3648a469f0fb07172ece85292a5ce8613ac37e3239706f93cac30eb840e698f2

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/parrots_jit.py

@@ -0,0 +1,41 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import os
+
+from .parrots_wrapper import TORCH_VERSION
+
+parrots_jit_option = os.getenv('PARROTS_JIT_OPTION')
+
+if TORCH_VERSION == 'parrots' and parrots_jit_option == 'ON':
+    from parrots.jit import pat as jit
+else:
+
+    def jit(func=None,
+            check_input=None,
+            full_shape=True,
+            derivate=False,
+            coderize=False,
+            optimize=False):
+
+        def wrapper(func):
+
+            def wrapper_inner(*args, **kargs):
+                return func(*args, **kargs)
+
+            return wrapper_inner
+
+        if func is None:
+            return wrapper
+        else:
+            return func
+
+
+if TORCH_VERSION == 'parrots':
+    from parrots.utils.tester import skip_no_elena
+else:
+
+    def skip_no_elena(func):
+
+        def wrapper(*args, **kargs):
+            return func(*args, **kargs)
+
+        return wrapper

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/parrots_wrapper.py

@@ -0,0 +1,107 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from functools import partial
+
+import torch
+
+TORCH_VERSION = torch.__version__
+
+
+def is_rocm_pytorch() -> bool:
+    is_rocm = False
+    if TORCH_VERSION != 'parrots':
+        try:
+            from torch.utils.cpp_extension import ROCM_HOME
+            is_rocm = True if ((torch.version.hip is not None) and
+                               (ROCM_HOME is not None)) else False
+        except ImportError:
+            pass
+    return is_rocm
+
+
+def _get_cuda_home():
+    if TORCH_VERSION == 'parrots':
+        from parrots.utils.build_extension import CUDA_HOME
+    else:
+        if is_rocm_pytorch():
+            from torch.utils.cpp_extension import ROCM_HOME
+            CUDA_HOME = ROCM_HOME
+        else:
+            from torch.utils.cpp_extension import CUDA_HOME
+    return CUDA_HOME
+
+
+def get_build_config():
+    if TORCH_VERSION == 'parrots':
+        from parrots.config import get_build_info
+        return get_build_info()
+    else:
+        return torch.__config__.show()
+
+
+def _get_conv():
+    if TORCH_VERSION == 'parrots':
+        from parrots.nn.modules.conv import _ConvNd, _ConvTransposeMixin
+    else:
+        from torch.nn.modules.conv import _ConvNd, _ConvTransposeMixin
+    return _ConvNd, _ConvTransposeMixin
+
+
+def _get_dataloader():
+    if TORCH_VERSION == 'parrots':
+        from torch.utils.data import DataLoader, PoolDataLoader
+    else:
+        from torch.utils.data import DataLoader
+        PoolDataLoader = DataLoader
+    return DataLoader, PoolDataLoader
+
+
+def _get_extension():
+    if TORCH_VERSION == 'parrots':
+        from parrots.utils.build_extension import BuildExtension, Extension
+        CppExtension = partial(Extension, cuda=False)
+        CUDAExtension = partial(Extension, cuda=True)
+    else:
+        from torch.utils.cpp_extension import (BuildExtension, CppExtension,
+                                               CUDAExtension)
+    return BuildExtension, CppExtension, CUDAExtension
+
+
+def _get_pool():
+    if TORCH_VERSION == 'parrots':
+        from parrots.nn.modules.pool import (_AdaptiveAvgPoolNd,
+                                             _AdaptiveMaxPoolNd, _AvgPoolNd,
+                                             _MaxPoolNd)
+    else:
+        from torch.nn.modules.pooling import (_AdaptiveAvgPoolNd,
+                                              _AdaptiveMaxPoolNd, _AvgPoolNd,
+                                              _MaxPoolNd)
+    return _AdaptiveAvgPoolNd, _AdaptiveMaxPoolNd, _AvgPoolNd, _MaxPoolNd
+
+
+def _get_norm():
+    if TORCH_VERSION == 'parrots':
+        from parrots.nn.modules.batchnorm import _BatchNorm, _InstanceNorm
+        SyncBatchNorm_ = torch.nn.SyncBatchNorm2d
+    else:
+        from torch.nn.modules.instancenorm import _InstanceNorm
+        from torch.nn.modules.batchnorm import _BatchNorm
+        SyncBatchNorm_ = torch.nn.SyncBatchNorm
+    return _BatchNorm, _InstanceNorm, SyncBatchNorm_
+
+
+_ConvNd, _ConvTransposeMixin = _get_conv()
+DataLoader, PoolDataLoader = _get_dataloader()
+BuildExtension, CppExtension, CUDAExtension = _get_extension()
+_BatchNorm, _InstanceNorm, SyncBatchNorm_ = _get_norm()
+_AdaptiveAvgPoolNd, _AdaptiveMaxPoolNd, _AvgPoolNd, _MaxPoolNd = _get_pool()
+
+
+class SyncBatchNorm(SyncBatchNorm_):
+
+    def _check_input_dim(self, input):
+        if TORCH_VERSION == 'parrots':
+            if input.dim() < 2:
+                raise ValueError(
+                    f'expected at least 2D input (got {input.dim()}D input)')
+        else:
+            super()._check_input_dim(input)

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/path.py

@@ -0,0 +1,101 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import os
+import os.path as osp
+from pathlib import Path
+
+from .misc import is_str
+
+
+def is_filepath(x):
+    return is_str(x) or isinstance(x, Path)
+
+
+def fopen(filepath, *args, **kwargs):
+    if is_str(filepath):
+        return open(filepath, *args, **kwargs)
+    elif isinstance(filepath, Path):
+        return filepath.open(*args, **kwargs)
+    raise ValueError('`filepath` should be a string or a Path')
+
+
+def check_file_exist(filename, msg_tmpl='file "{}" does not exist'):
+    if not osp.isfile(filename):
+        raise FileNotFoundError(msg_tmpl.format(filename))
+
+
+def mkdir_or_exist(dir_name, mode=0o777):
+    if dir_name == '':
+        return
+    dir_name = osp.expanduser(dir_name)
+    os.makedirs(dir_name, mode=mode, exist_ok=True)
+
+
+def symlink(src, dst, overwrite=True, **kwargs):
+    if os.path.lexists(dst) and overwrite:
+        os.remove(dst)
+    os.symlink(src, dst, **kwargs)
+
+
+def scandir(dir_path, suffix=None, recursive=False, case_sensitive=True):
+    """Scan a directory to find the interested files.
+
+    Args:
+        dir_path (str | obj:`Path`): Path of the directory.
+        suffix (str | tuple(str), optional): File suffix that we are
+            interested in. Default: None.
+        recursive (bool, optional): If set to True, recursively scan the
+            directory. Default: False.
+        case_sensitive (bool, optional) : If set to False, ignore the case of
+            suffix. Default: True.
+
+    Returns:
+        A generator for all the interested files with relative paths.
+    """
+    if isinstance(dir_path, (str, Path)):
+        dir_path = str(dir_path)
+    else:
+        raise TypeError('"dir_path" must be a string or Path object')
+
+    if (suffix is not None) and not isinstance(suffix, (str, tuple)):
+        raise TypeError('"suffix" must be a string or tuple of strings')
+
+    if suffix is not None and not case_sensitive:
+        suffix = suffix.lower() if isinstance(suffix, str) else tuple(
+            item.lower() for item in suffix)
+
+    root = dir_path
+
+    def _scandir(dir_path, suffix, recursive, case_sensitive):
+        for entry in os.scandir(dir_path):
+            if not entry.name.startswith('.') and entry.is_file():
+                rel_path = osp.relpath(entry.path, root)
+                _rel_path = rel_path if case_sensitive else rel_path.lower()
+                if suffix is None or _rel_path.endswith(suffix):
+                    yield rel_path
+            elif recursive and os.path.isdir(entry.path):
+                # scan recursively if entry.path is a directory
+                yield from _scandir(entry.path, suffix, recursive,
+                                    case_sensitive)
+
+    return _scandir(dir_path, suffix, recursive, case_sensitive)
+
+
+def find_vcs_root(path, markers=('.git', )):
+    """Finds the root directory (including itself) of specified markers.
+
+    Args:
+        path (str): Path of directory or file.
+        markers (list[str], optional): List of file or directory names.
+
+    Returns:
+        The directory contained one of the markers or None if not found.
+    """
+    if osp.isfile(path):
+        path = osp.dirname(path)
+
+    prev, cur = None, osp.abspath(osp.expanduser(path))
+    while cur != prev:
+        if any(osp.exists(osp.join(cur, marker)) for marker in markers):
+            return cur
+        prev, cur = cur, osp.split(cur)[0]
+    return None

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/progressbar.py

@@ -0,0 +1,208 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import sys
+from collections.abc import Iterable
+from multiprocessing import Pool
+from shutil import get_terminal_size
+
+from .timer import Timer
+
+
+class ProgressBar:
+    """A progress bar which can print the progress."""
+
+    def __init__(self, task_num=0, bar_width=50, start=True, file=sys.stdout):
+        self.task_num = task_num
+        self.bar_width = bar_width
+        self.completed = 0
+        self.file = file
+        if start:
+            self.start()
+
+    @property
+    def terminal_width(self):
+        width, _ = get_terminal_size()
+        return width
+
+    def start(self):
+        if self.task_num > 0:
+            self.file.write(f'[{" " * self.bar_width}] 0/{self.task_num}, '
+                            'elapsed: 0s, ETA:')
+        else:
+            self.file.write('completed: 0, elapsed: 0s')
+        self.file.flush()
+        self.timer = Timer()
+
+    def update(self, num_tasks=1):
+        assert num_tasks > 0
+        self.completed += num_tasks
+        elapsed = self.timer.since_start()
+        if elapsed > 0:
+            fps = self.completed / elapsed
+        else:
+            fps = float('inf')
+        if self.task_num > 0:
+            percentage = self.completed / float(self.task_num)
+            eta = int(elapsed * (1 - percentage) / percentage + 0.5)
+            msg = f'\r[{{}}] {self.completed}/{self.task_num}, ' \
+                  f'{fps:.1f} task/s, elapsed: {int(elapsed + 0.5)}s, ' \
+                  f'ETA: {eta:5}s'
+
+            bar_width = min(self.bar_width,
+                            int(self.terminal_width - len(msg)) + 2,
+                            int(self.terminal_width * 0.6))
+            bar_width = max(2, bar_width)
+            mark_width = int(bar_width * percentage)
+            bar_chars = '>' * mark_width + ' ' * (bar_width - mark_width)
+            self.file.write(msg.format(bar_chars))
+        else:
+            self.file.write(
+                f'completed: {self.completed}, elapsed: {int(elapsed + 0.5)}s,'
+                f' {fps:.1f} tasks/s')
+        self.file.flush()
+
+
+def track_progress(func, tasks, bar_width=50, file=sys.stdout, **kwargs):
+    """Track the progress of tasks execution with a progress bar.
+
+    Tasks are done with a simple for-loop.
+
+    Args:
+        func (callable): The function to be applied to each task.
+        tasks (list or tuple[Iterable, int]): A list of tasks or
+            (tasks, total num).
+        bar_width (int): Width of progress bar.
+
+    Returns:
+        list: The task results.
+    """
+    if isinstance(tasks, tuple):
+        assert len(tasks) == 2
+        assert isinstance(tasks[0], Iterable)
+        assert isinstance(tasks[1], int)
+        task_num = tasks[1]
+        tasks = tasks[0]
+    elif isinstance(tasks, Iterable):
+        task_num = len(tasks)
+    else:
+        raise TypeError(
+            '"tasks" must be an iterable object or a (iterator, int) tuple')
+    prog_bar = ProgressBar(task_num, bar_width, file=file)
+    results = []
+    for task in tasks:
+        results.append(func(task, **kwargs))
+        prog_bar.update()
+    prog_bar.file.write('\n')
+    return results
+
+
+def init_pool(process_num, initializer=None, initargs=None):
+    if initializer is None:
+        return Pool(process_num)
+    elif initargs is None:
+        return Pool(process_num, initializer)
+    else:
+        if not isinstance(initargs, tuple):
+            raise TypeError('"initargs" must be a tuple')
+        return Pool(process_num, initializer, initargs)
+
+
+def track_parallel_progress(func,
+                            tasks,
+                            nproc,
+                            initializer=None,
+                            initargs=None,
+                            bar_width=50,
+                            chunksize=1,
+                            skip_first=False,
+                            keep_order=True,
+                            file=sys.stdout):
+    """Track the progress of parallel task execution with a progress bar.
+
+    The built-in :mod:`multiprocessing` module is used for process pools and
+    tasks are done with :func:`Pool.map` or :func:`Pool.imap_unordered`.
+
+    Args:
+        func (callable): The function to be applied to each task.
+        tasks (list or tuple[Iterable, int]): A list of tasks or
+            (tasks, total num).
+        nproc (int): Process (worker) number.
+        initializer (None or callable): Refer to :class:`multiprocessing.Pool`
+            for details.
+        initargs (None or tuple): Refer to :class:`multiprocessing.Pool` for
+            details.
+        chunksize (int): Refer to :class:`multiprocessing.Pool` for details.
+        bar_width (int): Width of progress bar.
+        skip_first (bool): Whether to skip the first sample for each worker
+            when estimating fps, since the initialization step may takes
+            longer.
+        keep_order (bool): If True, :func:`Pool.imap` is used, otherwise
+            :func:`Pool.imap_unordered` is used.
+
+    Returns:
+        list: The task results.
+    """
+    if isinstance(tasks, tuple):
+        assert len(tasks) == 2
+        assert isinstance(tasks[0], Iterable)
+        assert isinstance(tasks[1], int)
+        task_num = tasks[1]
+        tasks = tasks[0]
+    elif isinstance(tasks, Iterable):
+        task_num = len(tasks)
+    else:
+        raise TypeError(
+            '"tasks" must be an iterable object or a (iterator, int) tuple')
+    pool = init_pool(nproc, initializer, initargs)
+    start = not skip_first
+    task_num -= nproc * chunksize * int(skip_first)
+    prog_bar = ProgressBar(task_num, bar_width, start, file=file)
+    results = []
+    if keep_order:
+        gen = pool.imap(func, tasks, chunksize)
+    else:
+        gen = pool.imap_unordered(func, tasks, chunksize)
+    for result in gen:
+        results.append(result)
+        if skip_first:
+            if len(results) < nproc * chunksize:
+                continue
+            elif len(results) == nproc * chunksize:
+                prog_bar.start()
+                continue
+        prog_bar.update()
+    prog_bar.file.write('\n')
+    pool.close()
+    pool.join()
+    return results
+
+
+def track_iter_progress(tasks, bar_width=50, file=sys.stdout):
+    """Track the progress of tasks iteration or enumeration with a progress
+    bar.
+
+    Tasks are yielded with a simple for-loop.
+
+    Args:
+        tasks (list or tuple[Iterable, int]): A list of tasks or
+            (tasks, total num).
+        bar_width (int): Width of progress bar.
+
+    Yields:
+        list: The task results.
+    """
+    if isinstance(tasks, tuple):
+        assert len(tasks) == 2
+        assert isinstance(tasks[0], Iterable)
+        assert isinstance(tasks[1], int)
+        task_num = tasks[1]
+        tasks = tasks[0]
+    elif isinstance(tasks, Iterable):
+        task_num = len(tasks)
+    else:
+        raise TypeError(
+            '"tasks" must be an iterable object or a (iterator, int) tuple')
+    prog_bar = ProgressBar(task_num, bar_width, file=file)
+    for task in tasks:
+        yield task
+        prog_bar.update()
+    prog_bar.file.write('\n')

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/registry.py

@@ -0,0 +1,315 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import inspect
+import warnings
+from functools import partial
+
+from .misc import is_seq_of
+
+
+def build_from_cfg(cfg, registry, default_args=None):
+    """Build a module from config dict.
+
+    Args:
+        cfg (dict): Config dict. It should at least contain the key "type".
+        registry (:obj:`Registry`): The registry to search the type from.
+        default_args (dict, optional): Default initialization arguments.
+
+    Returns:
+        object: The constructed object.
+    """
+    if not isinstance(cfg, dict):
+        raise TypeError(f'cfg must be a dict, but got {type(cfg)}')
+    if 'type' not in cfg:
+        if default_args is None or 'type' not in default_args:
+            raise KeyError(
+                '`cfg` or `default_args` must contain the key "type", '
+                f'but got {cfg}\n{default_args}')
+    if not isinstance(registry, Registry):
+        raise TypeError('registry must be an mmcv.Registry object, '
+                        f'but got {type(registry)}')
+    if not (isinstance(default_args, dict) or default_args is None):
+        raise TypeError('default_args must be a dict or None, '
+                        f'but got {type(default_args)}')
+
+    args = cfg.copy()
+
+    if default_args is not None:
+        for name, value in default_args.items():
+            args.setdefault(name, value)
+
+    obj_type = args.pop('type')
+    if isinstance(obj_type, str):
+        obj_cls = registry.get(obj_type)
+        if obj_cls is None:
+            raise KeyError(
+                f'{obj_type} is not in the {registry.name} registry')
+    elif inspect.isclass(obj_type):
+        obj_cls = obj_type
+    else:
+        raise TypeError(
+            f'type must be a str or valid type, but got {type(obj_type)}')
+    try:
+        return obj_cls(**args)
+    except Exception as e:
+        # Normal TypeError does not print class name.
+        raise type(e)(f'{obj_cls.__name__}: {e}')
+
+
+class Registry:
+    """A registry to map strings to classes.
+
+    Registered object could be built from registry.
+    Example:
+        >>> MODELS = Registry('models')
+        >>> @MODELS.register_module()
+        >>> class ResNet:
+        >>>     pass
+        >>> resnet = MODELS.build(dict(type='ResNet'))
+
+    Please refer to
+    https://mmcv.readthedocs.io/en/latest/understand_mmcv/registry.html for
+    advanced usage.
+
+    Args:
+        name (str): Registry name.
+        build_func(func, optional): Build function to construct instance from
+            Registry, func:`build_from_cfg` is used if neither ``parent`` or
+            ``build_func`` is specified. If ``parent`` is specified and
+            ``build_func`` is not given,  ``build_func`` will be inherited
+            from ``parent``. Default: None.
+        parent (Registry, optional): Parent registry. The class registered in
+            children registry could be built from parent. Default: None.
+        scope (str, optional): The scope of registry. It is the key to search
+            for children registry. If not specified, scope will be the name of
+            the package where class is defined, e.g. mmdet, mmcls, mmseg.
+            Default: None.
+    """
+
+    def __init__(self, name, build_func=None, parent=None, scope=None):
+        self._name = name
+        self._module_dict = dict()
+        self._children = dict()
+        self._scope = self.infer_scope() if scope is None else scope
+
+        # self.build_func will be set with the following priority:
+        # 1. build_func
+        # 2. parent.build_func
+        # 3. build_from_cfg
+        if build_func is None:
+            if parent is not None:
+                self.build_func = parent.build_func
+            else:
+                self.build_func = build_from_cfg
+        else:
+            self.build_func = build_func
+        if parent is not None:
+            assert isinstance(parent, Registry)
+            parent._add_children(self)
+            self.parent = parent
+        else:
+            self.parent = None
+
+    def __len__(self):
+        return len(self._module_dict)
+
+    def __contains__(self, key):
+        return self.get(key) is not None
+
+    def __repr__(self):
+        format_str = self.__class__.__name__ + \
+                     f'(name={self._name}, ' \
+                     f'items={self._module_dict})'
+        return format_str
+
+    @staticmethod
+    def infer_scope():
+        """Infer the scope of registry.
+
+        The name of the package where registry is defined will be returned.
+
+        Example:
+            # in mmdet/models/backbone/resnet.py
+            >>> MODELS = Registry('models')
+            >>> @MODELS.register_module()
+            >>> class ResNet:
+            >>>     pass
+            The scope of ``ResNet`` will be ``mmdet``.
+
+
+        Returns:
+            scope (str): The inferred scope name.
+        """
+        # inspect.stack() trace where this function is called, the index-2
+        # indicates the frame where `infer_scope()` is called
+        filename = inspect.getmodule(inspect.stack()[2][0]).__name__
+        split_filename = filename.split('.')
+        return split_filename[0]
+
+    @staticmethod
+    def split_scope_key(key):
+        """Split scope and key.
+
+        The first scope will be split from key.
+
+        Examples:
+            >>> Registry.split_scope_key('mmdet.ResNet')
+            'mmdet', 'ResNet'
+            >>> Registry.split_scope_key('ResNet')
+            None, 'ResNet'
+
+        Return:
+            scope (str, None): The first scope.
+            key (str): The remaining key.
+        """
+        split_index = key.find('.')
+        if split_index != -1:
+            return key[:split_index], key[split_index + 1:]
+        else:
+            return None, key
+
+    @property
+    def name(self):
+        return self._name
+
+    @property
+    def scope(self):
+        return self._scope
+
+    @property
+    def module_dict(self):
+        return self._module_dict
+
+    @property
+    def children(self):
+        return self._children
+
+    def get(self, key):
+        """Get the registry record.
+
+        Args:
+            key (str): The class name in string format.
+
+        Returns:
+            class: The corresponding class.
+        """
+        scope, real_key = self.split_scope_key(key)
+        if scope is None or scope == self._scope:
+            # get from self
+            if real_key in self._module_dict:
+                return self._module_dict[real_key]
+        else:
+            # get from self._children
+            if scope in self._children:
+                return self._children[scope].get(real_key)
+            else:
+                # goto root
+                parent = self.parent
+                while parent.parent is not None:
+                    parent = parent.parent
+                return parent.get(key)
+
+    def build(self, *args, **kwargs):
+        return self.build_func(*args, **kwargs, registry=self)
+
+    def _add_children(self, registry):
+        """Add children for a registry.
+
+        The ``registry`` will be added as children based on its scope.
+        The parent registry could build objects from children registry.
+
+        Example:
+            >>> models = Registry('models')
+            >>> mmdet_models = Registry('models', parent=models)
+            >>> @mmdet_models.register_module()
+            >>> class ResNet:
+            >>>     pass
+            >>> resnet = models.build(dict(type='mmdet.ResNet'))
+        """
+
+        assert isinstance(registry, Registry)
+        assert registry.scope is not None
+        assert registry.scope not in self.children, \
+            f'scope {registry.scope} exists in {self.name} registry'
+        self.children[registry.scope] = registry
+
+    def _register_module(self, module_class, module_name=None, force=False):
+        if not inspect.isclass(module_class):
+            raise TypeError('module must be a class, '
+                            f'but got {type(module_class)}')
+
+        if module_name is None:
+            module_name = module_class.__name__
+        if isinstance(module_name, str):
+            module_name = [module_name]
+        for name in module_name:
+            if not force and name in self._module_dict:
+                raise KeyError(f'{name} is already registered '
+                               f'in {self.name}')
+            self._module_dict[name] = module_class
+
+    def deprecated_register_module(self, cls=None, force=False):
+        warnings.warn(
+            'The old API of register_module(module, force=False) '
+            'is deprecated and will be removed, please use the new API '
+            'register_module(name=None, force=False, module=None) instead.')
+        if cls is None:
+            return partial(self.deprecated_register_module, force=force)
+        self._register_module(cls, force=force)
+        return cls
+
+    def register_module(self, name=None, force=False, module=None):
+        """Register a module.
+
+        A record will be added to `self._module_dict`, whose key is the class
+        name or the specified name, and value is the class itself.
+        It can be used as a decorator or a normal function.
+
+        Example:
+            >>> backbones = Registry('backbone')
+            >>> @backbones.register_module()
+            >>> class ResNet:
+            >>>     pass
+
+            >>> backbones = Registry('backbone')
+            >>> @backbones.register_module(name='mnet')
+            >>> class MobileNet:
+            >>>     pass
+
+            >>> backbones = Registry('backbone')
+            >>> class ResNet:
+            >>>     pass
+            >>> backbones.register_module(ResNet)
+
+        Args:
+            name (str | None): The module name to be registered. If not
+                specified, the class name will be used.
+            force (bool, optional): Whether to override an existing class with
+                the same name. Default: False.
+            module (type): Module class to be registered.
+        """
+        if not isinstance(force, bool):
+            raise TypeError(f'force must be a boolean, but got {type(force)}')
+        # NOTE: This is a walkaround to be compatible with the old api,
+        # while it may introduce unexpected bugs.
+        if isinstance(name, type):
+            return self.deprecated_register_module(name, force=force)
+
+        # raise the error ahead of time
+        if not (name is None or isinstance(name, str) or is_seq_of(name, str)):
+            raise TypeError(
+                'name must be either of None, an instance of str or a sequence'
+                f'  of str, but got {type(name)}')
+
+        # use it as a normal method: x.register_module(module=SomeClass)
+        if module is not None:
+            self._register_module(
+                module_class=module, module_name=name, force=force)
+            return module
+
+        # use it as a decorator: @x.register_module()
+        def _register(cls):
+            self._register_module(
+                module_class=cls, module_name=name, force=force)
+            return cls
+
+        return _register

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/testing.py

@@ -0,0 +1,140 @@
+# Copyright (c) Open-MMLab.
+import sys
+from collections.abc import Iterable
+from runpy import run_path
+from shlex import split
+from typing import Any, Dict, List
+from unittest.mock import patch
+
+
+def check_python_script(cmd):
+    """Run the python cmd script with `__main__`. The difference between
+    `os.system` is that, this function exectues code in the current process, so
+    that it can be tracked by coverage tools. Currently it supports two forms:
+
+    - ./tests/data/scripts/hello.py zz
+    - python tests/data/scripts/hello.py zz
+    """
+    args = split(cmd)
+    if args[0] == 'python':
+        args = args[1:]
+    with patch.object(sys, 'argv', args):
+        run_path(args[0], run_name='__main__')
+
+
+def _any(judge_result):
+    """Since built-in ``any`` works only when the element of iterable is not
+    iterable, implement the function."""
+    if not isinstance(judge_result, Iterable):
+        return judge_result
+
+    try:
+        for element in judge_result:
+            if _any(element):
+                return True
+    except TypeError:
+        # Maybe encounter the case: torch.tensor(True) | torch.tensor(False)
+        if judge_result:
+            return True
+    return False
+
+
+def assert_dict_contains_subset(dict_obj: Dict[Any, Any],
+                                expected_subset: Dict[Any, Any]) -> bool:
+    """Check if the dict_obj contains the expected_subset.
+
+    Args:
+        dict_obj (Dict[Any, Any]): Dict object to be checked.
+        expected_subset (Dict[Any, Any]): Subset expected to be contained in
+            dict_obj.
+
+    Returns:
+        bool: Whether the dict_obj contains the expected_subset.
+    """
+
+    for key, value in expected_subset.items():
+        if key not in dict_obj.keys() or _any(dict_obj[key] != value):
+            return False
+    return True
+
+
+def assert_attrs_equal(obj: Any, expected_attrs: Dict[str, Any]) -> bool:
+    """Check if attribute of class object is correct.
+
+    Args:
+        obj (object): Class object to be checked.
+        expected_attrs (Dict[str, Any]): Dict of the expected attrs.
+
+    Returns:
+        bool: Whether the attribute of class object is correct.
+    """
+    for attr, value in expected_attrs.items():
+        if not hasattr(obj, attr) or _any(getattr(obj, attr) != value):
+            return False
+    return True
+
+
+def assert_dict_has_keys(obj: Dict[str, Any],
+                         expected_keys: List[str]) -> bool:
+    """Check if the obj has all the expected_keys.
+
+    Args:
+        obj (Dict[str, Any]): Object to be checked.
+        expected_keys (List[str]): Keys expected to contained in the keys of
+            the obj.
+
+    Returns:
+        bool: Whether the obj has the expected keys.
+    """
+    return set(expected_keys).issubset(set(obj.keys()))
+
+
+def assert_keys_equal(result_keys: List[str], target_keys: List[str]) -> bool:
+    """Check if target_keys is equal to result_keys.
+
+    Args:
+        result_keys (List[str]): Result keys to be checked.
+        target_keys (List[str]): Target keys to be checked.
+
+    Returns:
+        bool: Whether target_keys is equal to result_keys.
+    """
+    return set(result_keys) == set(target_keys)
+
+
+def assert_is_norm_layer(module) -> bool:
+    """Check if the module is a norm layer.
+
+    Args:
+        module (nn.Module): The module to be checked.
+
+    Returns:
+        bool: Whether the module is a norm layer.
+    """
+    from .parrots_wrapper import _BatchNorm, _InstanceNorm
+    from torch.nn import GroupNorm, LayerNorm
+    norm_layer_candidates = (_BatchNorm, _InstanceNorm, GroupNorm, LayerNorm)
+    return isinstance(module, norm_layer_candidates)
+
+
+def assert_params_all_zeros(module) -> bool:
+    """Check if the parameters of the module is all zeros.
+
+    Args:
+        module (nn.Module): The module to be checked.
+
+    Returns:
+        bool: Whether the parameters of the module is all zeros.
+    """
+    weight_data = module.weight.data
+    is_weight_zero = weight_data.allclose(
+        weight_data.new_zeros(weight_data.size()))
+
+    if hasattr(module, 'bias') and module.bias is not None:
+        bias_data = module.bias.data
+        is_bias_zero = bias_data.allclose(
+            bias_data.new_zeros(bias_data.size()))
+    else:
+        is_bias_zero = True
+
+    return is_weight_zero and is_bias_zero

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/timer.py

@@ -0,0 +1,118 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from time import time
+
+
+class TimerError(Exception):
+
+    def __init__(self, message):
+        self.message = message
+        super(TimerError, self).__init__(message)
+
+
+class Timer:
+    """A flexible Timer class.
+
+    :Example:
+
+    >>> import time
+    >>> import annotator.mmpkg.mmcv as mmcv
+    >>> with mmcv.Timer():
+    >>>     # simulate a code block that will run for 1s
+    >>>     time.sleep(1)
+    1.000
+    >>> with mmcv.Timer(print_tmpl='it takes {:.1f} seconds'):
+    >>>     # simulate a code block that will run for 1s
+    >>>     time.sleep(1)
+    it takes 1.0 seconds
+    >>> timer = mmcv.Timer()
+    >>> time.sleep(0.5)
+    >>> print(timer.since_start())
+    0.500
+    >>> time.sleep(0.5)
+    >>> print(timer.since_last_check())
+    0.500
+    >>> print(timer.since_start())
+    1.000
+    """
+
+    def __init__(self, start=True, print_tmpl=None):
+        self._is_running = False
+        self.print_tmpl = print_tmpl if print_tmpl else '{:.3f}'
+        if start:
+            self.start()
+
+    @property
+    def is_running(self):
+        """bool: indicate whether the timer is running"""
+        return self._is_running
+
+    def __enter__(self):
+        self.start()
+        return self
+
+    def __exit__(self, type, value, traceback):
+        print(self.print_tmpl.format(self.since_last_check()))
+        self._is_running = False
+
+    def start(self):
+        """Start the timer."""
+        if not self._is_running:
+            self._t_start = time()
+            self._is_running = True
+        self._t_last = time()
+
+    def since_start(self):
+        """Total time since the timer is started.
+
+        Returns (float): Time in seconds.
+        """
+        if not self._is_running:
+            raise TimerError('timer is not running')
+        self._t_last = time()
+        return self._t_last - self._t_start
+
+    def since_last_check(self):
+        """Time since the last checking.
+
+        Either :func:`since_start` or :func:`since_last_check` is a checking
+        operation.
+
+        Returns (float): Time in seconds.
+        """
+        if not self._is_running:
+            raise TimerError('timer is not running')
+        dur = time() - self._t_last
+        self._t_last = time()
+        return dur
+
+
+_g_timers = {}  # global timers
+
+
+def check_time(timer_id):
+    """Add check points in a single line.
+
+    This method is suitable for running a task on a list of items. A timer will
+    be registered when the method is called for the first time.
+
+    :Example:
+
+    >>> import time
+    >>> import annotator.mmpkg.mmcv as mmcv
+    >>> for i in range(1, 6):
+    >>>     # simulate a code block
+    >>>     time.sleep(i)
+    >>>     mmcv.check_time('task1')
+    2.000
+    3.000
+    4.000
+    5.000
+
+    Args:
+        timer_id (str): Timer identifier.
+    """
+    if timer_id not in _g_timers:
+        _g_timers[timer_id] = Timer()
+        return 0
+    else:
+        return _g_timers[timer_id].since_last_check()

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/trace.py

@@ -0,0 +1,23 @@
+import warnings
+
+import torch
+
+from annotator.mmpkg.mmcv.utils import digit_version
+
+
+def is_jit_tracing() -> bool:
+    if (torch.__version__ != 'parrots'
+            and digit_version(torch.__version__) >= digit_version('1.6.0')):
+        on_trace = torch.jit.is_tracing()
+        # In PyTorch 1.6, torch.jit.is_tracing has a bug.
+        # Refers to https://github.com/pytorch/pytorch/issues/42448
+        if isinstance(on_trace, bool):
+            return on_trace
+        else:
+            return torch._C._is_tracing()
+    else:
+        warnings.warn(
+            'torch.jit.is_tracing is only supported after v1.6.0. '
+            'Therefore is_tracing returns False automatically. Please '
+            'set on_trace manually if you are using trace.', UserWarning)
+        return False

microsoftexcel-controlnet/annotator/mmpkg/mmcv/utils/version_utils.py

@@ -0,0 +1,90 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import os
+import subprocess
+import warnings
+
+from packaging.version import parse
+
+
+def digit_version(version_str: str, length: int = 4):
+    """Convert a version string into a tuple of integers.
+
+    This method is usually used for comparing two versions. For pre-release
+    versions: alpha < beta < rc.
+
+    Args:
+        version_str (str): The version string.
+        length (int): The maximum number of version levels. Default: 4.
+
+    Returns:
+        tuple[int]: The version info in digits (integers).
+    """
+    assert 'parrots' not in version_str
+    version = parse(version_str)
+    assert version.release, f'failed to parse version {version_str}'
+    release = list(version.release)
+    release = release[:length]
+    if len(release) < length:
+        release = release + [0] * (length - len(release))
+    if version.is_prerelease:
+        mapping = {'a': -3, 'b': -2, 'rc': -1}
+        val = -4
+        # version.pre can be None
+        if version.pre:
+            if version.pre[0] not in mapping:
+                warnings.warn(f'unknown prerelease version {version.pre[0]}, '
+                              'version checking may go wrong')
+            else:
+                val = mapping[version.pre[0]]
+            release.extend([val, version.pre[-1]])
+        else:
+            release.extend([val, 0])
+
+    elif version.is_postrelease:
+        release.extend([1, version.post])
+    else:
+        release.extend([0, 0])
+    return tuple(release)
+
+
+def _minimal_ext_cmd(cmd):
+    # construct minimal environment
+    env = {}
+    for k in ['SYSTEMROOT', 'PATH', 'HOME']:
+        v = os.environ.get(k)
+        if v is not None:
+            env[k] = v
+    # LANGUAGE is used on win32
+    env['LANGUAGE'] = 'C'
+    env['LANG'] = 'C'
+    env['LC_ALL'] = 'C'
+    out = subprocess.Popen(
+        cmd, stdout=subprocess.PIPE, env=env).communicate()[0]
+    return out
+
+
+def get_git_hash(fallback='unknown', digits=None):
+    """Get the git hash of the current repo.
+
+    Args:
+        fallback (str, optional): The fallback string when git hash is
+            unavailable. Defaults to 'unknown'.
+        digits (int, optional): kept digits of the hash. Defaults to None,
+            meaning all digits are kept.
+
+    Returns:
+        str: Git commit hash.
+    """
+
+    if digits is not None and not isinstance(digits, int):
+        raise TypeError('digits must be None or an integer')
+
+    try:
+        out = _minimal_ext_cmd(['git', 'rev-parse', 'HEAD'])
+        sha = out.strip().decode('ascii')
+        if digits is not None:
+            sha = sha[:digits]
+    except OSError:
+        sha = fallback
+
+    return sha

microsoftexcel-controlnet/annotator/mmpkg/mmcv/version.py

@@ -0,0 +1,35 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+__version__ = '1.3.17'
+
+
+def parse_version_info(version_str: str, length: int = 4) -> tuple:
+    """Parse a version string into a tuple.
+
+    Args:
+        version_str (str): The version string.
+        length (int): The maximum number of version levels. Default: 4.
+
+    Returns:
+        tuple[int | str]: The version info, e.g., "1.3.0" is parsed into
+            (1, 3, 0, 0, 0, 0), and "2.0.0rc1" is parsed into
+            (2, 0, 0, 0, 'rc', 1) (when length is set to 4).
+    """
+    from packaging.version import parse
+    version = parse(version_str)
+    assert version.release, f'failed to parse version {version_str}'
+    release = list(version.release)
+    release = release[:length]
+    if len(release) < length:
+        release = release + [0] * (length - len(release))
+    if version.is_prerelease:
+        release.extend(list(version.pre))
+    elif version.is_postrelease:
+        release.extend(list(version.post))
+    else:
+        release.extend([0, 0])
+    return tuple(release)
+
+
+version_info = tuple(int(x) for x in __version__.split('.')[:3])
+
+__all__ = ['__version__', 'version_info', 'parse_version_info']

microsoftexcel-controlnet/annotator/mmpkg/mmcv/video/__init__.py

@@ -0,0 +1,11 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from .io import Cache, VideoReader, frames2video
+from .optflow import (dequantize_flow, flow_from_bytes, flow_warp, flowread,
+                      flowwrite, quantize_flow, sparse_flow_from_bytes)
+from .processing import concat_video, convert_video, cut_video, resize_video
+
+__all__ = [
+    'Cache', 'VideoReader', 'frames2video', 'convert_video', 'resize_video',
+    'cut_video', 'concat_video', 'flowread', 'flowwrite', 'quantize_flow',
+    'dequantize_flow', 'flow_warp', 'flow_from_bytes', 'sparse_flow_from_bytes'
+]

microsoftexcel-controlnet/annotator/mmpkg/mmcv/video/io.py

@@ -0,0 +1,318 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import os.path as osp
+from collections import OrderedDict
+
+import cv2
+from cv2 import (CAP_PROP_FOURCC, CAP_PROP_FPS, CAP_PROP_FRAME_COUNT,
+                 CAP_PROP_FRAME_HEIGHT, CAP_PROP_FRAME_WIDTH,
+                 CAP_PROP_POS_FRAMES, VideoWriter_fourcc)
+
+from annotator.mmpkg.mmcv.utils import (check_file_exist, mkdir_or_exist, scandir,
+                        track_progress)
+
+
+class Cache:
+
+    def __init__(self, capacity):
+        self._cache = OrderedDict()
+        self._capacity = int(capacity)
+        if capacity <= 0:
+            raise ValueError('capacity must be a positive integer')
+
+    @property
+    def capacity(self):
+        return self._capacity
+
+    @property
+    def size(self):
+        return len(self._cache)
+
+    def put(self, key, val):
+        if key in self._cache:
+            return
+        if len(self._cache) >= self.capacity:
+            self._cache.popitem(last=False)
+        self._cache[key] = val
+
+    def get(self, key, default=None):
+        val = self._cache[key] if key in self._cache else default
+        return val
+
+
+class VideoReader:
+    """Video class with similar usage to a list object.
+
+    This video warpper class provides convenient apis to access frames.
+    There exists an issue of OpenCV's VideoCapture class that jumping to a
+    certain frame may be inaccurate. It is fixed in this class by checking
+    the position after jumping each time.
+    Cache is used when decoding videos. So if the same frame is visited for
+    the second time, there is no need to decode again if it is stored in the
+    cache.
+
+    :Example:
+
+    >>> import annotator.mmpkg.mmcv as mmcv
+    >>> v = mmcv.VideoReader('sample.mp4')
+    >>> len(v)  # get the total frame number with `len()`
+    120
+    >>> for img in v:  # v is iterable
+    >>>     mmcv.imshow(img)
+    >>> v[5]  # get the 6th frame
+    """
+
+    def __init__(self, filename, cache_capacity=10):
+        # Check whether the video path is a url
+        if not filename.startswith(('https://', 'http://')):
+            check_file_exist(filename, 'Video file not found: ' + filename)
+        self._vcap = cv2.VideoCapture(filename)
+        assert cache_capacity > 0
+        self._cache = Cache(cache_capacity)
+        self._position = 0
+        # get basic info
+        self._width = int(self._vcap.get(CAP_PROP_FRAME_WIDTH))
+        self._height = int(self._vcap.get(CAP_PROP_FRAME_HEIGHT))
+        self._fps = self._vcap.get(CAP_PROP_FPS)
+        self._frame_cnt = int(self._vcap.get(CAP_PROP_FRAME_COUNT))
+        self._fourcc = self._vcap.get(CAP_PROP_FOURCC)
+
+    @property
+    def vcap(self):
+        """:obj:`cv2.VideoCapture`: The raw VideoCapture object."""
+        return self._vcap
+
+    @property
+    def opened(self):
+        """bool: Indicate whether the video is opened."""
+        return self._vcap.isOpened()
+
+    @property
+    def width(self):
+        """int: Width of video frames."""
+        return self._width
+
+    @property
+    def height(self):
+        """int: Height of video frames."""
+        return self._height
+
+    @property
+    def resolution(self):
+        """tuple: Video resolution (width, height)."""
+        return (self._width, self._height)
+
+    @property
+    def fps(self):
+        """float: FPS of the video."""
+        return self._fps
+
+    @property
+    def frame_cnt(self):
+        """int: Total frames of the video."""
+        return self._frame_cnt
+
+    @property
+    def fourcc(self):
+        """str: "Four character code" of the video."""
+        return self._fourcc
+
+    @property
+    def position(self):
+        """int: Current cursor position, indicating frame decoded."""
+        return self._position
+
+    def _get_real_position(self):
+        return int(round(self._vcap.get(CAP_PROP_POS_FRAMES)))
+
+    def _set_real_position(self, frame_id):
+        self._vcap.set(CAP_PROP_POS_FRAMES, frame_id)
+        pos = self._get_real_position()
+        for _ in range(frame_id - pos):
+            self._vcap.read()
+        self._position = frame_id
+
+    def read(self):
+        """Read the next frame.
+
+        If the next frame have been decoded before and in the cache, then
+        return it directly, otherwise decode, cache and return it.
+
+        Returns:
+            ndarray or None: Return the frame if successful, otherwise None.
+        """
+        # pos = self._position
+        if self._cache:
+            img = self._cache.get(self._position)
+            if img is not None:
+                ret = True
+            else:
+                if self._position != self._get_real_position():
+                    self._set_real_position(self._position)
+                ret, img = self._vcap.read()
+                if ret:
+                    self._cache.put(self._position, img)
+        else:
+            ret, img = self._vcap.read()
+        if ret:
+            self._position += 1
+        return img
+
+    def get_frame(self, frame_id):
+        """Get frame by index.
+
+        Args:
+            frame_id (int): Index of the expected frame, 0-based.
+
+        Returns:
+            ndarray or None: Return the frame if successful, otherwise None.
+        """
+        if frame_id < 0 or frame_id >= self._frame_cnt:
+            raise IndexError(
+                f'"frame_id" must be between 0 and {self._frame_cnt - 1}')
+        if frame_id == self._position:
+            return self.read()
+        if self._cache:
+            img = self._cache.get(frame_id)
+            if img is not None:
+                self._position = frame_id + 1
+                return img
+        self._set_real_position(frame_id)
+        ret, img = self._vcap.read()
+        if ret:
+            if self._cache:
+                self._cache.put(self._position, img)
+            self._position += 1
+        return img
+
+    def current_frame(self):
+        """Get the current frame (frame that is just visited).
+
+        Returns:
+            ndarray or None: If the video is fresh, return None, otherwise
+                return the frame.
+        """
+        if self._position == 0:
+            return None
+        return self._cache.get(self._position - 1)
+
+    def cvt2frames(self,
+                   frame_dir,
+                   file_start=0,
+                   filename_tmpl='{:06d}.jpg',
+                   start=0,
+                   max_num=0,
+                   show_progress=True):
+        """Convert a video to frame images.
+
+        Args:
+            frame_dir (str): Output directory to store all the frame images.
+            file_start (int): Filenames will start from the specified number.
+            filename_tmpl (str): Filename template with the index as the
+                placeholder.
+            start (int): The starting frame index.
+            max_num (int): Maximum number of frames to be written.
+            show_progress (bool): Whether to show a progress bar.
+        """
+        mkdir_or_exist(frame_dir)
+        if max_num == 0:
+            task_num = self.frame_cnt - start
+        else:
+            task_num = min(self.frame_cnt - start, max_num)
+        if task_num <= 0:
+            raise ValueError('start must be less than total frame number')
+        if start > 0:
+            self._set_real_position(start)
+
+        def write_frame(file_idx):
+            img = self.read()
+            if img is None:
+                return
+            filename = osp.join(frame_dir, filename_tmpl.format(file_idx))
+            cv2.imwrite(filename, img)
+
+        if show_progress:
+            track_progress(write_frame, range(file_start,
+                                              file_start + task_num))
+        else:
+            for i in range(task_num):
+                write_frame(file_start + i)
+
+    def __len__(self):
+        return self.frame_cnt
+
+    def __getitem__(self, index):
+        if isinstance(index, slice):
+            return [
+                self.get_frame(i)
+                for i in range(*index.indices(self.frame_cnt))
+            ]
+        # support negative indexing
+        if index < 0:
+            index += self.frame_cnt
+            if index < 0:
+                raise IndexError('index out of range')
+        return self.get_frame(index)
+
+    def __iter__(self):
+        self._set_real_position(0)
+        return self
+
+    def __next__(self):
+        img = self.read()
+        if img is not None:
+            return img
+        else:
+            raise StopIteration
+
+    next = __next__
+
+    def __enter__(self):
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        self._vcap.release()
+
+
+def frames2video(frame_dir,
+                 video_file,
+                 fps=30,
+                 fourcc='XVID',
+                 filename_tmpl='{:06d}.jpg',
+                 start=0,
+                 end=0,
+                 show_progress=True):
+    """Read the frame images from a directory and join them as a video.
+
+    Args:
+        frame_dir (str): The directory containing video frames.
+        video_file (str): Output filename.
+        fps (float): FPS of the output video.
+        fourcc (str): Fourcc of the output video, this should be compatible
+            with the output file type.
+        filename_tmpl (str): Filename template with the index as the variable.
+        start (int): Starting frame index.
+        end (int): Ending frame index.
+        show_progress (bool): Whether to show a progress bar.
+    """
+    if end == 0:
+        ext = filename_tmpl.split('.')[-1]
+        end = len([name for name in scandir(frame_dir, ext)])
+    first_file = osp.join(frame_dir, filename_tmpl.format(start))
+    check_file_exist(first_file, 'The start frame not found: ' + first_file)
+    img = cv2.imread(first_file)
+    height, width = img.shape[:2]
+    resolution = (width, height)
+    vwriter = cv2.VideoWriter(video_file, VideoWriter_fourcc(*fourcc), fps,
+                              resolution)
+
+    def write_frame(file_idx):
+        filename = osp.join(frame_dir, filename_tmpl.format(file_idx))
+        img = cv2.imread(filename)
+        vwriter.write(img)
+
+    if show_progress:
+        track_progress(write_frame, range(start, end))
+    else:
+        for i in range(start, end):
+            write_frame(i)
+    vwriter.release()

microsoftexcel-controlnet/annotator/mmpkg/mmcv/video/optflow.py

@@ -0,0 +1,254 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import warnings
+
+import cv2
+import numpy as np
+
+from annotator.mmpkg.mmcv.arraymisc import dequantize, quantize
+from annotator.mmpkg.mmcv.image import imread, imwrite
+from annotator.mmpkg.mmcv.utils import is_str
+
+
+def flowread(flow_or_path, quantize=False, concat_axis=0, *args, **kwargs):
+    """Read an optical flow map.
+
+    Args:
+        flow_or_path (ndarray or str): A flow map or filepath.
+        quantize (bool): whether to read quantized pair, if set to True,
+            remaining args will be passed to :func:`dequantize_flow`.
+        concat_axis (int): The axis that dx and dy are concatenated,
+            can be either 0 or 1. Ignored if quantize is False.
+
+    Returns:
+        ndarray: Optical flow represented as a (h, w, 2) numpy array
+    """
+    if isinstance(flow_or_path, np.ndarray):
+        if (flow_or_path.ndim != 3) or (flow_or_path.shape[-1] != 2):
+            raise ValueError(f'Invalid flow with shape {flow_or_path.shape}')
+        return flow_or_path
+    elif not is_str(flow_or_path):
+        raise TypeError(f'"flow_or_path" must be a filename or numpy array, '
+                        f'not {type(flow_or_path)}')
+
+    if not quantize:
+        with open(flow_or_path, 'rb') as f:
+            try:
+                header = f.read(4).decode('utf-8')
+            except Exception:
+                raise IOError(f'Invalid flow file: {flow_or_path}')
+            else:
+                if header != 'PIEH':
+                    raise IOError(f'Invalid flow file: {flow_or_path}, '
+                                  'header does not contain PIEH')
+
+            w = np.fromfile(f, np.int32, 1).squeeze()
+            h = np.fromfile(f, np.int32, 1).squeeze()
+            flow = np.fromfile(f, np.float32, w * h * 2).reshape((h, w, 2))
+    else:
+        assert concat_axis in [0, 1]
+        cat_flow = imread(flow_or_path, flag='unchanged')
+        if cat_flow.ndim != 2:
+            raise IOError(
+                f'{flow_or_path} is not a valid quantized flow file, '
+                f'its dimension is {cat_flow.ndim}.')
+        assert cat_flow.shape[concat_axis] % 2 == 0
+        dx, dy = np.split(cat_flow, 2, axis=concat_axis)
+        flow = dequantize_flow(dx, dy, *args, **kwargs)
+
+    return flow.astype(np.float32)
+
+
+def flowwrite(flow, filename, quantize=False, concat_axis=0, *args, **kwargs):
+    """Write optical flow to file.
+
+    If the flow is not quantized, it will be saved as a .flo file losslessly,
+    otherwise a jpeg image which is lossy but of much smaller size. (dx and dy
+    will be concatenated horizontally into a single image if quantize is True.)
+
+    Args:
+        flow (ndarray): (h, w, 2) array of optical flow.
+        filename (str): Output filepath.
+        quantize (bool): Whether to quantize the flow and save it to 2 jpeg
+            images. If set to True, remaining args will be passed to
+            :func:`quantize_flow`.
+        concat_axis (int): The axis that dx and dy are concatenated,
+            can be either 0 or 1. Ignored if quantize is False.
+    """
+    if not quantize:
+        with open(filename, 'wb') as f:
+            f.write('PIEH'.encode('utf-8'))
+            np.array([flow.shape[1], flow.shape[0]], dtype=np.int32).tofile(f)
+            flow = flow.astype(np.float32)
+            flow.tofile(f)
+            f.flush()
+    else:
+        assert concat_axis in [0, 1]
+        dx, dy = quantize_flow(flow, *args, **kwargs)
+        dxdy = np.concatenate((dx, dy), axis=concat_axis)
+        imwrite(dxdy, filename)
+
+
+def quantize_flow(flow, max_val=0.02, norm=True):
+    """Quantize flow to [0, 255].
+
+    After this step, the size of flow will be much smaller, and can be
+    dumped as jpeg images.
+
+    Args:
+        flow (ndarray): (h, w, 2) array of optical flow.
+        max_val (float): Maximum value of flow, values beyond
+                        [-max_val, max_val] will be truncated.
+        norm (bool): Whether to divide flow values by image width/height.
+
+    Returns:
+        tuple[ndarray]: Quantized dx and dy.
+    """
+    h, w, _ = flow.shape
+    dx = flow[..., 0]
+    dy = flow[..., 1]
+    if norm:
+        dx = dx / w  # avoid inplace operations
+        dy = dy / h
+    # use 255 levels instead of 256 to make sure 0 is 0 after dequantization.
+    flow_comps = [
+        quantize(d, -max_val, max_val, 255, np.uint8) for d in [dx, dy]
+    ]
+    return tuple(flow_comps)
+
+
+def dequantize_flow(dx, dy, max_val=0.02, denorm=True):
+    """Recover from quantized flow.
+
+    Args:
+        dx (ndarray): Quantized dx.
+        dy (ndarray): Quantized dy.
+        max_val (float): Maximum value used when quantizing.
+        denorm (bool): Whether to multiply flow values with width/height.
+
+    Returns:
+        ndarray: Dequantized flow.
+    """
+    assert dx.shape == dy.shape
+    assert dx.ndim == 2 or (dx.ndim == 3 and dx.shape[-1] == 1)
+
+    dx, dy = [dequantize(d, -max_val, max_val, 255) for d in [dx, dy]]
+
+    if denorm:
+        dx *= dx.shape[1]
+        dy *= dx.shape[0]
+    flow = np.dstack((dx, dy))
+    return flow
+
+
+def flow_warp(img, flow, filling_value=0, interpolate_mode='nearest'):
+    """Use flow to warp img.
+
+    Args:
+        img (ndarray, float or uint8): Image to be warped.
+        flow (ndarray, float): Optical Flow.
+        filling_value (int): The missing pixels will be set with filling_value.
+        interpolate_mode (str): bilinear -> Bilinear Interpolation;
+                                nearest -> Nearest Neighbor.
+
+    Returns:
+        ndarray: Warped image with the same shape of img
+    """
+    warnings.warn('This function is just for prototyping and cannot '
+                  'guarantee the computational efficiency.')
+    assert flow.ndim == 3, 'Flow must be in 3D arrays.'
+    height = flow.shape[0]
+    width = flow.shape[1]
+    channels = img.shape[2]
+
+    output = np.ones(
+        (height, width, channels), dtype=img.dtype) * filling_value
+
+    grid = np.indices((height, width)).swapaxes(0, 1).swapaxes(1, 2)
+    dx = grid[:, :, 0] + flow[:, :, 1]
+    dy = grid[:, :, 1] + flow[:, :, 0]
+    sx = np.floor(dx).astype(int)
+    sy = np.floor(dy).astype(int)
+    valid = (sx >= 0) & (sx < height - 1) & (sy >= 0) & (sy < width - 1)
+
+    if interpolate_mode == 'nearest':
+        output[valid, :] = img[dx[valid].round().astype(int),
+                               dy[valid].round().astype(int), :]
+    elif interpolate_mode == 'bilinear':
+        # dirty walkround for integer positions
+        eps_ = 1e-6
+        dx, dy = dx + eps_, dy + eps_
+        left_top_ = img[np.floor(dx[valid]).astype(int),
+                        np.floor(dy[valid]).astype(int), :] * (
+                            np.ceil(dx[valid]) - dx[valid])[:, None] * (
+                                np.ceil(dy[valid]) - dy[valid])[:, None]
+        left_down_ = img[np.ceil(dx[valid]).astype(int),
+                         np.floor(dy[valid]).astype(int), :] * (
+                             dx[valid] - np.floor(dx[valid]))[:, None] * (
+                                 np.ceil(dy[valid]) - dy[valid])[:, None]
+        right_top_ = img[np.floor(dx[valid]).astype(int),
+                         np.ceil(dy[valid]).astype(int), :] * (
+                             np.ceil(dx[valid]) - dx[valid])[:, None] * (
+                                 dy[valid] - np.floor(dy[valid]))[:, None]
+        right_down_ = img[np.ceil(dx[valid]).astype(int),
+                          np.ceil(dy[valid]).astype(int), :] * (
+                              dx[valid] - np.floor(dx[valid]))[:, None] * (
+                                  dy[valid] - np.floor(dy[valid]))[:, None]
+        output[valid, :] = left_top_ + left_down_ + right_top_ + right_down_
+    else:
+        raise NotImplementedError(
+            'We only support interpolation modes of nearest and bilinear, '
+            f'but got {interpolate_mode}.')
+    return output.astype(img.dtype)
+
+
+def flow_from_bytes(content):
+    """Read dense optical flow from bytes.
+
+    .. note::
+        This load optical flow function works for FlyingChairs, FlyingThings3D,
+        Sintel, FlyingChairsOcc datasets, but cannot load the data from
+        ChairsSDHom.
+
+    Args:
+        content (bytes): Optical flow bytes got from files or other streams.
+
+    Returns:
+        ndarray: Loaded optical flow with the shape (H, W, 2).
+    """
+
+    # header in first 4 bytes
+    header = content[:4]
+    if header.decode('utf-8') != 'PIEH':
+        raise Exception('Flow file header does not contain PIEH')
+    # width in second 4 bytes
+    width = np.frombuffer(content[4:], np.int32, 1).squeeze()
+    # height in third 4 bytes
+    height = np.frombuffer(content[8:], np.int32, 1).squeeze()
+    # after first 12 bytes, all bytes are flow
+    flow = np.frombuffer(content[12:], np.float32, width * height * 2).reshape(
+        (height, width, 2))
+
+    return flow
+
+
+def sparse_flow_from_bytes(content):
+    """Read the optical flow in KITTI datasets from bytes.
+
+    This function is modified from RAFT load the `KITTI datasets
+    <https://github.com/princeton-vl/RAFT/blob/224320502d66c356d88e6c712f38129e60661e80/core/utils/frame_utils.py#L102>`_.
+
+    Args:
+        content (bytes): Optical flow bytes got from files or other streams.
+
+    Returns:
+        Tuple(ndarray, ndarray): Loaded optical flow with the shape (H, W, 2)
+            and flow valid mask with the shape (H, W).
+    """  # nopa
+
+    content = np.frombuffer(content, np.uint8)
+    flow = cv2.imdecode(content, cv2.IMREAD_ANYDEPTH | cv2.IMREAD_COLOR)
+    flow = flow[:, :, ::-1].astype(np.float32)
+    # flow shape (H, W, 2) valid shape (H, W)
+    flow, valid = flow[:, :, :2], flow[:, :, 2]
+    flow = (flow - 2**15) / 64.0
+    return flow, valid

microsoftexcel-controlnet/annotator/mmpkg/mmcv/video/processing.py

@@ -0,0 +1,160 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import os
+import os.path as osp
+import subprocess
+import tempfile
+
+from annotator.mmpkg.mmcv.utils import requires_executable
+
+
+@requires_executable('ffmpeg')
+def convert_video(in_file,
+                  out_file,
+                  print_cmd=False,
+                  pre_options='',
+                  **kwargs):
+    """Convert a video with ffmpeg.
+
+    This provides a general api to ffmpeg, the executed command is::
+
+        `ffmpeg -y <pre_options> -i <in_file> <options> <out_file>`
+
+    Options(kwargs) are mapped to ffmpeg commands with the following rules:
+
+    - key=val: "-key val"
+    - key=True: "-key"
+    - key=False: ""
+
+    Args:
+        in_file (str): Input video filename.
+        out_file (str): Output video filename.
+        pre_options (str): Options appears before "-i <in_file>".
+        print_cmd (bool): Whether to print the final ffmpeg command.
+    """
+    options = []
+    for k, v in kwargs.items():
+        if isinstance(v, bool):
+            if v:
+                options.append(f'-{k}')
+        elif k == 'log_level':
+            assert v in [
+                'quiet', 'panic', 'fatal', 'error', 'warning', 'info',
+                'verbose', 'debug', 'trace'
+            ]
+            options.append(f'-loglevel {v}')
+        else:
+            options.append(f'-{k} {v}')
+    cmd = f'ffmpeg -y {pre_options} -i {in_file} {" ".join(options)} ' \
+          f'{out_file}'
+    if print_cmd:
+        print(cmd)
+    subprocess.call(cmd, shell=True)
+
+
+@requires_executable('ffmpeg')
+def resize_video(in_file,
+                 out_file,
+                 size=None,
+                 ratio=None,
+                 keep_ar=False,
+                 log_level='info',
+                 print_cmd=False):
+    """Resize a video.
+
+    Args:
+        in_file (str): Input video filename.
+        out_file (str): Output video filename.
+        size (tuple): Expected size (w, h), eg, (320, 240) or (320, -1).
+        ratio (tuple or float): Expected resize ratio, (2, 0.5) means
+            (w*2, h*0.5).
+        keep_ar (bool): Whether to keep original aspect ratio.
+        log_level (str): Logging level of ffmpeg.
+        print_cmd (bool): Whether to print the final ffmpeg command.
+    """
+    if size is None and ratio is None:
+        raise ValueError('expected size or ratio must be specified')
+    if size is not None and ratio is not None:
+        raise ValueError('size and ratio cannot be specified at the same time')
+    options = {'log_level': log_level}
+    if size:
+        if not keep_ar:
+            options['vf'] = f'scale={size[0]}:{size[1]}'
+        else:
+            options['vf'] = f'scale=w={size[0]}:h={size[1]}:' \
+                            'force_original_aspect_ratio=decrease'
+    else:
+        if not isinstance(ratio, tuple):
+            ratio = (ratio, ratio)
+        options['vf'] = f'scale="trunc(iw*{ratio[0]}):trunc(ih*{ratio[1]})"'
+    convert_video(in_file, out_file, print_cmd, **options)
+
+
+@requires_executable('ffmpeg')
+def cut_video(in_file,
+              out_file,
+              start=None,
+              end=None,
+              vcodec=None,
+              acodec=None,
+              log_level='info',
+              print_cmd=False):
+    """Cut a clip from a video.
+
+    Args:
+        in_file (str): Input video filename.
+        out_file (str): Output video filename.
+        start (None or float): Start time (in seconds).
+        end (None or float): End time (in seconds).
+        vcodec (None or str): Output video codec, None for unchanged.
+        acodec (None or str): Output audio codec, None for unchanged.
+        log_level (str): Logging level of ffmpeg.
+        print_cmd (bool): Whether to print the final ffmpeg command.
+    """
+    options = {'log_level': log_level}
+    if vcodec is None:
+        options['vcodec'] = 'copy'
+    if acodec is None:
+        options['acodec'] = 'copy'
+    if start:
+        options['ss'] = start
+    else:
+        start = 0
+    if end:
+        options['t'] = end - start
+    convert_video(in_file, out_file, print_cmd, **options)
+
+
+@requires_executable('ffmpeg')
+def concat_video(video_list,
+                 out_file,
+                 vcodec=None,
+                 acodec=None,
+                 log_level='info',
+                 print_cmd=False):
+    """Concatenate multiple videos into a single one.
+
+    Args:
+        video_list (list): A list of video filenames
+        out_file (str): Output video filename
+        vcodec (None or str): Output video codec, None for unchanged
+        acodec (None or str): Output audio codec, None for unchanged
+        log_level (str): Logging level of ffmpeg.
+        print_cmd (bool): Whether to print the final ffmpeg command.
+    """
+    tmp_filehandler, tmp_filename = tempfile.mkstemp(suffix='.txt', text=True)
+    with open(tmp_filename, 'w') as f:
+        for filename in video_list:
+            f.write(f'file {osp.abspath(filename)}\n')
+    options = {'log_level': log_level}
+    if vcodec is None:
+        options['vcodec'] = 'copy'
+    if acodec is None:
+        options['acodec'] = 'copy'
+    convert_video(
+        tmp_filename,
+        out_file,
+        print_cmd,
+        pre_options='-f concat -safe 0',
+        **options)
+    os.close(tmp_filehandler)
+    os.remove(tmp_filename)

microsoftexcel-controlnet/annotator/mmpkg/mmcv/visualization/__init__.py

@@ -0,0 +1,9 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from .color import Color, color_val
+from .image import imshow, imshow_bboxes, imshow_det_bboxes
+from .optflow import flow2rgb, flowshow, make_color_wheel
+
+__all__ = [
+    'Color', 'color_val', 'imshow', 'imshow_bboxes', 'imshow_det_bboxes',
+    'flowshow', 'flow2rgb', 'make_color_wheel'
+]

microsoftexcel-controlnet/annotator/mmpkg/mmcv/visualization/color.py

@@ -0,0 +1,51 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from enum import Enum
+
+import numpy as np
+
+from annotator.mmpkg.mmcv.utils import is_str
+
+
+class Color(Enum):
+    """An enum that defines common colors.
+
+    Contains red, green, blue, cyan, yellow, magenta, white and black.
+    """
+    red = (0, 0, 255)
+    green = (0, 255, 0)
+    blue = (255, 0, 0)
+    cyan = (255, 255, 0)
+    yellow = (0, 255, 255)
+    magenta = (255, 0, 255)
+    white = (255, 255, 255)
+    black = (0, 0, 0)
+
+
+def color_val(color):
+    """Convert various input to color tuples.
+
+    Args:
+        color (:obj:`Color`/str/tuple/int/ndarray): Color inputs
+
+    Returns:
+        tuple[int]: A tuple of 3 integers indicating BGR channels.
+    """
+    if is_str(color):
+        return Color[color].value
+    elif isinstance(color, Color):
+        return color.value
+    elif isinstance(color, tuple):
+        assert len(color) == 3
+        for channel in color:
+            assert 0 <= channel <= 255
+        return color
+    elif isinstance(color, int):
+        assert 0 <= color <= 255
+        return color, color, color
+    elif isinstance(color, np.ndarray):
+        assert color.ndim == 1 and color.size == 3
+        assert np.all((color >= 0) & (color <= 255))
+        color = color.astype(np.uint8)
+        return tuple(color)
+    else:
+        raise TypeError(f'Invalid type for color: {type(color)}')

microsoftexcel-controlnet/annotator/mmpkg/mmcv/visualization/image.py

@@ -0,0 +1,152 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import cv2
+import numpy as np
+
+from annotator.mmpkg.mmcv.image import imread, imwrite
+from .color import color_val
+
+
+def imshow(img, win_name='', wait_time=0):
+    """Show an image.
+
+    Args:
+        img (str or ndarray): The image to be displayed.
+        win_name (str): The window name.
+        wait_time (int): Value of waitKey param.
+    """
+    cv2.imshow(win_name, imread(img))
+    if wait_time == 0:  # prevent from hanging if windows was closed
+        while True:
+            ret = cv2.waitKey(1)
+
+            closed = cv2.getWindowProperty(win_name, cv2.WND_PROP_VISIBLE) < 1
+            # if user closed window or if some key pressed
+            if closed or ret != -1:
+                break
+    else:
+        ret = cv2.waitKey(wait_time)
+
+
+def imshow_bboxes(img,
+                  bboxes,
+                  colors='green',
+                  top_k=-1,
+                  thickness=1,
+                  show=True,
+                  win_name='',
+                  wait_time=0,
+                  out_file=None):
+    """Draw bboxes on an image.
+
+    Args:
+        img (str or ndarray): The image to be displayed.
+        bboxes (list or ndarray): A list of ndarray of shape (k, 4).
+        colors (list[str or tuple or Color]): A list of colors.
+        top_k (int): Plot the first k bboxes only if set positive.
+        thickness (int): Thickness of lines.
+        show (bool): Whether to show the image.
+        win_name (str): The window name.
+        wait_time (int): Value of waitKey param.
+        out_file (str, optional): The filename to write the image.
+
+    Returns:
+        ndarray: The image with bboxes drawn on it.
+    """
+    img = imread(img)
+    img = np.ascontiguousarray(img)
+
+    if isinstance(bboxes, np.ndarray):
+        bboxes = [bboxes]
+    if not isinstance(colors, list):
+        colors = [colors for _ in range(len(bboxes))]
+    colors = [color_val(c) for c in colors]
+    assert len(bboxes) == len(colors)
+
+    for i, _bboxes in enumerate(bboxes):
+        _bboxes = _bboxes.astype(np.int32)
+        if top_k <= 0:
+            _top_k = _bboxes.shape[0]
+        else:
+            _top_k = min(top_k, _bboxes.shape[0])
+        for j in range(_top_k):
+            left_top = (_bboxes[j, 0], _bboxes[j, 1])
+            right_bottom = (_bboxes[j, 2], _bboxes[j, 3])
+            cv2.rectangle(
+                img, left_top, right_bottom, colors[i], thickness=thickness)
+
+    if show:
+        imshow(img, win_name, wait_time)
+    if out_file is not None:
+        imwrite(img, out_file)
+    return img
+
+
+def imshow_det_bboxes(img,
+                      bboxes,
+                      labels,
+                      class_names=None,
+                      score_thr=0,
+                      bbox_color='green',
+                      text_color='green',
+                      thickness=1,
+                      font_scale=0.5,
+                      show=True,
+                      win_name='',
+                      wait_time=0,
+                      out_file=None):
+    """Draw bboxes and class labels (with scores) on an image.
+
+    Args:
+        img (str or ndarray): The image to be displayed.
+        bboxes (ndarray): Bounding boxes (with scores), shaped (n, 4) or
+            (n, 5).
+        labels (ndarray): Labels of bboxes.
+        class_names (list[str]): Names of each classes.
+        score_thr (float): Minimum score of bboxes to be shown.
+        bbox_color (str or tuple or :obj:`Color`): Color of bbox lines.
+        text_color (str or tuple or :obj:`Color`): Color of texts.
+        thickness (int): Thickness of lines.
+        font_scale (float): Font scales of texts.
+        show (bool): Whether to show the image.
+        win_name (str): The window name.
+        wait_time (int): Value of waitKey param.
+        out_file (str or None): The filename to write the image.
+
+    Returns:
+        ndarray: The image with bboxes drawn on it.
+    """
+    assert bboxes.ndim == 2
+    assert labels.ndim == 1
+    assert bboxes.shape[0] == labels.shape[0]
+    assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5
+    img = imread(img)
+    img = np.ascontiguousarray(img)
+
+    if score_thr > 0:
+        assert bboxes.shape[1] == 5
+        scores = bboxes[:, -1]
+        inds = scores > score_thr
+        bboxes = bboxes[inds, :]
+        labels = labels[inds]
+
+    bbox_color = color_val(bbox_color)
+    text_color = color_val(text_color)
+
+    for bbox, label in zip(bboxes, labels):
+        bbox_int = bbox.astype(np.int32)
+        left_top = (bbox_int[0], bbox_int[1])
+        right_bottom = (bbox_int[2], bbox_int[3])
+        cv2.rectangle(
+            img, left_top, right_bottom, bbox_color, thickness=thickness)
+        label_text = class_names[
+            label] if class_names is not None else f'cls {label}'
+        if len(bbox) > 4:
+            label_text += f'|{bbox[-1]:.02f}'
+        cv2.putText(img, label_text, (bbox_int[0], bbox_int[1] - 2),
+                    cv2.FONT_HERSHEY_COMPLEX, font_scale, text_color)
+
+    if show:
+        imshow(img, win_name, wait_time)
+    if out_file is not None:
+        imwrite(img, out_file)
+    return img

microsoftexcel-controlnet/annotator/mmpkg/mmcv/visualization/optflow.py

@@ -0,0 +1,112 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from __future__ import division
+
+import numpy as np
+
+from annotator.mmpkg.mmcv.image import rgb2bgr
+from annotator.mmpkg.mmcv.video import flowread
+from .image import imshow
+
+
+def flowshow(flow, win_name='', wait_time=0):
+    """Show optical flow.
+
+    Args:
+        flow (ndarray or str): The optical flow to be displayed.
+        win_name (str): The window name.
+        wait_time (int): Value of waitKey param.
+    """
+    flow = flowread(flow)
+    flow_img = flow2rgb(flow)
+    imshow(rgb2bgr(flow_img), win_name, wait_time)
+
+
+def flow2rgb(flow, color_wheel=None, unknown_thr=1e6):
+    """Convert flow map to RGB image.
+
+    Args:
+        flow (ndarray): Array of optical flow.
+        color_wheel (ndarray or None): Color wheel used to map flow field to
+            RGB colorspace. Default color wheel will be used if not specified.
+        unknown_thr (str): Values above this threshold will be marked as
+            unknown and thus ignored.
+
+    Returns:
+        ndarray: RGB image that can be visualized.
+    """
+    assert flow.ndim == 3 and flow.shape[-1] == 2
+    if color_wheel is None:
+        color_wheel = make_color_wheel()
+    assert color_wheel.ndim == 2 and color_wheel.shape[1] == 3
+    num_bins = color_wheel.shape[0]
+
+    dx = flow[:, :, 0].copy()
+    dy = flow[:, :, 1].copy()
+
+    ignore_inds = (
+        np.isnan(dx) | np.isnan(dy) | (np.abs(dx) > unknown_thr) |
+        (np.abs(dy) > unknown_thr))
+    dx[ignore_inds] = 0
+    dy[ignore_inds] = 0
+
+    rad = np.sqrt(dx**2 + dy**2)
+    if np.any(rad > np.finfo(float).eps):
+        max_rad = np.max(rad)
+        dx /= max_rad
+        dy /= max_rad
+
+    rad = np.sqrt(dx**2 + dy**2)
+    angle = np.arctan2(-dy, -dx) / np.pi
+
+    bin_real = (angle + 1) / 2 * (num_bins - 1)
+    bin_left = np.floor(bin_real).astype(int)
+    bin_right = (bin_left + 1) % num_bins
+    w = (bin_real - bin_left.astype(np.float32))[..., None]
+    flow_img = (1 -
+                w) * color_wheel[bin_left, :] + w * color_wheel[bin_right, :]
+    small_ind = rad <= 1
+    flow_img[small_ind] = 1 - rad[small_ind, None] * (1 - flow_img[small_ind])
+    flow_img[np.logical_not(small_ind)] *= 0.75
+
+    flow_img[ignore_inds, :] = 0
+
+    return flow_img
+
+
+def make_color_wheel(bins=None):
+    """Build a color wheel.
+
+    Args:
+        bins(list or tuple, optional): Specify the number of bins for each
+            color range, corresponding to six ranges: red -> yellow,
+            yellow -> green, green -> cyan, cyan -> blue, blue -> magenta,
+            magenta -> red. [15, 6, 4, 11, 13, 6] is used for default
+            (see Middlebury).
+
+    Returns:
+        ndarray: Color wheel of shape (total_bins, 3).
+    """
+    if bins is None:
+        bins = [15, 6, 4, 11, 13, 6]
+    assert len(bins) == 6
+
+    RY, YG, GC, CB, BM, MR = tuple(bins)
+
+    ry = [1, np.arange(RY) / RY, 0]
+    yg = [1 - np.arange(YG) / YG, 1, 0]
+    gc = [0, 1, np.arange(GC) / GC]
+    cb = [0, 1 - np.arange(CB) / CB, 1]
+    bm = [np.arange(BM) / BM, 0, 1]
+    mr = [1, 0, 1 - np.arange(MR) / MR]
+
+    num_bins = RY + YG + GC + CB + BM + MR
+
+    color_wheel = np.zeros((3, num_bins), dtype=np.float32)
+
+    col = 0
+    for i, color in enumerate([ry, yg, gc, cb, bm, mr]):
+        for j in range(3):
+            color_wheel[j, col:col + bins[i]] = color[j]
+        col += bins[i]
+
+    return color_wheel.T

microsoftexcel-controlnet/annotator/mmpkg/mmseg/apis/__init__.py

@@ -0,0 +1,9 @@
+from .inference import inference_segmentor, init_segmentor, show_result_pyplot
+from .test import multi_gpu_test, single_gpu_test
+from .train import get_root_logger, set_random_seed, train_segmentor
+
+__all__ = [
+    'get_root_logger', 'set_random_seed', 'train_segmentor', 'init_segmentor',
+    'inference_segmentor', 'multi_gpu_test', 'single_gpu_test',
+    'show_result_pyplot'
+]

microsoftexcel-controlnet/annotator/mmpkg/mmseg/apis/inference.py

@@ -0,0 +1,138 @@
+import matplotlib.pyplot as plt
+import annotator.mmpkg.mmcv as mmcv
+import torch
+from annotator.mmpkg.mmcv.parallel import collate, scatter
+from annotator.mmpkg.mmcv.runner import load_checkpoint
+
+from annotator.mmpkg.mmseg.datasets.pipelines import Compose
+from annotator.mmpkg.mmseg.models import build_segmentor
+from modules import devices
+
+
+def init_segmentor(config, checkpoint=None, device=devices.get_device_for("controlnet")):
+    """Initialize a segmentor from config file.
+
+    Args:
+        config (str or :obj:`mmcv.Config`): Config file path or the config
+            object.
+        checkpoint (str, optional): Checkpoint path. If left as None, the model
+            will not load any weights.
+        device (str, optional) CPU/CUDA device option. Default 'cuda:0'.
+            Use 'cpu' for loading model on CPU.
+    Returns:
+        nn.Module: The constructed segmentor.
+    """
+    if isinstance(config, str):
+        config = mmcv.Config.fromfile(config)
+    elif not isinstance(config, mmcv.Config):
+        raise TypeError('config must be a filename or Config object, '
+                        'but got {}'.format(type(config)))
+    config.model.pretrained = None
+    config.model.train_cfg = None
+    model = build_segmentor(config.model, test_cfg=config.get('test_cfg'))
+    if checkpoint is not None:
+        checkpoint = load_checkpoint(model, checkpoint, map_location='cpu')
+        model.CLASSES = checkpoint['meta']['CLASSES']
+        model.PALETTE = checkpoint['meta']['PALETTE']
+    model.cfg = config  # save the config in the model for convenience
+    model.to(device)
+    model.eval()
+    return model
+
+
+class LoadImage:
+    """A simple pipeline to load image."""
+
+    def __call__(self, results):
+        """Call function to load images into results.
+
+        Args:
+            results (dict): A result dict contains the file name
+                of the image to be read.
+
+        Returns:
+            dict: ``results`` will be returned containing loaded image.
+        """
+
+        if isinstance(results['img'], str):
+            results['filename'] = results['img']
+            results['ori_filename'] = results['img']
+        else:
+            results['filename'] = None
+            results['ori_filename'] = None
+        img = mmcv.imread(results['img'])
+        results['img'] = img
+        results['img_shape'] = img.shape
+        results['ori_shape'] = img.shape
+        return results
+
+
+def inference_segmentor(model, img):
+    """Inference image(s) with the segmentor.
+
+    Args:
+        model (nn.Module): The loaded segmentor.
+        imgs (str/ndarray or list[str/ndarray]): Either image files or loaded
+            images.
+
+    Returns:
+        (list[Tensor]): The segmentation result.
+    """
+    cfg = model.cfg
+    device = next(model.parameters()).device  # model device
+    # build the data pipeline
+    test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
+    test_pipeline = Compose(test_pipeline)
+    # prepare data
+    data = dict(img=img)
+    data = test_pipeline(data)
+    data = collate([data], samples_per_gpu=1)
+    if next(model.parameters()).is_cuda:
+        # scatter to specified GPU
+        data = scatter(data, [device])[0]
+    else:
+        data['img'][0] = data['img'][0].to(devices.get_device_for("controlnet"))
+        data['img_metas'] = [i.data[0] for i in data['img_metas']]
+
+    # forward the model
+    with torch.no_grad():
+        result = model(return_loss=False, rescale=True, **data)
+    return result
+
+
+def show_result_pyplot(model,
+                       img,
+                       result,
+                       palette=None,
+                       fig_size=(15, 10),
+                       opacity=0.5,
+                       title='',
+                       block=True):
+    """Visualize the segmentation results on the image.
+
+    Args:
+        model (nn.Module): The loaded segmentor.
+        img (str or np.ndarray): Image filename or loaded image.
+        result (list): The segmentation result.
+        palette (list[list[int]]] | None): The palette of segmentation
+            map. If None is given, random palette will be generated.
+            Default: None
+        fig_size (tuple): Figure size of the pyplot figure.
+        opacity(float): Opacity of painted segmentation map.
+            Default 0.5.
+            Must be in (0, 1] range.
+        title (str): The title of pyplot figure.
+            Default is ''.
+        block (bool): Whether to block the pyplot figure.
+            Default is True.
+    """
+    if hasattr(model, 'module'):
+        model = model.module
+    img = model.show_result(
+        img, result, palette=palette, show=False, opacity=opacity)
+    # plt.figure(figsize=fig_size)
+    # plt.imshow(mmcv.bgr2rgb(img))
+    # plt.title(title)
+    # plt.tight_layout()
+    # plt.show(block=block)
+    return mmcv.bgr2rgb(img)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/apis/test.py

@@ -0,0 +1,238 @@
+import os.path as osp
+import pickle
+import shutil
+import tempfile
+
+import annotator.mmpkg.mmcv as mmcv
+import numpy as np
+import torch
+import torch.distributed as dist
+from annotator.mmpkg.mmcv.image import tensor2imgs
+from annotator.mmpkg.mmcv.runner import get_dist_info
+
+
+def np2tmp(array, temp_file_name=None):
+    """Save ndarray to local numpy file.
+
+    Args:
+        array (ndarray): Ndarray to save.
+        temp_file_name (str): Numpy file name. If 'temp_file_name=None', this
+            function will generate a file name with tempfile.NamedTemporaryFile
+            to save ndarray. Default: None.
+
+    Returns:
+        str: The numpy file name.
+    """
+
+    if temp_file_name is None:
+        temp_file_name = tempfile.NamedTemporaryFile(
+            suffix='.npy', delete=False).name
+    np.save(temp_file_name, array)
+    return temp_file_name
+
+
+def single_gpu_test(model,
+                    data_loader,
+                    show=False,
+                    out_dir=None,
+                    efficient_test=False,
+                    opacity=0.5):
+    """Test with single GPU.
+
+    Args:
+        model (nn.Module): Model to be tested.
+        data_loader (utils.data.Dataloader): Pytorch data loader.
+        show (bool): Whether show results during inference. Default: False.
+        out_dir (str, optional): If specified, the results will be dumped into
+            the directory to save output results.
+        efficient_test (bool): Whether save the results as local numpy files to
+            save CPU memory during evaluation. Default: False.
+        opacity(float): Opacity of painted segmentation map.
+            Default 0.5.
+            Must be in (0, 1] range.
+    Returns:
+        list: The prediction results.
+    """
+
+    model.eval()
+    results = []
+    dataset = data_loader.dataset
+    prog_bar = mmcv.ProgressBar(len(dataset))
+    for i, data in enumerate(data_loader):
+        with torch.no_grad():
+            result = model(return_loss=False, **data)
+
+        if show or out_dir:
+            img_tensor = data['img'][0]
+            img_metas = data['img_metas'][0].data[0]
+            imgs = tensor2imgs(img_tensor, **img_metas[0]['img_norm_cfg'])
+            assert len(imgs) == len(img_metas)
+
+            for img, img_meta in zip(imgs, img_metas):
+                h, w, _ = img_meta['img_shape']
+                img_show = img[:h, :w, :]
+
+                ori_h, ori_w = img_meta['ori_shape'][:-1]
+                img_show = mmcv.imresize(img_show, (ori_w, ori_h))
+
+                if out_dir:
+                    out_file = osp.join(out_dir, img_meta['ori_filename'])
+                else:
+                    out_file = None
+
+                model.module.show_result(
+                    img_show,
+                    result,
+                    palette=dataset.PALETTE,
+                    show=show,
+                    out_file=out_file,
+                    opacity=opacity)
+
+        if isinstance(result, list):
+            if efficient_test:
+                result = [np2tmp(_) for _ in result]
+            results.extend(result)
+        else:
+            if efficient_test:
+                result = np2tmp(result)
+            results.append(result)
+
+        batch_size = len(result)
+        for _ in range(batch_size):
+            prog_bar.update()
+    return results
+
+
+def multi_gpu_test(model,
+                   data_loader,
+                   tmpdir=None,
+                   gpu_collect=False,
+                   efficient_test=False):
+    """Test model with multiple gpus.
+
+    This method tests model with multiple gpus and collects the results
+    under two different modes: gpu and cpu modes. By setting 'gpu_collect=True'
+    it encodes results to gpu tensors and use gpu communication for results
+    collection. On cpu mode it saves the results on different gpus to 'tmpdir'
+    and collects them by the rank 0 worker.
+
+    Args:
+        model (nn.Module): Model to be tested.
+        data_loader (utils.data.Dataloader): Pytorch data loader.
+        tmpdir (str): Path of directory to save the temporary results from
+            different gpus under cpu mode.
+        gpu_collect (bool): Option to use either gpu or cpu to collect results.
+        efficient_test (bool): Whether save the results as local numpy files to
+            save CPU memory during evaluation. Default: False.
+
+    Returns:
+        list: The prediction results.
+    """
+
+    model.eval()
+    results = []
+    dataset = data_loader.dataset
+    rank, world_size = get_dist_info()
+    if rank == 0:
+        prog_bar = mmcv.ProgressBar(len(dataset))
+    for i, data in enumerate(data_loader):
+        with torch.no_grad():
+            result = model(return_loss=False, rescale=True, **data)
+
+        if isinstance(result, list):
+            if efficient_test:
+                result = [np2tmp(_) for _ in result]
+            results.extend(result)
+        else:
+            if efficient_test:
+                result = np2tmp(result)
+            results.append(result)
+
+        if rank == 0:
+            batch_size = data['img'][0].size(0)
+            for _ in range(batch_size * world_size):
+                prog_bar.update()
+
+    # collect results from all ranks
+    if gpu_collect:
+        results = collect_results_gpu(results, len(dataset))
+    else:
+        results = collect_results_cpu(results, len(dataset), tmpdir)
+    return results
+
+
+def collect_results_cpu(result_part, size, tmpdir=None):
+    """Collect results with CPU."""
+    rank, world_size = get_dist_info()
+    # create a tmp dir if it is not specified
+    if tmpdir is None:
+        MAX_LEN = 512
+        # 32 is whitespace
+        dir_tensor = torch.full((MAX_LEN, ),
+                                32,
+                                dtype=torch.uint8,
+                                device='cuda')
+        if rank == 0:
+            tmpdir = tempfile.mkdtemp()
+            tmpdir = torch.tensor(
+                bytearray(tmpdir.encode()), dtype=torch.uint8, device='cuda')
+            dir_tensor[:len(tmpdir)] = tmpdir
+        dist.broadcast(dir_tensor, 0)
+        tmpdir = dir_tensor.cpu().numpy().tobytes().decode().rstrip()
+    else:
+        mmcv.mkdir_or_exist(tmpdir)
+    # dump the part result to the dir
+    mmcv.dump(result_part, osp.join(tmpdir, 'part_{}.pkl'.format(rank)))
+    dist.barrier()
+    # collect all parts
+    if rank != 0:
+        return None
+    else:
+        # load results of all parts from tmp dir
+        part_list = []
+        for i in range(world_size):
+            part_file = osp.join(tmpdir, 'part_{}.pkl'.format(i))
+            part_list.append(mmcv.load(part_file))
+        # sort the results
+        ordered_results = []
+        for res in zip(*part_list):
+            ordered_results.extend(list(res))
+        # the dataloader may pad some samples
+        ordered_results = ordered_results[:size]
+        # remove tmp dir
+        shutil.rmtree(tmpdir)
+        return ordered_results
+
+
+def collect_results_gpu(result_part, size):
+    """Collect results with GPU."""
+    rank, world_size = get_dist_info()
+    # dump result part to tensor with pickle
+    part_tensor = torch.tensor(
+        bytearray(pickle.dumps(result_part)), dtype=torch.uint8, device='cuda')
+    # gather all result part tensor shape
+    shape_tensor = torch.tensor(part_tensor.shape, device='cuda')
+    shape_list = [shape_tensor.clone() for _ in range(world_size)]
+    dist.all_gather(shape_list, shape_tensor)
+    # padding result part tensor to max length
+    shape_max = torch.tensor(shape_list).max()
+    part_send = torch.zeros(shape_max, dtype=torch.uint8, device='cuda')
+    part_send[:shape_tensor[0]] = part_tensor
+    part_recv_list = [
+        part_tensor.new_zeros(shape_max) for _ in range(world_size)
+    ]
+    # gather all result part
+    dist.all_gather(part_recv_list, part_send)
+
+    if rank == 0:
+        part_list = []
+        for recv, shape in zip(part_recv_list, shape_list):
+            part_list.append(
+                pickle.loads(recv[:shape[0]].cpu().numpy().tobytes()))
+        # sort the results
+        ordered_results = []
+        for res in zip(*part_list):
+            ordered_results.extend(list(res))
+        # the dataloader may pad some samples
+        ordered_results = ordered_results[:size]
+        return ordered_results

microsoftexcel-controlnet/annotator/mmpkg/mmseg/apis/train.py

@@ -0,0 +1,116 @@
+import random
+import warnings
+
+import numpy as np
+import torch
+from annotator.mmpkg.mmcv.parallel import MMDataParallel, MMDistributedDataParallel
+from annotator.mmpkg.mmcv.runner import build_optimizer, build_runner
+
+from annotator.mmpkg.mmseg.core import DistEvalHook, EvalHook
+from annotator.mmpkg.mmseg.datasets import build_dataloader, build_dataset
+from annotator.mmpkg.mmseg.utils import get_root_logger
+
+
+def set_random_seed(seed, deterministic=False):
+    """Set random seed.
+
+    Args:
+        seed (int): Seed to be used.
+        deterministic (bool): Whether to set the deterministic option for
+            CUDNN backend, i.e., set `torch.backends.cudnn.deterministic`
+            to True and `torch.backends.cudnn.benchmark` to False.
+            Default: False.
+    """
+    random.seed(seed)
+    np.random.seed(seed)
+    torch.manual_seed(seed)
+    torch.cuda.manual_seed_all(seed)
+    if deterministic:
+        torch.backends.cudnn.deterministic = True
+        torch.backends.cudnn.benchmark = False
+
+
+def train_segmentor(model,
+                    dataset,
+                    cfg,
+                    distributed=False,
+                    validate=False,
+                    timestamp=None,
+                    meta=None):
+    """Launch segmentor training."""
+    logger = get_root_logger(cfg.log_level)
+
+    # prepare data loaders
+    dataset = dataset if isinstance(dataset, (list, tuple)) else [dataset]
+    data_loaders = [
+        build_dataloader(
+            ds,
+            cfg.data.samples_per_gpu,
+            cfg.data.workers_per_gpu,
+            # cfg.gpus will be ignored if distributed
+            len(cfg.gpu_ids),
+            dist=distributed,
+            seed=cfg.seed,
+            drop_last=True) for ds in dataset
+    ]
+
+    # put model on gpus
+    if distributed:
+        find_unused_parameters = cfg.get('find_unused_parameters', False)
+        # Sets the `find_unused_parameters` parameter in
+        # torch.nn.parallel.DistributedDataParallel
+        model = MMDistributedDataParallel(
+            model.cuda(),
+            device_ids=[torch.cuda.current_device()],
+            broadcast_buffers=False,
+            find_unused_parameters=find_unused_parameters)
+    else:
+        model = MMDataParallel(
+            model.cuda(cfg.gpu_ids[0]), device_ids=cfg.gpu_ids)
+
+    # build runner
+    optimizer = build_optimizer(model, cfg.optimizer)
+
+    if cfg.get('runner') is None:
+        cfg.runner = {'type': 'IterBasedRunner', 'max_iters': cfg.total_iters}
+        warnings.warn(
+            'config is now expected to have a `runner` section, '
+            'please set `runner` in your config.', UserWarning)
+
+    runner = build_runner(
+        cfg.runner,
+        default_args=dict(
+            model=model,
+            batch_processor=None,
+            optimizer=optimizer,
+            work_dir=cfg.work_dir,
+            logger=logger,
+            meta=meta))
+
+    # register hooks
+    runner.register_training_hooks(cfg.lr_config, cfg.optimizer_config,
+                                   cfg.checkpoint_config, cfg.log_config,
+                                   cfg.get('momentum_config', None))
+
+    # an ugly walkaround to make the .log and .log.json filenames the same
+    runner.timestamp = timestamp
+
+    # register eval hooks
+    if validate:
+        val_dataset = build_dataset(cfg.data.val, dict(test_mode=True))
+        val_dataloader = build_dataloader(
+            val_dataset,
+            samples_per_gpu=1,
+            workers_per_gpu=cfg.data.workers_per_gpu,
+            dist=distributed,
+            shuffle=False)
+        eval_cfg = cfg.get('evaluation', {})
+        eval_cfg['by_epoch'] = cfg.runner['type'] != 'IterBasedRunner'
+        eval_hook = DistEvalHook if distributed else EvalHook
+        runner.register_hook(eval_hook(val_dataloader, **eval_cfg), priority='LOW')
+
+    if cfg.resume_from:
+        runner.resume(cfg.resume_from)
+    elif cfg.load_from:
+        runner.load_checkpoint(cfg.load_from)
+    runner.run(data_loaders, cfg.workflow)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/__init__.py

@@ -0,0 +1,3 @@
+from .evaluation import *  # noqa: F401, F403
+from .seg import *  # noqa: F401, F403
+from .utils import *  # noqa: F401, F403

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/evaluation/__init__.py

@@ -0,0 +1,8 @@
+from .class_names import get_classes, get_palette
+from .eval_hooks import DistEvalHook, EvalHook
+from .metrics import eval_metrics, mean_dice, mean_fscore, mean_iou
+
+__all__ = [
+    'EvalHook', 'DistEvalHook', 'mean_dice', 'mean_iou', 'mean_fscore',
+    'eval_metrics', 'get_classes', 'get_palette'
+]

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/evaluation/class_names.py

@@ -0,0 +1,152 @@
+import annotator.mmpkg.mmcv as mmcv
+
+
+def cityscapes_classes():
+    """Cityscapes class names for external use."""
+    return [
+        'road', 'sidewalk', 'building', 'wall', 'fence', 'pole',
+        'traffic light', 'traffic sign', 'vegetation', 'terrain', 'sky',
+        'person', 'rider', 'car', 'truck', 'bus', 'train', 'motorcycle',
+        'bicycle'
+    ]
+
+
+def ade_classes():
+    """ADE20K class names for external use."""
+    return [
+        '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'
+    ]
+
+
+def voc_classes():
+    """Pascal VOC class names for external use."""
+    return [
+        'background', 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus',
+        'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse',
+        'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train',
+        'tvmonitor'
+    ]
+
+
+def cityscapes_palette():
+    """Cityscapes palette for external use."""
+    return [[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 ade_palette():
+    """ADE20K palette for external use."""
+    return [[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 voc_palette():
+    """Pascal VOC palette for external use."""
+    return [[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0], [0, 0, 128],
+            [128, 0, 128], [0, 128, 128], [128, 128, 128], [64, 0, 0],
+            [192, 0, 0], [64, 128, 0], [192, 128, 0], [64, 0, 128],
+            [192, 0, 128], [64, 128, 128], [192, 128, 128], [0, 64, 0],
+            [128, 64, 0], [0, 192, 0], [128, 192, 0], [0, 64, 128]]
+
+
+dataset_aliases = {
+    'cityscapes': ['cityscapes'],
+    'ade': ['ade', 'ade20k'],
+    'voc': ['voc', 'pascal_voc', 'voc12', 'voc12aug']
+}
+
+
+def get_classes(dataset):
+    """Get class names of a dataset."""
+    alias2name = {}
+    for name, aliases in dataset_aliases.items():
+        for alias in aliases:
+            alias2name[alias] = name
+
+    if mmcv.is_str(dataset):
+        if dataset in alias2name:
+            labels = eval(alias2name[dataset] + '_classes()')
+        else:
+            raise ValueError(f'Unrecognized dataset: {dataset}')
+    else:
+        raise TypeError(f'dataset must a str, but got {type(dataset)}')
+    return labels
+
+
+def get_palette(dataset):
+    """Get class palette (RGB) of a dataset."""
+    alias2name = {}
+    for name, aliases in dataset_aliases.items():
+        for alias in aliases:
+            alias2name[alias] = name
+
+    if mmcv.is_str(dataset):
+        if dataset in alias2name:
+            labels = eval(alias2name[dataset] + '_palette()')
+        else:
+            raise ValueError(f'Unrecognized dataset: {dataset}')
+    else:
+        raise TypeError(f'dataset must a str, but got {type(dataset)}')
+    return labels

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/evaluation/eval_hooks.py

@@ -0,0 +1,109 @@
+import os.path as osp
+
+from annotator.mmpkg.mmcv.runner import DistEvalHook as _DistEvalHook
+from annotator.mmpkg.mmcv.runner import EvalHook as _EvalHook
+
+
+class EvalHook(_EvalHook):
+    """Single GPU EvalHook, with efficient test support.
+
+    Args:
+        by_epoch (bool): Determine perform evaluation by epoch or by iteration.
+            If set to True, it will perform by epoch. Otherwise, by iteration.
+            Default: False.
+        efficient_test (bool): Whether save the results as local numpy files to
+            save CPU memory during evaluation. Default: False.
+    Returns:
+        list: The prediction results.
+    """
+
+    greater_keys = ['mIoU', 'mAcc', 'aAcc']
+
+    def __init__(self, *args, by_epoch=False, efficient_test=False, **kwargs):
+        super().__init__(*args, by_epoch=by_epoch, **kwargs)
+        self.efficient_test = efficient_test
+
+    def after_train_iter(self, runner):
+        """After train epoch hook.
+
+        Override default ``single_gpu_test``.
+        """
+        if self.by_epoch or not self.every_n_iters(runner, self.interval):
+            return
+        from annotator.mmpkg.mmseg.apis import single_gpu_test
+        runner.log_buffer.clear()
+        results = single_gpu_test(
+            runner.model,
+            self.dataloader,
+            show=False,
+            efficient_test=self.efficient_test)
+        self.evaluate(runner, results)
+
+    def after_train_epoch(self, runner):
+        """After train epoch hook.
+
+        Override default ``single_gpu_test``.
+        """
+        if not self.by_epoch or not self.every_n_epochs(runner, self.interval):
+            return
+        from annotator.mmpkg.mmseg.apis import single_gpu_test
+        runner.log_buffer.clear()
+        results = single_gpu_test(runner.model, self.dataloader, show=False)
+        self.evaluate(runner, results)
+
+
+class DistEvalHook(_DistEvalHook):
+    """Distributed EvalHook, with efficient test support.
+
+    Args:
+        by_epoch (bool): Determine perform evaluation by epoch or by iteration.
+            If set to True, it will perform by epoch. Otherwise, by iteration.
+            Default: False.
+        efficient_test (bool): Whether save the results as local numpy files to
+            save CPU memory during evaluation. Default: False.
+    Returns:
+        list: The prediction results.
+    """
+
+    greater_keys = ['mIoU', 'mAcc', 'aAcc']
+
+    def __init__(self, *args, by_epoch=False, efficient_test=False, **kwargs):
+        super().__init__(*args, by_epoch=by_epoch, **kwargs)
+        self.efficient_test = efficient_test
+
+    def after_train_iter(self, runner):
+        """After train epoch hook.
+
+        Override default ``multi_gpu_test``.
+        """
+        if self.by_epoch or not self.every_n_iters(runner, self.interval):
+            return
+        from annotator.mmpkg.mmseg.apis import multi_gpu_test
+        runner.log_buffer.clear()
+        results = multi_gpu_test(
+            runner.model,
+            self.dataloader,
+            tmpdir=osp.join(runner.work_dir, '.eval_hook'),
+            gpu_collect=self.gpu_collect,
+            efficient_test=self.efficient_test)
+        if runner.rank == 0:
+            print('\n')
+            self.evaluate(runner, results)
+
+    def after_train_epoch(self, runner):
+        """After train epoch hook.
+
+        Override default ``multi_gpu_test``.
+        """
+        if not self.by_epoch or not self.every_n_epochs(runner, self.interval):
+            return
+        from annotator.mmpkg.mmseg.apis import multi_gpu_test
+        runner.log_buffer.clear()
+        results = multi_gpu_test(
+            runner.model,
+            self.dataloader,
+            tmpdir=osp.join(runner.work_dir, '.eval_hook'),
+            gpu_collect=self.gpu_collect)
+        if runner.rank == 0:
+            print('\n')
+            self.evaluate(runner, results)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/evaluation/metrics.py

@@ -0,0 +1,326 @@
+from collections import OrderedDict
+
+import annotator.mmpkg.mmcv as mmcv
+import numpy as np
+import torch
+
+
+def f_score(precision, recall, beta=1):
+    """calcuate the f-score value.
+
+    Args:
+        precision (float | torch.Tensor): The precision value.
+        recall (float | torch.Tensor): The recall value.
+        beta (int): Determines the weight of recall in the combined score.
+            Default: False.
+
+    Returns:
+        [torch.tensor]: The f-score value.
+    """
+    score = (1 + beta**2) * (precision * recall) / (
+        (beta**2 * precision) + recall)
+    return score
+
+
+def intersect_and_union(pred_label,
+                        label,
+                        num_classes,
+                        ignore_index,
+                        label_map=dict(),
+                        reduce_zero_label=False):
+    """Calculate intersection and Union.
+
+    Args:
+        pred_label (ndarray | str): Prediction segmentation map
+            or predict result filename.
+        label (ndarray | str): Ground truth segmentation map
+            or label filename.
+        num_classes (int): Number of categories.
+        ignore_index (int): Index that will be ignored in evaluation.
+        label_map (dict): Mapping old labels to new labels. The parameter will
+            work only when label is str. Default: dict().
+        reduce_zero_label (bool): Whether ignore zero label. The parameter will
+            work only when label is str. Default: False.
+
+     Returns:
+         torch.Tensor: The intersection of prediction and ground truth
+            histogram on all classes.
+         torch.Tensor: The union of prediction and ground truth histogram on
+            all classes.
+         torch.Tensor: The prediction histogram on all classes.
+         torch.Tensor: The ground truth histogram on all classes.
+    """
+
+    if isinstance(pred_label, str):
+        pred_label = torch.from_numpy(np.load(pred_label))
+    else:
+        pred_label = torch.from_numpy((pred_label))
+
+    if isinstance(label, str):
+        label = torch.from_numpy(
+            mmcv.imread(label, flag='unchanged', backend='pillow'))
+    else:
+        label = torch.from_numpy(label)
+
+    if label_map is not None:
+        for old_id, new_id in label_map.items():
+            label[label == old_id] = new_id
+    if reduce_zero_label:
+        label[label == 0] = 255
+        label = label - 1
+        label[label == 254] = 255
+
+    mask = (label != ignore_index)
+    pred_label = pred_label[mask]
+    label = label[mask]
+
+    intersect = pred_label[pred_label == label]
+    area_intersect = torch.histc(
+        intersect.float(), bins=(num_classes), min=0, max=num_classes - 1)
+    area_pred_label = torch.histc(
+        pred_label.float(), bins=(num_classes), min=0, max=num_classes - 1)
+    area_label = torch.histc(
+        label.float(), bins=(num_classes), min=0, max=num_classes - 1)
+    area_union = area_pred_label + area_label - area_intersect
+    return area_intersect, area_union, area_pred_label, area_label
+
+
+def total_intersect_and_union(results,
+                              gt_seg_maps,
+                              num_classes,
+                              ignore_index,
+                              label_map=dict(),
+                              reduce_zero_label=False):
+    """Calculate Total Intersection and Union.
+
+    Args:
+        results (list[ndarray] | list[str]): List of prediction segmentation
+            maps or list of prediction result filenames.
+        gt_seg_maps (list[ndarray] | list[str]): list of ground truth
+            segmentation maps or list of label filenames.
+        num_classes (int): Number of categories.
+        ignore_index (int): Index that will be ignored in evaluation.
+        label_map (dict): Mapping old labels to new labels. Default: dict().
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
+
+     Returns:
+         ndarray: The intersection of prediction and ground truth histogram
+             on all classes.
+         ndarray: The union of prediction and ground truth histogram on all
+             classes.
+         ndarray: The prediction histogram on all classes.
+         ndarray: The ground truth histogram on all classes.
+    """
+    num_imgs = len(results)
+    assert len(gt_seg_maps) == num_imgs
+    total_area_intersect = torch.zeros((num_classes, ), dtype=torch.float64)
+    total_area_union = torch.zeros((num_classes, ), dtype=torch.float64)
+    total_area_pred_label = torch.zeros((num_classes, ), dtype=torch.float64)
+    total_area_label = torch.zeros((num_classes, ), dtype=torch.float64)
+    for i in range(num_imgs):
+        area_intersect, area_union, area_pred_label, area_label = \
+            intersect_and_union(
+                results[i], gt_seg_maps[i], num_classes, ignore_index,
+                label_map, reduce_zero_label)
+        total_area_intersect += area_intersect
+        total_area_union += area_union
+        total_area_pred_label += area_pred_label
+        total_area_label += area_label
+    return total_area_intersect, total_area_union, total_area_pred_label, \
+        total_area_label
+
+
+def mean_iou(results,
+             gt_seg_maps,
+             num_classes,
+             ignore_index,
+             nan_to_num=None,
+             label_map=dict(),
+             reduce_zero_label=False):
+    """Calculate Mean Intersection and Union (mIoU)
+
+    Args:
+        results (list[ndarray] | list[str]): List of prediction segmentation
+            maps or list of prediction result filenames.
+        gt_seg_maps (list[ndarray] | list[str]): list of ground truth
+            segmentation maps or list of label filenames.
+        num_classes (int): Number of categories.
+        ignore_index (int): Index that will be ignored in evaluation.
+        nan_to_num (int, optional): If specified, NaN values will be replaced
+            by the numbers defined by the user. Default: None.
+        label_map (dict): Mapping old labels to new labels. Default: dict().
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
+
+     Returns:
+        dict[str, float | ndarray]:
+            <aAcc> float: Overall accuracy on all images.
+            <Acc> ndarray: Per category accuracy, shape (num_classes, ).
+            <IoU> ndarray: Per category IoU, shape (num_classes, ).
+    """
+    iou_result = eval_metrics(
+        results=results,
+        gt_seg_maps=gt_seg_maps,
+        num_classes=num_classes,
+        ignore_index=ignore_index,
+        metrics=['mIoU'],
+        nan_to_num=nan_to_num,
+        label_map=label_map,
+        reduce_zero_label=reduce_zero_label)
+    return iou_result
+
+
+def mean_dice(results,
+              gt_seg_maps,
+              num_classes,
+              ignore_index,
+              nan_to_num=None,
+              label_map=dict(),
+              reduce_zero_label=False):
+    """Calculate Mean Dice (mDice)
+
+    Args:
+        results (list[ndarray] | list[str]): List of prediction segmentation
+            maps or list of prediction result filenames.
+        gt_seg_maps (list[ndarray] | list[str]): list of ground truth
+            segmentation maps or list of label filenames.
+        num_classes (int): Number of categories.
+        ignore_index (int): Index that will be ignored in evaluation.
+        nan_to_num (int, optional): If specified, NaN values will be replaced
+            by the numbers defined by the user. Default: None.
+        label_map (dict): Mapping old labels to new labels. Default: dict().
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
+
+     Returns:
+        dict[str, float | ndarray]: Default metrics.
+            <aAcc> float: Overall accuracy on all images.
+            <Acc> ndarray: Per category accuracy, shape (num_classes, ).
+            <Dice> ndarray: Per category dice, shape (num_classes, ).
+    """
+
+    dice_result = eval_metrics(
+        results=results,
+        gt_seg_maps=gt_seg_maps,
+        num_classes=num_classes,
+        ignore_index=ignore_index,
+        metrics=['mDice'],
+        nan_to_num=nan_to_num,
+        label_map=label_map,
+        reduce_zero_label=reduce_zero_label)
+    return dice_result
+
+
+def mean_fscore(results,
+                gt_seg_maps,
+                num_classes,
+                ignore_index,
+                nan_to_num=None,
+                label_map=dict(),
+                reduce_zero_label=False,
+                beta=1):
+    """Calculate Mean Intersection and Union (mIoU)
+
+    Args:
+        results (list[ndarray] | list[str]): List of prediction segmentation
+            maps or list of prediction result filenames.
+        gt_seg_maps (list[ndarray] | list[str]): list of ground truth
+            segmentation maps or list of label filenames.
+        num_classes (int): Number of categories.
+        ignore_index (int): Index that will be ignored in evaluation.
+        nan_to_num (int, optional): If specified, NaN values will be replaced
+            by the numbers defined by the user. Default: None.
+        label_map (dict): Mapping old labels to new labels. Default: dict().
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
+        beta (int): Determines the weight of recall in the combined score.
+            Default: False.
+
+
+     Returns:
+        dict[str, float | ndarray]: Default metrics.
+            <aAcc> float: Overall accuracy on all images.
+            <Fscore> ndarray: Per category recall, shape (num_classes, ).
+            <Precision> ndarray: Per category precision, shape (num_classes, ).
+            <Recall> ndarray: Per category f-score, shape (num_classes, ).
+    """
+    fscore_result = eval_metrics(
+        results=results,
+        gt_seg_maps=gt_seg_maps,
+        num_classes=num_classes,
+        ignore_index=ignore_index,
+        metrics=['mFscore'],
+        nan_to_num=nan_to_num,
+        label_map=label_map,
+        reduce_zero_label=reduce_zero_label,
+        beta=beta)
+    return fscore_result
+
+
+def eval_metrics(results,
+                 gt_seg_maps,
+                 num_classes,
+                 ignore_index,
+                 metrics=['mIoU'],
+                 nan_to_num=None,
+                 label_map=dict(),
+                 reduce_zero_label=False,
+                 beta=1):
+    """Calculate evaluation metrics
+    Args:
+        results (list[ndarray] | list[str]): List of prediction segmentation
+            maps or list of prediction result filenames.
+        gt_seg_maps (list[ndarray] | list[str]): list of ground truth
+            segmentation maps or list of label filenames.
+        num_classes (int): Number of categories.
+        ignore_index (int): Index that will be ignored in evaluation.
+        metrics (list[str] | str): Metrics to be evaluated, 'mIoU' and 'mDice'.
+        nan_to_num (int, optional): If specified, NaN values will be replaced
+            by the numbers defined by the user. Default: None.
+        label_map (dict): Mapping old labels to new labels. Default: dict().
+        reduce_zero_label (bool): Whether ignore zero label. Default: False.
+     Returns:
+        float: Overall accuracy on all images.
+        ndarray: Per category accuracy, shape (num_classes, ).
+        ndarray: Per category evaluation metrics, shape (num_classes, ).
+    """
+    if isinstance(metrics, str):
+        metrics = [metrics]
+    allowed_metrics = ['mIoU', 'mDice', 'mFscore']
+    if not set(metrics).issubset(set(allowed_metrics)):
+        raise KeyError('metrics {} is not supported'.format(metrics))
+
+    total_area_intersect, total_area_union, total_area_pred_label, \
+        total_area_label = total_intersect_and_union(
+            results, gt_seg_maps, num_classes, ignore_index, label_map,
+            reduce_zero_label)
+    all_acc = total_area_intersect.sum() / total_area_label.sum()
+    ret_metrics = OrderedDict({'aAcc': all_acc})
+    for metric in metrics:
+        if metric == 'mIoU':
+            iou = total_area_intersect / total_area_union
+            acc = total_area_intersect / total_area_label
+            ret_metrics['IoU'] = iou
+            ret_metrics['Acc'] = acc
+        elif metric == 'mDice':
+            dice = 2 * total_area_intersect / (
+                total_area_pred_label + total_area_label)
+            acc = total_area_intersect / total_area_label
+            ret_metrics['Dice'] = dice
+            ret_metrics['Acc'] = acc
+        elif metric == 'mFscore':
+            precision = total_area_intersect / total_area_pred_label
+            recall = total_area_intersect / total_area_label
+            f_value = torch.tensor(
+                [f_score(x[0], x[1], beta) for x in zip(precision, recall)])
+            ret_metrics['Fscore'] = f_value
+            ret_metrics['Precision'] = precision
+            ret_metrics['Recall'] = recall
+
+    ret_metrics = {
+        metric: value.numpy()
+        for metric, value in ret_metrics.items()
+    }
+    if nan_to_num is not None:
+        ret_metrics = OrderedDict({
+            metric: np.nan_to_num(metric_value, nan=nan_to_num)
+            for metric, metric_value in ret_metrics.items()
+        })
+    return ret_metrics

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/seg/__init__.py

@@ -0,0 +1,4 @@
+from .builder import build_pixel_sampler
+from .sampler import BasePixelSampler, OHEMPixelSampler
+
+__all__ = ['build_pixel_sampler', 'BasePixelSampler', 'OHEMPixelSampler']

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/seg/builder.py

@@ -0,0 +1,8 @@
+from annotator.mmpkg.mmcv.utils import Registry, build_from_cfg
+
+PIXEL_SAMPLERS = Registry('pixel sampler')
+
+
+def build_pixel_sampler(cfg, **default_args):
+    """Build pixel sampler for segmentation map."""
+    return build_from_cfg(cfg, PIXEL_SAMPLERS, default_args)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/seg/sampler/__init__.py

@@ -0,0 +1,4 @@
+from .base_pixel_sampler import BasePixelSampler
+from .ohem_pixel_sampler import OHEMPixelSampler
+
+__all__ = ['BasePixelSampler', 'OHEMPixelSampler']

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/seg/sampler/base_pixel_sampler.py

@@ -0,0 +1,12 @@
+from abc import ABCMeta, abstractmethod
+
+
+class BasePixelSampler(metaclass=ABCMeta):
+    """Base class of pixel sampler."""
+
+    def __init__(self, **kwargs):
+        pass
+
+    @abstractmethod
+    def sample(self, seg_logit, seg_label):
+        """Placeholder for sample function."""

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/seg/sampler/ohem_pixel_sampler.py

@@ -0,0 +1,76 @@
+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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/utils/__init__.py

@@ -0,0 +1,3 @@
+from .misc import add_prefix
+
+__all__ = ['add_prefix']

microsoftexcel-controlnet/annotator/mmpkg/mmseg/core/utils/misc.py

@@ -0,0 +1,17 @@
+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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/__init__.py

@@ -0,0 +1,19 @@
+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'
+]

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/ade.py

@@ -0,0 +1,84 @@
+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)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/builder.py

@@ -0,0 +1,169 @@
+import copy
+import platform
+import random
+from functools import partial
+
+import numpy as np
+from annotator.mmpkg.mmcv.parallel import collate
+from annotator.mmpkg.mmcv.runner import get_dist_info
+from annotator.mmpkg.mmcv.utils import Registry, build_from_cfg
+from annotator.mmpkg.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
+
+    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)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/chase_db1.py

@@ -0,0 +1,27 @@
+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)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/cityscapes.py

@@ -0,0 +1,217 @@
+import os.path as osp
+import tempfile
+
+import annotator.mmpkg.mmcv as mmcv
+import numpy as np
+from annotator.mmpkg.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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/custom.py

@@ -0,0 +1,403 @@
+import os
+import os.path as osp
+from collections import OrderedDict
+from functools import reduce
+
+import annotator.mmpkg.mmcv as mmcv
+import numpy as np
+from annotator.mmpkg.mmcv.utils import print_log
+from torch.utils.data import Dataset
+
+from annotator.mmpkg.mmseg.core import eval_metrics
+from annotator.mmpkg.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)
+
+        try:
+            from prettytable import PrettyTable
+            # 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)
+        except ImportError:  # prettytable is not installed
+            pass
+
+        # 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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/dataset_wrappers.py

@@ -0,0 +1,50 @@
+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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/drive.py

@@ -0,0 +1,27 @@
+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)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/hrf.py

@@ -0,0 +1,27 @@
+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)

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/pascal_context.py

@@ -0,0 +1,103 @@
+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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/pipelines/__init__.py

@@ -0,0 +1,16 @@
+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'
+]

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/pipelines/compose.py

@@ -0,0 +1,51 @@
+import collections
+
+from annotator.mmpkg.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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/pipelines/formating.py

@@ -0,0 +1,288 @@
+from collections.abc import Sequence
+
+import annotator.mmpkg.mmcv as mmcv
+import numpy as np
+import torch
+from annotator.mmpkg.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})'

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/pipelines/loading.py

@@ -0,0 +1,153 @@
+import os.path as osp
+
+import annotator.mmpkg.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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/pipelines/test_time_aug.py

@@ -0,0 +1,133 @@
+import warnings
+
+import annotator.mmpkg.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

microsoftexcel-controlnet/annotator/mmpkg/mmseg/datasets/pipelines/transforms.py

@@ -0,0 +1,889 @@
+import annotator.mmpkg.mmcv as mmcv
+import numpy as np
+from annotator.mmpkg.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