_map_suffix, self.split)
+
+    def __len__(self):
+        """Total number of samples of data."""
+        return len(self.img_infos)
+
+    def load_annotations(self, img_dir, img_suffix, ann_dir, seg_map_suffix,
+                         split):
+        """Load annotation from directory.
+
+        Args:
+            img_dir (str): Path to image directory
+            img_suffix (str): Suffix of images.
+            ann_dir (str|None): Path to annotation directory.
+            seg_map_suffix (str|None): Suffix of segmentation maps.
+            split (str|None): Split txt file. If split is specified, only file
+                with suffix in the splits will be loaded. Otherwise, all images
+                in img_dir/ann_dir will be loaded. Default: None
+
+        Returns:
+            list[dict]: All image info of dataset.
+        """
+
+        img_infos = []
+        if split is not None:
+            with open(split) as f:
+                for line in f:
+                    img_name = line.strip()
+                    img_info = dict(filename=img_name + img_suffix)
+                    if ann_dir is not None:
+                        seg_map = img_name + seg_map_suffix
+                        img_info['ann'] = dict(seg_map=seg_map)
+                    img_infos.append(img_info)
+        else:
+            for img in mmcv.scandir(img_dir, img_suffix, recursive=True):
+                img_info = dict(filename=img)
+                if ann_dir is not None:
+                    seg_map = img.replace(img_suffix, seg_map_suffix)
+                    img_info['ann'] = dict(seg_map=seg_map)
+                img_infos.append(img_info)
+
+        print_log(f'Loaded {len(img_infos)} images', logger=get_root_logger())
+        return img_infos
+
+    def get_ann_info(self, idx):
+        """Get annotation by index.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Annotation info of specified index.
+        """
+
+        return self.img_infos[idx]['ann']
+
+    def pre_pipeline(self, results):
+        """Prepare results dict for pipeline."""
+        results['seg_fields'] = []
+        results['img_prefix'] = self.img_dir
+        results['seg_prefix'] = self.ann_dir
+        if self.custom_classes:
+            results['label_map'] = self.label_map
+
+    def __getitem__(self, idx):
+        """Get training/test data after pipeline.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Training/test data (with annotation if `test_mode` is set
+                False).
+        """
+
+        if self.test_mode:
+            return self.prepare_test_img(idx)
+        else:
+            return self.prepare_train_img(idx)
+
+    def prepare_train_img(self, idx):
+        """Get training data and annotations after pipeline.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Training data and annotation after pipeline with new keys
+                introduced by pipeline.
+        """
+
+        img_info = self.img_infos[idx]
+        ann_info = self.get_ann_info(idx)
+        results = dict(img_info=img_info, ann_info=ann_info)
+        self.pre_pipeline(results)
+        return self.pipeline(results)
+
+    def prepare_test_img(self, idx):
+        """Get testing data after pipeline.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Testing data after pipeline with new keys introduced by
+                pipeline.
+        """
+
+        img_info = self.img_infos[idx]
+        results = dict(img_info=img_info)
+        self.pre_pipeline(results)
+        return self.pipeline(results)
+
+    def format_results(self, results, **kwargs):
+        """Place holder to format result to dataset specific output."""
+
+    def get_gt_seg_maps(self, efficient_test=False):
+        """Get ground truth segmentation maps for evaluation."""
+        gt_seg_maps = []
+        for img_info in self.img_infos:
+            seg_map = osp.join(self.ann_dir, img_info['ann']['seg_map'])
+            if efficient_test:
+                gt_seg_map = seg_map
+            else:
+                gt_seg_map = mmcv.imread(
+                    seg_map, flag='unchanged', backend='pillow')
+            gt_seg_maps.append(gt_seg_map)
+        return gt_seg_maps
+
+    def get_classes_and_palette(self, classes=None, palette=None):
+        """Get class names of current dataset.
+
+        Args:
+            classes (Sequence[str] | str | None): If classes is None, use
+                default CLASSES defined by builtin dataset. If classes is a
+                string, take it as a file name. The file contains the name of
+                classes where each line contains one class name. If classes is
+                a tuple or list, override the CLASSES defined by the dataset.
+            palette (Sequence[Sequence[int]]] | np.ndarray | None):
+                The palette of segmentation map. If None is given, random
+                palette will be generated. Default: None
+        """
+        if classes is None:
+            self.custom_classes = False
+            return self.CLASSES, self.PALETTE
+
+        self.custom_classes = True
+        if isinstance(classes, str):
+            # take it as a file path
+            class_names = mmcv.list_from_file(classes)
+        elif isinstance(classes, (tuple, list)):
+            class_names = classes
+        else:
+            raise ValueError(f'Unsupported type {type(classes)} of classes.')
+
+        if self.CLASSES:
+            if not set(classes).issubset(self.CLASSES):
+                raise ValueError('classes is not a subset of CLASSES.')
+
+            # dictionary, its keys are the old label ids and its values
+            # are the new label ids.
+            # used for changing pixel labels in load_annotations.
+            self.label_map = {}
+            for i, c in enumerate(self.CLASSES):
+                if c not in class_names:
+                    self.label_map[i] = -1
+                else:
+                    self.label_map[i] = classes.index(c)
+
+        palette = self.get_palette_for_custom_classes(class_names, palette)
+
+        return class_names, palette
+
+    def get_palette_for_custom_classes(self, class_names, palette=None):
+
+        if self.label_map is not None:
+            # return subset of palette
+            palette = []
+            for old_id, new_id in sorted(
+                    self.label_map.items(), key=lambda x: x[1]):
+                if new_id != -1:
+                    palette.append(self.PALETTE[old_id])
+            palette = type(self.PALETTE)(palette)
+
+        elif palette is None:
+            if self.PALETTE is None:
+                palette = np.random.randint(0, 255, size=(len(class_names), 3))
+            else:
+                palette = self.PALETTE
+
+        return palette
+
+    def evaluate(self,
+                 results,
+                 metric='mIoU',
+                 logger=None,
+                 efficient_test=False,
+                 **kwargs):
+        """Evaluate the dataset.
+
+        Args:
+            results (list): Testing results of the dataset.
+            metric (str | list[str]): Metrics to be evaluated. 'mIoU',
+                'mDice' and 'mFscore' are supported.
+            logger (logging.Logger | None | str): Logger used for printing
+                related information during evaluation. Default: None.
+
+        Returns:
+            dict[str, float]: Default metrics.
+        """
+
+        if isinstance(metric, str):
+            metric = [metric]
+        allowed_metrics = ['mIoU', 'mDice', 'mFscore']
+        if not set(metric).issubset(set(allowed_metrics)):
+            raise KeyError('metric {} is not supported'.format(metric))
+        eval_results = {}
+        gt_seg_maps = self.get_gt_seg_maps(efficient_test)
+        if self.CLASSES is None:
+            num_classes = len(
+                reduce(np.union1d, [np.unique(_) for _ in gt_seg_maps]))
+        else:
+            num_classes = len(self.CLASSES)
+        ret_metrics = eval_metrics(
+            results,
+            gt_seg_maps,
+            num_classes,
+            self.ignore_index,
+            metric,
+            label_map=self.label_map,
+            reduce_zero_label=self.reduce_zero_label)
+
+        if self.CLASSES is None:
+            class_names = tuple(range(num_classes))
+        else:
+            class_names = self.CLASSES
+
+        # summary table
+        ret_metrics_summary = OrderedDict({
+            ret_metric: np.round(np.nanmean(ret_metric_value) * 100, 2)
+            for ret_metric, ret_metric_value in ret_metrics.items()
+        })
+
+        # each class table
+        ret_metrics.pop('aAcc', None)
+        ret_metrics_class = OrderedDict({
+            ret_metric: np.round(ret_metric_value * 100, 2)
+            for ret_metric, ret_metric_value in ret_metrics.items()
+        })
+        ret_metrics_class.update({'Class': class_names})
+        ret_metrics_class.move_to_end('Class', last=False)
+
+        # for logger
+        class_table_data = PrettyTable()
+        for key, val in ret_metrics_class.items():
+            class_table_data.add_column(key, val)
+
+        summary_table_data = PrettyTable()
+        for key, val in ret_metrics_summary.items():
+            if key == 'aAcc':
+                summary_table_data.add_column(key, [val])
+            else:
+                summary_table_data.add_column('m' + key, [val])
+
+        print_log('per class results:', logger)
+        print_log('\n' + class_table_data.get_string(), logger=logger)
+        print_log('Summary:', logger)
+        print_log('\n' + summary_table_data.get_string(), logger=logger)
+
+        # each metric dict
+        for key, value in ret_metrics_summary.items():
+            if key == 'aAcc':
+                eval_results[key] = value / 100.0
+            else:
+                eval_results['m' + key] = value / 100.0
+
+        ret_metrics_class.pop('Class', None)
+        for key, value in ret_metrics_class.items():
+            eval_results.update({
+                key + '.' + str(name): value[idx] / 100.0
+                for idx, name in enumerate(class_names)
+            })
+
+        if mmcv.is_list_of(results, str):
+            for file_name in results:
+                os.remove(file_name)
+        return eval_results

lavis/common/annotator/uniformer/mmseg/datasets/dataset_wrappers.py

+from torch.utils.data.dataset import ConcatDataset as _ConcatDataset
+
+from .builder import DATASETS
+
+
+@DATASETS.register_module()
+class ConcatDataset(_ConcatDataset):
+    """A wrapper of concatenated dataset.
+
+    Same as :obj:`torch.utils.data.dataset.ConcatDataset`, but
+    concat the group flag for image aspect ratio.
+
+    Args:
+        datasets (list[:obj:`Dataset`]): A list of datasets.
+    """
+
+    def __init__(self, datasets):
+        super(ConcatDataset, self).__init__(datasets)
+        self.CLASSES = datasets[0].CLASSES
+        self.PALETTE = datasets[0].PALETTE
+
+
+@DATASETS.register_module()
+class RepeatDataset(object):
+    """A wrapper of repeated dataset.
+
+    The length of repeated dataset will be `times` larger than the original
+    dataset. This is useful when the data loading time is long but the dataset
+    is small. Using RepeatDataset can reduce the data loading time between
+    epochs.
+
+    Args:
+        dataset (:obj:`Dataset`): The dataset to be repeated.
+        times (int): Repeat times.
+    """
+
+    def __init__(self, dataset, times):
+        self.dataset = dataset
+        self.times = times
+        self.CLASSES = dataset.CLASSES
+        self.PALETTE = dataset.PALETTE
+        self._ori_len = len(self.dataset)
+
+    def __getitem__(self, idx):
+        """Get item from original dataset."""
+        return self.dataset[idx % self._ori_len]
+
+    def __len__(self):
+        """The length is multiplied by ``times``"""
+        return self.times * self._ori_len

lavis/common/annotator/uniformer/mmseg/datasets/drive.py

+import os.path as osp
+
+from .builder import DATASETS
+from .custom import CustomDataset
+
+
+@DATASETS.register_module()
+class DRIVEDataset(CustomDataset):
+    """DRIVE dataset.
+
+    In segmentation map annotation for DRIVE, 0 stands for background, which is
+    included in 2 categories. ``reduce_zero_label`` is fixed to False. The
+    ``img_suffix`` is fixed to '.png' and ``seg_map_suffix`` is fixed to
+    '_manual1.png'.
+    """
+
+    CLASSES = ('background', 'vessel')
+
+    PALETTE = [[120, 120, 120], [6, 230, 230]]
+
+    def __init__(self, **kwargs):
+        super(DRIVEDataset, self).__init__(
+            img_suffix='.png',
+            seg_map_suffix='_manual1.png',
+            reduce_zero_label=False,
+            **kwargs)
+        assert osp.exists(self.img_dir)

lavis/common/annotator/uniformer/mmseg/datasets/hrf.py

+import os.path as osp
+
+from .builder import DATASETS
+from .custom import CustomDataset
+
+
+@DATASETS.register_module()
+class HRFDataset(CustomDataset):
+    """HRF dataset.
+
+    In segmentation map annotation for HRF, 0 stands for background, which is
+    included in 2 categories. ``reduce_zero_label`` is fixed to False. The
+    ``img_suffix`` is fixed to '.png' and ``seg_map_suffix`` is fixed to
+    '.png'.
+    """
+
+    CLASSES = ('background', 'vessel')
+
+    PALETTE = [[120, 120, 120], [6, 230, 230]]
+
+    def __init__(self, **kwargs):
+        super(HRFDataset, self).__init__(
+            img_suffix='.png',
+            seg_map_suffix='.png',
+            reduce_zero_label=False,
+            **kwargs)
+        assert osp.exists(self.img_dir)

lavis/common/annotator/uniformer/mmseg/datasets/pascal_context.py

+import os.path as osp
+
+from .builder import DATASETS
+from .custom import CustomDataset
+
+
+@DATASETS.register_module()
+class PascalContextDataset(CustomDataset):
+    """PascalContext dataset.
+
+    In segmentation map annotation for PascalContext, 0 stands for background,
+    which is included in 60 categories. ``reduce_zero_label`` is fixed to
+    False. The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is
+    fixed to '.png'.
+
+    Args:
+        split (str): Split txt file for PascalContext.
+    """
+
+    CLASSES = ('background', 'aeroplane', 'bag', 'bed', 'bedclothes', 'bench',
+               'bicycle', 'bird', 'boat', 'book', 'bottle', 'building', 'bus',
+               'cabinet', 'car', 'cat', 'ceiling', 'chair', 'cloth',
+               'computer', 'cow', 'cup', 'curtain', 'dog', 'door', 'fence',
+               'floor', 'flower', 'food', 'grass', 'ground', 'horse',
+               'keyboard', 'light', 'motorbike', 'mountain', 'mouse', 'person',
+               'plate', 'platform', 'pottedplant', 'road', 'rock', 'sheep',
+               'shelves', 'sidewalk', 'sign', 'sky', 'snow', 'sofa', 'table',
+               'track', 'train', 'tree', 'truck', 'tvmonitor', 'wall', 'water',
+               'window', 'wood')
+
+    PALETTE = [[120, 120, 120], [180, 120, 120], [6, 230, 230], [80, 50, 50],
+               [4, 200, 3], [120, 120, 80], [140, 140, 140], [204, 5, 255],
+               [230, 230, 230], [4, 250, 7], [224, 5, 255], [235, 255, 7],
+               [150, 5, 61], [120, 120, 70], [8, 255, 51], [255, 6, 82],
+               [143, 255, 140], [204, 255, 4], [255, 51, 7], [204, 70, 3],
+               [0, 102, 200], [61, 230, 250], [255, 6, 51], [11, 102, 255],
+               [255, 7, 71], [255, 9, 224], [9, 7, 230], [220, 220, 220],
+               [255, 9, 92], [112, 9, 255], [8, 255, 214], [7, 255, 224],
+               [255, 184, 6], [10, 255, 71], [255, 41, 10], [7, 255, 255],
+               [224, 255, 8], [102, 8, 255], [255, 61, 6], [255, 194, 7],
+               [255, 122, 8], [0, 255, 20], [255, 8, 41], [255, 5, 153],
+               [6, 51, 255], [235, 12, 255], [160, 150, 20], [0, 163, 255],
+               [140, 140, 140], [250, 10, 15], [20, 255, 0], [31, 255, 0],
+               [255, 31, 0], [255, 224, 0], [153, 255, 0], [0, 0, 255],
+               [255, 71, 0], [0, 235, 255], [0, 173, 255], [31, 0, 255]]
+
+    def __init__(self, split, **kwargs):
+        super(PascalContextDataset, self).__init__(
+            img_suffix='.jpg',
+            seg_map_suffix='.png',
+            split=split,
+            reduce_zero_label=False,
+            **kwargs)
+        assert osp.exists(self.img_dir) and self.split is not None
+
+
+@DATASETS.register_module()
+class PascalContextDataset59(CustomDataset):
+    """PascalContext dataset.
+
+    In segmentation map annotation for PascalContext, 0 stands for background,
+    which is included in 60 categories. ``reduce_zero_label`` is fixed to
+    False. The ``img_suffix`` is fixed to '.jpg' and ``seg_map_suffix`` is
+    fixed to '.png'.
+
+    Args:
+        split (str): Split txt file for PascalContext.
+    """
+
+    CLASSES = ('aeroplane', 'bag', 'bed', 'bedclothes', 'bench', 'bicycle',
+               'bird', 'boat', 'book', 'bottle', 'building', 'bus', 'cabinet',
+               'car', 'cat', 'ceiling', 'chair', 'cloth', 'computer', 'cow',
+               'cup', 'curtain', 'dog', 'door', 'fence', 'floor', 'flower',
+               'food', 'grass', 'ground', 'horse', 'keyboard', 'light',
+               'motorbike', 'mountain', 'mouse', 'person', 'plate', 'platform',
+               'pottedplant', 'road', 'rock', 'sheep', 'shelves', 'sidewalk',
+               'sign', 'sky', 'snow', 'sofa', 'table', 'track', 'train',
+               'tree', 'truck', 'tvmonitor', 'wall', 'water', 'window', 'wood')
+
+    PALETTE = [[180, 120, 120], [6, 230, 230], [80, 50, 50], [4, 200, 3],
+               [120, 120, 80], [140, 140, 140], [204, 5, 255], [230, 230, 230],
+               [4, 250, 7], [224, 5, 255], [235, 255, 7], [150, 5, 61],
+               [120, 120, 70], [8, 255, 51], [255, 6, 82], [143, 255, 140],
+               [204, 255, 4], [255, 51, 7], [204, 70, 3], [0, 102, 200],
+               [61, 230, 250], [255, 6, 51], [11, 102, 255], [255, 7, 71],
+               [255, 9, 224], [9, 7, 230], [220, 220, 220], [255, 9, 92],
+               [112, 9, 255], [8, 255, 214], [7, 255, 224], [255, 184, 6],
+               [10, 255, 71], [255, 41, 10], [7, 255, 255], [224, 255, 8],
+               [102, 8, 255], [255, 61, 6], [255, 194, 7], [255, 122, 8],
+               [0, 255, 20], [255, 8, 41], [255, 5, 153], [6, 51, 255],
+               [235, 12, 255], [160, 150, 20], [0, 163, 255], [140, 140, 140],
+               [250, 10, 15], [20, 255, 0], [31, 255, 0], [255, 31, 0],
+               [255, 224, 0], [153, 255, 0], [0, 0, 255], [255, 71, 0],
+               [0, 235, 255], [0, 173, 255], [31, 0, 255]]
+
+    def __init__(self, split, **kwargs):
+        super(PascalContextDataset59, self).__init__(
+            img_suffix='.jpg',
+            seg_map_suffix='.png',
+            split=split,
+            reduce_zero_label=True,
+            **kwargs)
+        assert osp.exists(self.img_dir) and self.split is not None

lavis/common/annotator/uniformer/mmseg/datasets/pipelines/__init__.py

+from .compose import Compose
+from .formating import (Collect, ImageToTensor, ToDataContainer, ToTensor,
+                        Transpose, to_tensor)
+from .loading import LoadAnnotations, LoadImageFromFile
+from .test_time_aug import MultiScaleFlipAug
+from .transforms import (CLAHE, AdjustGamma, Normalize, Pad,
+                         PhotoMetricDistortion, RandomCrop, RandomFlip,
+                         RandomRotate, Rerange, Resize, RGB2Gray, SegRescale)
+
+__all__ = [
+    'Compose', 'to_tensor', 'ToTensor', 'ImageToTensor', 'ToDataContainer',
+    'Transpose', 'Collect', 'LoadAnnotations', 'LoadImageFromFile',
+    'MultiScaleFlipAug', 'Resize', 'RandomFlip', 'Pad', 'RandomCrop',
+    'Normalize', 'SegRescale', 'PhotoMetricDistortion', 'RandomRotate',
+    'AdjustGamma', 'CLAHE', 'Rerange', 'RGB2Gray'
+]

lavis/common/annotator/uniformer/mmseg/datasets/pipelines/compose.py

+import collections
+
+from annotator.uniformer.mmcv.utils import build_from_cfg
+
+from ..builder import PIPELINES
+
+
+@PIPELINES.register_module()
+class Compose(object):
+    """Compose multiple transforms sequentially.
+
+    Args:
+        transforms (Sequence[dict | callable]): Sequence of transform object or
+            config dict to be composed.
+    """
+
+    def __init__(self, transforms):
+        assert isinstance(transforms, collections.abc.Sequence)
+        self.transforms = []
+        for transform in transforms:
+            if isinstance(transform, dict):
+                transform = build_from_cfg(transform, PIPELINES)
+                self.transforms.append(transform)
+            elif callable(transform):
+                self.transforms.append(transform)
+            else:
+                raise TypeError('transform must be callable or a dict')
+
+    def __call__(self, data):
+        """Call function to apply transforms sequentially.
+
+        Args:
+            data (dict): A result dict contains the data to transform.
+
+        Returns:
+           dict: Transformed data.
+        """
+
+        for t in self.transforms:
+            data = t(data)
+            if data is None:
+                return None
+        return data
+
+    def __repr__(self):
+        format_string = self.__class__.__name__ + '('
+        for t in self.transforms:
+            format_string += '\n'
+            format_string += f'    {t}'
+        format_string += '\n)'
+        return format_string

lavis/common/annotator/uniformer/mmseg/datasets/pipelines/formating.py

+from collections.abc import Sequence
+
+import annotator.uniformer.mmcv as mmcv
+import numpy as np
+import torch
+from annotator.uniformer.mmcv.parallel import DataContainer as DC
+
+from ..builder import PIPELINES
+
+
+def to_tensor(data):
+    """Convert objects of various python types to :obj:`torch.Tensor`.
+
+    Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
+    :class:`Sequence`, :class:`int` and :class:`float`.
+
+    Args:
+        data (torch.Tensor | numpy.ndarray | Sequence | int | float): Data to
+            be converted.
+    """
+
+    if isinstance(data, torch.Tensor):
+        return data
+    elif isinstance(data, np.ndarray):
+        return torch.from_numpy(data)
+    elif isinstance(data, Sequence) and not mmcv.is_str(data):
+        return torch.tensor(data)
+    elif isinstance(data, int):
+        return torch.LongTensor([data])
+    elif isinstance(data, float):
+        return torch.FloatTensor([data])
+    else:
+        raise TypeError(f'type {type(data)} cannot be converted to tensor.')
+
+
+@PIPELINES.register_module()
+class ToTensor(object):
+    """Convert some results to :obj:`torch.Tensor` by given keys.
+
+    Args:
+        keys (Sequence[str]): Keys that need to be converted to Tensor.
+    """
+
+    def __init__(self, keys):
+        self.keys = keys
+
+    def __call__(self, results):
+        """Call function to convert data in results to :obj:`torch.Tensor`.
+
+        Args:
+            results (dict): Result dict contains the data to convert.
+
+        Returns:
+            dict: The result dict contains the data converted
+                to :obj:`torch.Tensor`.
+        """
+
+        for key in self.keys:
+            results[key] = to_tensor(results[key])
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(keys={self.keys})'
+
+
+@PIPELINES.register_module()
+class ImageToTensor(object):
+    """Convert image to :obj:`torch.Tensor` by given keys.
+
+    The dimension order of input image is (H, W, C). The pipeline will convert
+    it to (C, H, W). If only 2 dimension (H, W) is given, the output would be
+    (1, H, W).
+
+    Args:
+        keys (Sequence[str]): Key of images to be converted to Tensor.
+    """
+
+    def __init__(self, keys):
+        self.keys = keys
+
+    def __call__(self, results):
+        """Call function to convert image in results to :obj:`torch.Tensor` and
+        transpose the channel order.
+
+        Args:
+            results (dict): Result dict contains the image data to convert.
+
+        Returns:
+            dict: The result dict contains the image converted
+                to :obj:`torch.Tensor` and transposed to (C, H, W) order.
+        """
+
+        for key in self.keys:
+            img = results[key]
+            if len(img.shape) < 3:
+                img = np.expand_dims(img, -1)
+            results[key] = to_tensor(img.transpose(2, 0, 1))
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(keys={self.keys})'
+
+
+@PIPELINES.register_module()
+class Transpose(object):
+    """Transpose some results by given keys.
+
+    Args:
+        keys (Sequence[str]): Keys of results to be transposed.
+        order (Sequence[int]): Order of transpose.
+    """
+
+    def __init__(self, keys, order):
+        self.keys = keys
+        self.order = order
+
+    def __call__(self, results):
+        """Call function to convert image in results to :obj:`torch.Tensor` and
+        transpose the channel order.
+
+        Args:
+            results (dict): Result dict contains the image data to convert.
+
+        Returns:
+            dict: The result dict contains the image converted
+                to :obj:`torch.Tensor` and transposed to (C, H, W) order.
+        """
+
+        for key in self.keys:
+            results[key] = results[key].transpose(self.order)
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + \
+               f'(keys={self.keys}, order={self.order})'
+
+
+@PIPELINES.register_module()
+class ToDataContainer(object):
+    """Convert results to :obj:`mmcv.DataContainer` by given fields.
+
+    Args:
+        fields (Sequence[dict]): Each field is a dict like
+            ``dict(key='xxx', **kwargs)``. The ``key`` in result will
+            be converted to :obj:`mmcv.DataContainer` with ``**kwargs``.
+            Default: ``(dict(key='img', stack=True),
+            dict(key='gt_semantic_seg'))``.
+    """
+
+    def __init__(self,
+                 fields=(dict(key='img',
+                              stack=True), dict(key='gt_semantic_seg'))):
+        self.fields = fields
+
+    def __call__(self, results):
+        """Call function to convert data in results to
+        :obj:`mmcv.DataContainer`.
+
+        Args:
+            results (dict): Result dict contains the data to convert.
+
+        Returns:
+            dict: The result dict contains the data converted to
+                :obj:`mmcv.DataContainer`.
+        """
+
+        for field in self.fields:
+            field = field.copy()
+            key = field.pop('key')
+            results[key] = DC(results[key], **field)
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(fields={self.fields})'
+
+
+@PIPELINES.register_module()
+class DefaultFormatBundle(object):
+    """Default formatting bundle.
+
+    It simplifies the pipeline of formatting common fields, including "img"
+    and "gt_semantic_seg". These fields are formatted as follows.
+
+    - img: (1)transpose, (2)to tensor, (3)to DataContainer (stack=True)
+    - gt_semantic_seg: (1)unsqueeze dim-0 (2)to tensor,
+                       (3)to DataContainer (stack=True)
+    """
+
+    def __call__(self, results):
+        """Call function to transform and format common fields in results.
+
+        Args:
+            results (dict): Result dict contains the data to convert.
+
+        Returns:
+            dict: The result dict contains the data that is formatted with
+                default bundle.
+        """
+
+        if 'img' in results:
+            img = results['img']
+            if len(img.shape) < 3:
+                img = np.expand_dims(img, -1)
+            img = np.ascontiguousarray(img.transpose(2, 0, 1))
+            results['img'] = DC(to_tensor(img), stack=True)
+        if 'gt_semantic_seg' in results:
+            # convert to long
+            results['gt_semantic_seg'] = DC(
+                to_tensor(results['gt_semantic_seg'][None,
+                                                     ...].astype(np.int64)),
+                stack=True)
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__
+
+
+@PIPELINES.register_module()
+class Collect(object):
+    """Collect data from the loader relevant to the specific task.
+
+    This is usually the last stage of the data loader pipeline. Typically keys
+    is set to some subset of "img", "gt_semantic_seg".
+
+    The "img_meta" item is always populated.  The contents of the "img_meta"
+    dictionary depends on "meta_keys". By default this includes:
+
+        - "img_shape": shape of the image input to the network as a tuple
+            (h, w, c).  Note that images may be zero padded on the bottom/right
+            if the batch tensor is larger than this shape.
+
+        - "scale_factor": a float indicating the preprocessing scale
+
+        - "flip": a boolean indicating if image flip transform was used
+
+        - "filename": path to the image file
+
+        - "ori_shape": original shape of the image as a tuple (h, w, c)
+
+        - "pad_shape": image shape after padding
+
+        - "img_norm_cfg": a dict of normalization information:
+            - mean - per channel mean subtraction
+            - std - per channel std divisor
+            - to_rgb - bool indicating if bgr was converted to rgb
+
+    Args:
+        keys (Sequence[str]): Keys of results to be collected in ``data``.
+        meta_keys (Sequence[str], optional): Meta keys to be converted to
+            ``mmcv.DataContainer`` and collected in ``data[img_metas]``.
+            Default: ``('filename', 'ori_filename', 'ori_shape', 'img_shape',
+            'pad_shape', 'scale_factor', 'flip', 'flip_direction',
+            'img_norm_cfg')``
+    """
+
+    def __init__(self,
+                 keys,
+                 meta_keys=('filename', 'ori_filename', 'ori_shape',
+                            'img_shape', 'pad_shape', 'scale_factor', 'flip',
+                            'flip_direction', 'img_norm_cfg')):
+        self.keys = keys
+        self.meta_keys = meta_keys
+
+    def __call__(self, results):
+        """Call function to collect keys in results. The keys in ``meta_keys``
+        will be converted to :obj:mmcv.DataContainer.
+
+        Args:
+            results (dict): Result dict contains the data to collect.
+
+        Returns:
+            dict: The result dict contains the following keys
+                - keys in``self.keys``
+                - ``img_metas``
+        """
+
+        data = {}
+        img_meta = {}
+        for key in self.meta_keys:
+            img_meta[key] = results[key]
+        data['img_metas'] = DC(img_meta, cpu_only=True)
+        for key in self.keys:
+            data[key] = results[key]
+        return data
+
+    def __repr__(self):
+        return self.__class__.__name__ + \
+               f'(keys={self.keys}, meta_keys={self.meta_keys})'

lavis/common/annotator/uniformer/mmseg/datasets/pipelines/loading.py

+import os.path as osp
+
+import annotator.uniformer.mmcv as mmcv
+import numpy as np
+
+from ..builder import PIPELINES
+
+
+@PIPELINES.register_module()
+class LoadImageFromFile(object):
+    """Load an image from file.
+
+    Required keys are "img_prefix" and "img_info" (a dict that must contain the
+    key "filename"). Added or updated keys are "filename", "img", "img_shape",
+    "ori_shape" (same as `img_shape`), "pad_shape" (same as `img_shape`),
+    "scale_factor" (1.0) and "img_norm_cfg" (means=0 and stds=1).
+
+    Args:
+        to_float32 (bool): Whether to convert the loaded image to a float32
+            numpy array. If set to False, the loaded image is an uint8 array.
+            Defaults to False.
+        color_type (str): The flag argument for :func:`mmcv.imfrombytes`.
+            Defaults to 'color'.
+        file_client_args (dict): Arguments to instantiate a FileClient.
+            See :class:`mmcv.fileio.FileClient` for details.
+            Defaults to ``dict(backend='disk')``.
+        imdecode_backend (str): Backend for :func:`mmcv.imdecode`. Default:
+            'cv2'
+    """
+
+    def __init__(self,
+                 to_float32=False,
+                 color_type='color',
+                 file_client_args=dict(backend='disk'),
+                 imdecode_backend='cv2'):
+        self.to_float32 = to_float32
+        self.color_type = color_type
+        self.file_client_args = file_client_args.copy()
+        self.file_client = None
+        self.imdecode_backend = imdecode_backend
+
+    def __call__(self, results):
+        """Call functions to load image and get image meta information.
+
+        Args:
+            results (dict): Result dict from :obj:`mmseg.CustomDataset`.
+
+        Returns:
+            dict: The dict contains loaded image and meta information.
+        """
+
+        if self.file_client is None:
+            self.file_client = mmcv.FileClient(**self.file_client_args)
+
+        if results.get('img_prefix') is not None:
+            filename = osp.join(results['img_prefix'],
+                                results['img_info']['filename'])
+        else:
+            filename = results['img_info']['filename']
+        img_bytes = self.file_client.get(filename)
+        img = mmcv.imfrombytes(
+            img_bytes, flag=self.color_type, backend=self.imdecode_backend)
+        if self.to_float32:
+            img = img.astype(np.float32)
+
+        results['filename'] = filename
+        results['ori_filename'] = results['img_info']['filename']
+        results['img'] = img
+        results['img_shape'] = img.shape
+        results['ori_shape'] = img.shape
+        # Set initial values for default meta_keys
+        results['pad_shape'] = img.shape
+        results['scale_factor'] = 1.0
+        num_channels = 1 if len(img.shape) < 3 else img.shape[2]
+        results['img_norm_cfg'] = dict(
+            mean=np.zeros(num_channels, dtype=np.float32),
+            std=np.ones(num_channels, dtype=np.float32),
+            to_rgb=False)
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(to_float32={self.to_float32},'
+        repr_str += f"color_type='{self.color_type}',"
+        repr_str += f"imdecode_backend='{self.imdecode_backend}')"
+        return repr_str
+
+
+@PIPELINES.register_module()
+class LoadAnnotations(object):
+    """Load annotations for semantic segmentation.
+
+    Args:
+        reduce_zero_label (bool): Whether reduce all label value by 1.
+            Usually used for datasets where 0 is background label.
+            Default: False.
+        file_client_args (dict): Arguments to instantiate a FileClient.
+            See :class:`mmcv.fileio.FileClient` for details.
+            Defaults to ``dict(backend='disk')``.
+        imdecode_backend (str): Backend for :func:`mmcv.imdecode`. Default:
+            'pillow'
+    """
+
+    def __init__(self,
+                 reduce_zero_label=False,
+                 file_client_args=dict(backend='disk'),
+                 imdecode_backend='pillow'):
+        self.reduce_zero_label = reduce_zero_label
+        self.file_client_args = file_client_args.copy()
+        self.file_client = None
+        self.imdecode_backend = imdecode_backend
+
+    def __call__(self, results):
+        """Call function to load multiple types annotations.
+
+        Args:
+            results (dict): Result dict from :obj:`mmseg.CustomDataset`.
+
+        Returns:
+            dict: The dict contains loaded semantic segmentation annotations.
+        """
+
+        if self.file_client is None:
+            self.file_client = mmcv.FileClient(**self.file_client_args)
+
+        if results.get('seg_prefix', None) is not None:
+            filename = osp.join(results['seg_prefix'],
+                                results['ann_info']['seg_map'])
+        else:
+            filename = results['ann_info']['seg_map']
+        img_bytes = self.file_client.get(filename)
+        gt_semantic_seg = mmcv.imfrombytes(
+            img_bytes, flag='unchanged',
+            backend=self.imdecode_backend).squeeze().astype(np.uint8)
+        # modify if custom classes
+        if results.get('label_map', None) is not None:
+            for old_id, new_id in results['label_map'].items():
+                gt_semantic_seg[gt_semantic_seg == old_id] = new_id
+        # reduce zero_label
+        if self.reduce_zero_label:
+            # avoid using underflow conversion
+            gt_semantic_seg[gt_semantic_seg == 0] = 255
+            gt_semantic_seg = gt_semantic_seg - 1
+            gt_semantic_seg[gt_semantic_seg == 254] = 255
+        results['gt_semantic_seg'] = gt_semantic_seg
+        results['seg_fields'].append('gt_semantic_seg')
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(reduce_zero_label={self.reduce_zero_label},'
+        repr_str += f"imdecode_backend='{self.imdecode_backend}')"
+        return repr_str

lavis/common/annotator/uniformer/mmseg/datasets/pipelines/test_time_aug.py

+import warnings
+
+import annotator.uniformer.mmcv as mmcv
+
+from ..builder import PIPELINES
+from .compose import Compose
+
+
+@PIPELINES.register_module()
+class MultiScaleFlipAug(object):
+    """Test-time augmentation with multiple scales and flipping.
+
+    An example configuration is as followed:
+
+    .. code-block::
+
+        img_scale=(2048, 1024),
+        img_ratios=[0.5, 1.0],
+        flip=True,
+        transforms=[
+            dict(type='Resize', keep_ratio=True),
+            dict(type='RandomFlip'),
+            dict(type='Normalize', **img_norm_cfg),
+            dict(type='Pad', size_divisor=32),
+            dict(type='ImageToTensor', keys=['img']),
+            dict(type='Collect', keys=['img']),
+        ]
+
+    After MultiScaleFLipAug with above configuration, the results are wrapped
+    into lists of the same length as followed:
+
+    .. code-block::
+
+        dict(
+            img=[...],
+            img_shape=[...],
+            scale=[(1024, 512), (1024, 512), (2048, 1024), (2048, 1024)]
+            flip=[False, True, False, True]
+            ...
+        )
+
+    Args:
+        transforms (list[dict]): Transforms to apply in each augmentation.
+        img_scale (None | tuple | list[tuple]): Images scales for resizing.
+        img_ratios (float | list[float]): Image ratios for resizing
+        flip (bool): Whether apply flip augmentation. Default: False.
+        flip_direction (str | list[str]): Flip augmentation directions,
+            options are "horizontal" and "vertical". If flip_direction is list,
+            multiple flip augmentations will be applied.
+            It has no effect when flip == False. Default: "horizontal".
+    """
+
+    def __init__(self,
+                 transforms,
+                 img_scale,
+                 img_ratios=None,
+                 flip=False,
+                 flip_direction='horizontal'):
+        self.transforms = Compose(transforms)
+        if img_ratios is not None:
+            img_ratios = img_ratios if isinstance(img_ratios,
+                                                  list) else [img_ratios]
+            assert mmcv.is_list_of(img_ratios, float)
+        if img_scale is None:
+            # mode 1: given img_scale=None and a range of image ratio
+            self.img_scale = None
+            assert mmcv.is_list_of(img_ratios, float)
+        elif isinstance(img_scale, tuple) and mmcv.is_list_of(
+                img_ratios, float):
+            assert len(img_scale) == 2
+            # mode 2: given a scale and a range of image ratio
+            self.img_scale = [(int(img_scale[0] * ratio),
+                               int(img_scale[1] * ratio))
+                              for ratio in img_ratios]
+        else:
+            # mode 3: given multiple scales
+            self.img_scale = img_scale if isinstance(img_scale,
+                                                     list) else [img_scale]
+        assert mmcv.is_list_of(self.img_scale, tuple) or self.img_scale is None
+        self.flip = flip
+        self.img_ratios = img_ratios
+        self.flip_direction = flip_direction if isinstance(
+            flip_direction, list) else [flip_direction]
+        assert mmcv.is_list_of(self.flip_direction, str)
+        if not self.flip and self.flip_direction != ['horizontal']:
+            warnings.warn(
+                'flip_direction has no effect when flip is set to False')
+        if (self.flip
+                and not any([t['type'] == 'RandomFlip' for t in transforms])):
+            warnings.warn(
+                'flip has no effect when RandomFlip is not in transforms')
+
+    def __call__(self, results):
+        """Call function to apply test time augment transforms on results.
+
+        Args:
+            results (dict): Result dict contains the data to transform.
+
+        Returns:
+           dict[str: list]: The augmented data, where each value is wrapped
+               into a list.
+        """
+
+        aug_data = []
+        if self.img_scale is None and mmcv.is_list_of(self.img_ratios, float):
+            h, w = results['img'].shape[:2]
+            img_scale = [(int(w * ratio), int(h * ratio))
+                         for ratio in self.img_ratios]
+        else:
+            img_scale = self.img_scale
+        flip_aug = [False, True] if self.flip else [False]
+        for scale in img_scale:
+            for flip in flip_aug:
+                for direction in self.flip_direction:
+                    _results = results.copy()
+                    _results['scale'] = scale
+                    _results['flip'] = flip
+                    _results['flip_direction'] = direction
+                    data = self.transforms(_results)
+                    aug_data.append(data)
+        # list of dict to dict of list
+        aug_data_dict = {key: [] for key in aug_data[0]}
+        for data in aug_data:
+            for key, val in data.items():
+                aug_data_dict[key].append(val)
+        return aug_data_dict
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(transforms={self.transforms}, '
+        repr_str += f'img_scale={self.img_scale}, flip={self.flip})'
+        repr_str += f'flip_direction={self.flip_direction}'
+        return repr_str

lavis/common/annotator/uniformer/mmseg/datasets/pipelines/transforms.py

+import annotator.uniformer.mmcv as mmcv
+import numpy as np
+from annotator.uniformer.mmcv.utils import deprecated_api_warning, is_tuple_of
+from numpy import random
+
+from ..builder import PIPELINES
+
+
+@PIPELINES.register_module()
+class Resize(object):
+    """Resize images & seg.
+
+    This transform resizes the input image to some scale. If the input dict
+    contains the key "scale", then the scale in the input dict is used,
+    otherwise the specified scale in the init method is used.
+
+    ``img_scale`` can be None, a tuple (single-scale) or a list of tuple
+    (multi-scale). There are 4 multiscale modes:
+
+    - ``ratio_range is not None``:
+    1. When img_scale is None, img_scale is the shape of image in results
+        (img_scale = results['img'].shape[:2]) and the image is resized based
+        on the original size. (mode 1)
+    2. When img_scale is a tuple (single-scale), randomly sample a ratio from
+        the ratio range and multiply it with the image scale. (mode 2)
+
+    - ``ratio_range is None and multiscale_mode == "range"``: randomly sample a
+    scale from the a range. (mode 3)
+
+    - ``ratio_range is None and multiscale_mode == "value"``: randomly sample a
+    scale from multiple scales. (mode 4)
+
+    Args:
+        img_scale (tuple or list[tuple]): Images scales for resizing.
+        multiscale_mode (str): Either "range" or "value".
+        ratio_range (tuple[float]): (min_ratio, max_ratio)
+        keep_ratio (bool): Whether to keep the aspect ratio when resizing the
+            image.
+    """
+
+    def __init__(self,
+                 img_scale=None,
+                 multiscale_mode='range',
+                 ratio_range=None,
+                 keep_ratio=True):
+        if img_scale is None:
+            self.img_scale = None
+        else:
+            if isinstance(img_scale, list):
+                self.img_scale = img_scale
+            else:
+                self.img_scale = [img_scale]
+            assert mmcv.is_list_of(self.img_scale, tuple)
+
+        if ratio_range is not None:
+            # mode 1: given img_scale=None and a range of image ratio
+            # mode 2: given a scale and a range of image ratio
+            assert self.img_scale is None or len(self.img_scale) == 1
+        else:
+            # mode 3 and 4: given multiple scales or a range of scales
+            assert multiscale_mode in ['value', 'range']
+
+        self.multiscale_mode = multiscale_mode
+        self.ratio_range = ratio_range
+        self.keep_ratio = keep_ratio
+
+    @staticmethod
+    def random_select(img_scales):
+        """Randomly select an img_scale from given candidates.
+
+        Args:
+            img_scales (list[tuple]): Images scales for selection.
+
+        Returns:
+            (tuple, int): Returns a tuple ``(img_scale, scale_dix)``,
+                where ``img_scale`` is the selected image scale and
+                ``scale_idx`` is the selected index in the given candidates.
+        """
+
+        assert mmcv.is_list_of(img_scales, tuple)
+        scale_idx = np.random.randint(len(img_scales))
+        img_scale = img_scales[scale_idx]
+        return img_scale, scale_idx
+
+    @staticmethod
+    def random_sample(img_scales):
+        """Randomly sample an img_scale when ``multiscale_mode=='range'``.
+
+        Args:
+            img_scales (list[tuple]): Images scale range for sampling.
+                There must be two tuples in img_scales, which specify the lower
+                and upper bound of image scales.
+
+        Returns:
+            (tuple, None): Returns a tuple ``(img_scale, None)``, where
+                ``img_scale`` is sampled scale and None is just a placeholder
+                to be consistent with :func:`random_select`.
+        """
+
+        assert mmcv.is_list_of(img_scales, tuple) and len(img_scales) == 2
+        img_scale_long = [max(s) for s in img_scales]
+        img_scale_short = [min(s) for s in img_scales]
+        long_edge = np.random.randint(
+            min(img_scale_long),
+            max(img_scale_long) + 1)
+        short_edge = np.random.randint(
+            min(img_scale_short),
+            max(img_scale_short) + 1)
+        img_scale = (long_edge, short_edge)
+        return img_scale, None
+
+    @staticmethod
+    def random_sample_ratio(img_scale, ratio_range):
+        """Randomly sample an img_scale when ``ratio_range`` is specified.
+
+        A ratio will be randomly sampled from the range specified by
+        ``ratio_range``. Then it would be multiplied with ``img_scale`` to
+        generate sampled scale.
+
+        Args:
+            img_scale (tuple): Images scale base to multiply with ratio.
+            ratio_range (tuple[float]): The minimum and maximum ratio to scale
+                the ``img_scale``.
+
+        Returns:
+            (tuple, None): Returns a tuple ``(scale, None)``, where
+                ``scale`` is sampled ratio multiplied with ``img_scale`` and
+                None is just a placeholder to be consistent with
+                :func:`random_select`.
+        """
+
+        assert isinstance(img_scale, tuple) and len(img_scale) == 2
+        min_ratio, max_ratio = ratio_range
+        assert min_ratio <= max_ratio
+        ratio = np.random.random_sample() * (max_ratio - min_ratio) + min_ratio
+        scale = int(img_scale[0] * ratio), int(img_scale[1] * ratio)
+        return scale, None
+
+    def _random_scale(self, results):
+        """Randomly sample an img_scale according to ``ratio_range`` and
+        ``multiscale_mode``.
+
+        If ``ratio_range`` is specified, a ratio will be sampled and be
+        multiplied with ``img_scale``.
+        If multiple scales are specified by ``img_scale``, a scale will be
+        sampled according to ``multiscale_mode``.
+        Otherwise, single scale will be used.
+
+        Args:
+            results (dict): Result dict from :obj:`dataset`.
+
+        Returns:
+            dict: Two new keys 'scale` and 'scale_idx` are added into
+                ``results``, which would be used by subsequent pipelines.
+        """
+
+        if self.ratio_range is not None:
+            if self.img_scale is None:
+                h, w = results['img'].shape[:2]
+                scale, scale_idx = self.random_sample_ratio((w, h),
+                                                            self.ratio_range)
+            else:
+                scale, scale_idx = self.random_sample_ratio(
+                    self.img_scale[0], self.ratio_range)
+        elif len(self.img_scale) == 1:
+            scale, scale_idx = self.img_scale[0], 0
+        elif self.multiscale_mode == 'range':
+            scale, scale_idx = self.random_sample(self.img_scale)
+        elif self.multiscale_mode == 'value':
+            scale, scale_idx = self.random_select(self.img_scale)
+        else:
+            raise NotImplementedError
+
+        results['scale'] = scale
+        results['scale_idx'] = scale_idx
+
+    def _resize_img(self, results):
+        """Resize images with ``results['scale']``."""
+        if self.keep_ratio:
+            img, scale_factor = mmcv.imrescale(
+                results['img'], results['scale'], return_scale=True)
+            # the w_scale and h_scale has minor difference
+            # a real fix should be done in the mmcv.imrescale in the future
+            new_h, new_w = img.shape[:2]
+            h, w = results['img'].shape[:2]
+            w_scale = new_w / w
+            h_scale = new_h / h
+        else:
+            img, w_scale, h_scale = mmcv.imresize(
+                results['img'], results['scale'], return_scale=True)
+        scale_factor = np.array([w_scale, h_scale, w_scale, h_scale],
+                                dtype=np.float32)
+        results['img'] = img
+        results['img_shape'] = img.shape
+        results['pad_shape'] = img.shape  # in case that there is no padding
+        results['scale_factor'] = scale_factor
+        results['keep_ratio'] = self.keep_ratio
+
+    def _resize_seg(self, results):
+        """Resize semantic segmentation map with ``results['scale']``."""
+        for key in results.get('seg_fields', []):
+            if self.keep_ratio:
+                gt_seg = mmcv.imrescale(
+                    results[key], results['scale'], interpolation='nearest')
+            else:
+                gt_seg = mmcv.imresize(
+                    results[key], results['scale'], interpolation='nearest')
+            results[key] = gt_seg
+
+    def __call__(self, results):
+        """Call function to resize images, bounding boxes, masks, semantic
+        segmentation map.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Resized results, 'img_shape', 'pad_shape', 'scale_factor',
+                'keep_ratio' keys are added into result dict.
+        """
+
+        if 'scale' not in results:
+            self._random_scale(results)
+        self._resize_img(results)
+        self._resize_seg(results)
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += (f'(img_scale={self.img_scale}, '
+                     f'multiscale_mode={self.multiscale_mode}, '
+                     f'ratio_range={self.ratio_range}, '
+                     f'keep_ratio={self.keep_ratio})')
+        return repr_str
+
+
+@PIPELINES.register_module()
+class RandomFlip(object):
+    """Flip the image & seg.
+
+    If the input dict contains the key "flip", then the flag will be used,
+    otherwise it will be randomly decided by a ratio specified in the init
+    method.
+
+    Args:
+        prob (float, optional): The flipping probability. Default: None.
+        direction(str, optional): The flipping direction. Options are
+            'horizontal' and 'vertical'. Default: 'horizontal'.
+    """
+
+    @deprecated_api_warning({'flip_ratio': 'prob'}, cls_name='RandomFlip')
+    def __init__(self, prob=None, direction='horizontal'):
+        self.prob = prob
+        self.direction = direction
+        if prob is not None:
+            assert prob >= 0 and prob <= 1
+        assert direction in ['horizontal', 'vertical']
+
+    def __call__(self, results):
+        """Call function to flip bounding boxes, masks, semantic segmentation
+        maps.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Flipped results, 'flip', 'flip_direction' keys are added into
+                result dict.
+        """
+
+        if 'flip' not in results:
+            flip = True if np.random.rand() < self.prob else False
+            results['flip'] = flip
+        if 'flip_direction' not in results:
+            results['flip_direction'] = self.direction
+        if results['flip']:
+            # flip image
+            results['img'] = mmcv.imflip(
+                results['img'], direction=results['flip_direction'])
+
+            # flip segs
+            for key in results.get('seg_fields', []):
+                # use copy() to make numpy stride positive
+                results[key] = mmcv.imflip(
+                    results[key], direction=results['flip_direction']).copy()
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(prob={self.prob})'
+
+
+@PIPELINES.register_module()
+class Pad(object):
+    """Pad the image & mask.
+
+    There are two padding modes: (1) pad to a fixed size and (2) pad to the
+    minimum size that is divisible by some number.
+    Added keys are "pad_shape", "pad_fixed_size", "pad_size_divisor",
+
+    Args:
+        size (tuple, optional): Fixed padding size.
+        size_divisor (int, optional): The divisor of padded size.
+        pad_val (float, optional): Padding value. Default: 0.
+        seg_pad_val (float, optional): Padding value of segmentation map.
+            Default: 255.
+    """
+
+    def __init__(self,
+                 size=None,
+                 size_divisor=None,
+                 pad_val=0,
+                 seg_pad_val=255):
+        self.size = size
+        self.size_divisor = size_divisor
+        self.pad_val = pad_val
+        self.seg_pad_val = seg_pad_val
+        # only one of size and size_divisor should be valid
+        assert size is not None or size_divisor is not None
+        assert size is None or size_divisor is None
+
+    def _pad_img(self, results):
+        """Pad images according to ``self.size``."""
+        if self.size is not None:
+            padded_img = mmcv.impad(
+                results['img'], shape=self.size, pad_val=self.pad_val)
+        elif self.size_divisor is not None:
+            padded_img = mmcv.impad_to_multiple(
+                results['img'], self.size_divisor, pad_val=self.pad_val)
+        results['img'] = padded_img
+        results['pad_shape'] = padded_img.shape
+        results['pad_fixed_size'] = self.size
+        results['pad_size_divisor'] = self.size_divisor
+
+    def _pad_seg(self, results):
+        """Pad masks according to ``results['pad_shape']``."""
+        for key in results.get('seg_fields', []):
+            results[key] = mmcv.impad(
+                results[key],
+                shape=results['pad_shape'][:2],
+                pad_val=self.seg_pad_val)
+
+    def __call__(self, results):
+        """Call function to pad images, masks, semantic segmentation maps.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Updated result dict.
+        """
+
+        self._pad_img(results)
+        self._pad_seg(results)
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(size={self.size}, size_divisor={self.size_divisor}, ' \
+                    f'pad_val={self.pad_val})'
+        return repr_str
+
+
+@PIPELINES.register_module()
+class Normalize(object):
+    """Normalize the image.
+
+    Added key is "img_norm_cfg".
+
+    Args:
+        mean (sequence): Mean values of 3 channels.
+        std (sequence): Std values of 3 channels.
+        to_rgb (bool): Whether to convert the image from BGR to RGB,
+            default is true.
+    """
+
+    def __init__(self, mean, std, to_rgb=True):
+        self.mean = np.array(mean, dtype=np.float32)
+        self.std = np.array(std, dtype=np.float32)
+        self.to_rgb = to_rgb
+
+    def __call__(self, results):
+        """Call function to normalize images.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Normalized results, 'img_norm_cfg' key is added into
+                result dict.
+        """
+
+        results['img'] = mmcv.imnormalize(results['img'], self.mean, self.std,
+                                          self.to_rgb)
+        results['img_norm_cfg'] = dict(
+            mean=self.mean, std=self.std, to_rgb=self.to_rgb)
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(mean={self.mean}, std={self.std}, to_rgb=' \
+                    f'{self.to_rgb})'
+        return repr_str
+
+
+@PIPELINES.register_module()
+class Rerange(object):
+    """Rerange the image pixel value.
+
+    Args:
+        min_value (float or int): Minimum value of the reranged image.
+            Default: 0.
+        max_value (float or int): Maximum value of the reranged image.
+            Default: 255.
+    """
+
+    def __init__(self, min_value=0, max_value=255):
+        assert isinstance(min_value, float) or isinstance(min_value, int)
+        assert isinstance(max_value, float) or isinstance(max_value, int)
+        assert min_value < max_value
+        self.min_value = min_value
+        self.max_value = max_value
+
+    def __call__(self, results):
+        """Call function to rerange images.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+        Returns:
+            dict: Reranged results.
+        """
+
+        img = results['img']
+        img_min_value = np.min(img)
+        img_max_value = np.max(img)
+
+        assert img_min_value < img_max_value
+        # rerange to [0, 1]
+        img = (img - img_min_value) / (img_max_value - img_min_value)
+        # rerange to [min_value, max_value]
+        img = img * (self.max_value - self.min_value) + self.min_value
+        results['img'] = img
+
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(min_value={self.min_value}, max_value={self.max_value})'
+        return repr_str
+
+
+@PIPELINES.register_module()
+class CLAHE(object):
+    """Use CLAHE method to process the image.
+
+    See `ZUIDERVELD,K. Contrast Limited Adaptive Histogram Equalization[J].
+    Graphics Gems, 1994:474-485.` for more information.
+
+    Args:
+        clip_limit (float): Threshold for contrast limiting. Default: 40.0.
+        tile_grid_size (tuple[int]): Size of grid for histogram equalization.
+            Input image will be divided into equally sized rectangular tiles.
+            It defines the number of tiles in row and column. Default: (8, 8).
+    """
+
+    def __init__(self, clip_limit=40.0, tile_grid_size=(8, 8)):
+        assert isinstance(clip_limit, (float, int))
+        self.clip_limit = clip_limit
+        assert is_tuple_of(tile_grid_size, int)
+        assert len(tile_grid_size) == 2
+        self.tile_grid_size = tile_grid_size
+
+    def __call__(self, results):
+        """Call function to Use CLAHE method process images.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Processed results.
+        """
+
+        for i in range(results['img'].shape[2]):
+            results['img'][:, :, i] = mmcv.clahe(
+                np.array(results['img'][:, :, i], dtype=np.uint8),
+                self.clip_limit, self.tile_grid_size)
+
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(clip_limit={self.clip_limit}, '\
+                    f'tile_grid_size={self.tile_grid_size})'
+        return repr_str
+
+
+@PIPELINES.register_module()
+class RandomCrop(object):
+    """Random crop the image & seg.
+
+    Args:
+        crop_size (tuple): Expected size after cropping, (h, w).
+        cat_max_ratio (float): The maximum ratio that single category could
+            occupy.
+    """
+
+    def __init__(self, crop_size, cat_max_ratio=1., ignore_index=255):
+        assert crop_size[0] > 0 and crop_size[1] > 0
+        self.crop_size = crop_size
+        self.cat_max_ratio = cat_max_ratio
+        self.ignore_index = ignore_index
+
+    def get_crop_bbox(self, img):
+        """Randomly get a crop bounding box."""
+        margin_h = max(img.shape[0] - self.crop_size[0], 0)
+        margin_w = max(img.shape[1] - self.crop_size[1], 0)
+        offset_h = np.random.randint(0, margin_h + 1)
+        offset_w = np.random.randint(0, margin_w + 1)
+        crop_y1, crop_y2 = offset_h, offset_h + self.crop_size[0]
+        crop_x1, crop_x2 = offset_w, offset_w + self.crop_size[1]
+
+        return crop_y1, crop_y2, crop_x1, crop_x2
+
+    def crop(self, img, crop_bbox):
+        """Crop from ``img``"""
+        crop_y1, crop_y2, crop_x1, crop_x2 = crop_bbox
+        img = img[crop_y1:crop_y2, crop_x1:crop_x2, ...]
+        return img
+
+    def __call__(self, results):
+        """Call function to randomly crop images, semantic segmentation maps.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Randomly cropped results, 'img_shape' key in result dict is
+                updated according to crop size.
+        """
+
+        img = results['img']
+        crop_bbox = self.get_crop_bbox(img)
+        if self.cat_max_ratio < 1.:
+            # Repeat 10 times
+            for _ in range(10):
+                seg_temp = self.crop(results['gt_semantic_seg'], crop_bbox)
+                labels, cnt = np.unique(seg_temp, return_counts=True)
+                cnt = cnt[labels != self.ignore_index]
+                if len(cnt) > 1 and np.max(cnt) / np.sum(
+                        cnt) < self.cat_max_ratio:
+                    break
+                crop_bbox = self.get_crop_bbox(img)
+
+        # crop the image
+        img = self.crop(img, crop_bbox)
+        img_shape = img.shape
+        results['img'] = img
+        results['img_shape'] = img_shape
+
+        # crop semantic seg
+        for key in results.get('seg_fields', []):
+            results[key] = self.crop(results[key], crop_bbox)
+
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(crop_size={self.crop_size})'
+
+
+@PIPELINES.register_module()
+class RandomRotate(object):
+    """Rotate the image & seg.
+
+    Args:
+        prob (float): The rotation probability.
+        degree (float, tuple[float]): Range of degrees to select from. If
+            degree is a number instead of tuple like (min, max),
+            the range of degree will be (``-degree``, ``+degree``)
+        pad_val (float, optional): Padding value of image. Default: 0.
+        seg_pad_val (float, optional): Padding value of segmentation map.
+            Default: 255.
+        center (tuple[float], optional): Center point (w, h) of the rotation in
+            the source image. If not specified, the center of the image will be
+            used. Default: None.
+        auto_bound (bool): Whether to adjust the image size to cover the whole
+            rotated image. Default: False
+    """
+
+    def __init__(self,
+                 prob,
+                 degree,
+                 pad_val=0,
+                 seg_pad_val=255,
+                 center=None,
+                 auto_bound=False):
+        self.prob = prob
+        assert prob >= 0 and prob <= 1
+        if isinstance(degree, (float, int)):
+            assert degree > 0, f'degree {degree} should be positive'
+            self.degree = (-degree, degree)
+        else:
+            self.degree = degree
+        assert len(self.degree) == 2, f'degree {self.degree} should be a ' \
+                                      f'tuple of (min, max)'
+        self.pal_val = pad_val
+        self.seg_pad_val = seg_pad_val
+        self.center = center
+        self.auto_bound = auto_bound
+
+    def __call__(self, results):
+        """Call function to rotate image, semantic segmentation maps.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Rotated results.
+        """
+
+        rotate = True if np.random.rand() < self.prob else False
+        degree = np.random.uniform(min(*self.degree), max(*self.degree))
+        if rotate:
+            # rotate image
+            results['img'] = mmcv.imrotate(
+                results['img'],
+                angle=degree,
+                border_value=self.pal_val,
+                center=self.center,
+                auto_bound=self.auto_bound)
+
+            # rotate segs
+            for key in results.get('seg_fields', []):
+                results[key] = mmcv.imrotate(
+                    results[key],
+                    angle=degree,
+                    border_value=self.seg_pad_val,
+                    center=self.center,
+                    auto_bound=self.auto_bound,
+                    interpolation='nearest')
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(prob={self.prob}, ' \
+                    f'degree={self.degree}, ' \
+                    f'pad_val={self.pal_val}, ' \
+                    f'seg_pad_val={self.seg_pad_val}, ' \
+                    f'center={self.center}, ' \
+                    f'auto_bound={self.auto_bound})'
+        return repr_str
+
+
+@PIPELINES.register_module()
+class RGB2Gray(object):
+    """Convert RGB image to grayscale image.
+
+    This transform calculate the weighted mean of input image channels with
+    ``weights`` and then expand the channels to ``out_channels``. When
+    ``out_channels`` is None, the number of output channels is the same as
+    input channels.
+
+    Args:
+        out_channels (int): Expected number of output channels after
+            transforming. Default: None.
+        weights (tuple[float]): The weights to calculate the weighted mean.
+            Default: (0.299, 0.587, 0.114).
+    """
+
+    def __init__(self, out_channels=None, weights=(0.299, 0.587, 0.114)):
+        assert out_channels is None or out_channels > 0
+        self.out_channels = out_channels
+        assert isinstance(weights, tuple)
+        for item in weights:
+            assert isinstance(item, (float, int))
+        self.weights = weights
+
+    def __call__(self, results):
+        """Call function to convert RGB image to grayscale image.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Result dict with grayscale image.
+        """
+        img = results['img']
+        assert len(img.shape) == 3
+        assert img.shape[2] == len(self.weights)
+        weights = np.array(self.weights).reshape((1, 1, -1))
+        img = (img * weights).sum(2, keepdims=True)
+        if self.out_channels is None:
+            img = img.repeat(weights.shape[2], axis=2)
+        else:
+            img = img.repeat(self.out_channels, axis=2)
+
+        results['img'] = img
+        results['img_shape'] = img.shape
+
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += f'(out_channels={self.out_channels}, ' \
+                    f'weights={self.weights})'
+        return repr_str
+
+
+@PIPELINES.register_module()
+class AdjustGamma(object):
+    """Using gamma correction to process the image.
+
+    Args:
+        gamma (float or int): Gamma value used in gamma correction.
+            Default: 1.0.
+    """
+
+    def __init__(self, gamma=1.0):
+        assert isinstance(gamma, float) or isinstance(gamma, int)
+        assert gamma > 0
+        self.gamma = gamma
+        inv_gamma = 1.0 / gamma
+        self.table = np.array([(i / 255.0)**inv_gamma * 255
+                               for i in np.arange(256)]).astype('uint8')
+
+    def __call__(self, results):
+        """Call function to process the image with gamma correction.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Processed results.
+        """
+
+        results['img'] = mmcv.lut_transform(
+            np.array(results['img'], dtype=np.uint8), self.table)
+
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(gamma={self.gamma})'
+
+
+@PIPELINES.register_module()
+class SegRescale(object):
+    """Rescale semantic segmentation maps.
+
+    Args:
+        scale_factor (float): The scale factor of the final output.
+    """
+
+    def __init__(self, scale_factor=1):
+        self.scale_factor = scale_factor
+
+    def __call__(self, results):
+        """Call function to scale the semantic segmentation map.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Result dict with semantic segmentation map scaled.
+        """
+        for key in results.get('seg_fields', []):
+            if self.scale_factor != 1:
+                results[key] = mmcv.imrescale(
+                    results[key], self.scale_factor, interpolation='nearest')
+        return results
+
+    def __repr__(self):
+        return self.__class__.__name__ + f'(scale_factor={self.scale_factor})'
+
+
+@PIPELINES.register_module()
+class PhotoMetricDistortion(object):
+    """Apply photometric distortion to image sequentially, every transformation
+    is applied with a probability of 0.5. The position of random contrast is in
+    second or second to last.
+
+    1. random brightness
+    2. random contrast (mode 0)
+    3. convert color from BGR to HSV
+    4. random saturation
+    5. random hue
+    6. convert color from HSV to BGR
+    7. random contrast (mode 1)
+
+    Args:
+        brightness_delta (int): delta of brightness.
+        contrast_range (tuple): range of contrast.
+        saturation_range (tuple): range of saturation.
+        hue_delta (int): delta of hue.
+    """
+
+    def __init__(self,
+                 brightness_delta=32,
+                 contrast_range=(0.5, 1.5),
+                 saturation_range=(0.5, 1.5),
+                 hue_delta=18):
+        self.brightness_delta = brightness_delta
+        self.contrast_lower, self.contrast_upper = contrast_range
+        self.saturation_lower, self.saturation_upper = saturation_range
+        self.hue_delta = hue_delta
+
+    def convert(self, img, alpha=1, beta=0):
+        """Multiple with alpha and add beat with clip."""
+        img = img.astype(np.float32) * alpha + beta
+        img = np.clip(img, 0, 255)
+        return img.astype(np.uint8)
+
+    def brightness(self, img):
+        """Brightness distortion."""
+        if random.randint(2):
+            return self.convert(
+                img,
+                beta=random.uniform(-self.brightness_delta,
+                                    self.brightness_delta))
+        return img
+
+    def contrast(self, img):
+        """Contrast distortion."""
+        if random.randint(2):
+            return self.convert(
+                img,
+                alpha=random.uniform(self.contrast_lower, self.contrast_upper))
+        return img
+
+    def saturation(self, img):
+        """Saturation distortion."""
+        if random.randint(2):
+            img = mmcv.bgr2hsv(img)
+            img[:, :, 1] = self.convert(
+                img[:, :, 1],
+                alpha=random.uniform(self.saturation_lower,
+                                     self.saturation_upper))
+            img = mmcv.hsv2bgr(img)
+        return img
+
+    def hue(self, img):
+        """Hue distortion."""
+        if random.randint(2):
+            img = mmcv.bgr2hsv(img)
+            img[:, :,
+                0] = (img[:, :, 0].astype(int) +
+                      random.randint(-self.hue_delta, self.hue_delta)) % 180
+            img = mmcv.hsv2bgr(img)
+        return img
+
+    def __call__(self, results):
+        """Call function to perform photometric distortion on images.
+
+        Args:
+            results (dict): Result dict from loading pipeline.
+
+        Returns:
+            dict: Result dict with images distorted.
+        """
+
+        img = results['img']
+        # random brightness
+        img = self.brightness(img)
+
+        # mode == 0 --> do random contrast first
+        # mode == 1 --> do random contrast last
+        mode = random.randint(2)
+        if mode == 1:
+            img = self.contrast(img)
+
+        # random saturation
+        img = self.saturation(img)
+
+        # random hue
+        img = self.hue(img)
+
+        # random contrast
+        if mode == 0:
+            img = self.contrast(img)
+
+        results['img'] = img
+        return results
+
+    def __repr__(self):
+        repr_str = self.__class__.__name__
+        repr_str += (f'(brightness_delta={self.brightness_delta}, '
+                     f'contrast_range=({self.contrast_lower}, '
+                     f'{self.contrast_upper}), '
+                     f'saturation_range=({self.saturation_lower}, '
+                     f'{self.saturation_upper}), '
+                     f'hue_delta={self.hue_delta})')
+        return repr_str

lavis/common/annotator/uniformer/mmseg/datasets/stare.py

+import os.path as osp
+
+from .builder import DATASETS
+from .custom import CustomDataset
+
+
+@DATASETS.register_module()
+class STAREDataset(CustomDataset):
+    """STARE dataset.
+
+    In segmentation map annotation for STARE, 0 stands for background, which is
+    included in 2 categories. ``reduce_zero_label`` is fixed to False. The
+    ``img_suffix`` is fixed to '.png' and ``seg_map_suffix`` is fixed to
+    '.ah.png'.
+    """
+
+    CLASSES = ('background', 'vessel')
+
+    PALETTE = [[120, 120, 120], [6, 230, 230]]
+
+    def __init__(self, **kwargs):
+        super(STAREDataset, self).__init__(
+            img_suffix='.png',
+            seg_map_suffix='.ah.png',
+            reduce_zero_label=False,
+            **kwargs)
+        assert osp.exists(self.img_dir)