class InfiniteDataLoader(dataloader.DataLoader):
    """Dataloader that reuses workers

    Uses same syntax as vanilla DataLoader
    """

    def __init__(self, *args, **kwargs):
        """Dataloader that reuses workers for same syntax as vanilla DataLoader."""
        super().__init__(*args, **kwargs)
        object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
        self.iterator = super().__iter__()

    def __len__(self):
        """Returns the length of batch_sampler's sampler."""
        return len(self.batch_sampler.sampler)

    def __iter__(self):
        """Creates a sampler that infinitely repeats."""
        for _ in range(len(self)):
            yield next(self.iterator)

class _RepeatSampler:
    """Sampler that repeats forever

    Args:
        sampler (Dataset.sampler): The sampler to repeat.
    """

    def __init__(self, sampler):
        """Sampler that repeats dataset samples infinitely."""
        self.sampler = sampler

    def __iter__(self):
        """Infinite loop iterating over a given sampler."""
        while True:
            yield from iter(self.sampler)

class LoadScreenshots:
    # YOLOv5 screenshot dataloader, i.e. `python detect.py --source "screen 0 100 100 512 256"`
    def __init__(self, source, img_size=640, stride=32, auto=True, transforms=None):
        """source = [screen_number left top width height] (pixels)."""
        check_requirements('mss')
        import mss

        source, *params = source.split()
        self.screen, left, top, width, height = 0, None, None, None, None  # default to full screen 0
        if len(params) == 1:
            self.screen = int(params[0])
        elif len(params) == 4:
            left, top, width, height = (int(x) for x in params)
        elif len(params) == 5:
            self.screen, left, top, width, height = (int(x) for x in params)
        self.img_size = img_size
        self.stride = stride
        self.transforms = transforms
        self.auto = auto
        self.mode = 'stream'
        self.frame = 0
        self.sct = mss.mss()

        # Parse monitor shape
        monitor = self.sct.monitors[self.screen]
        self.top = monitor['top'] if top is None else (monitor['top'] + top)
        self.left = monitor['left'] if left is None else (monitor['left'] + left)
        self.width = width or monitor['width']
        self.height = height or monitor['height']
        self.monitor = {'left': self.left, 'top': self.top, 'width': self.width, 'height': self.height}

    def __iter__(self):
        """Iterates over objects with the same structure as the monitor attribute."""
        return self

    def __next__(self):
        """mss screen capture: get raw pixels from the screen as np array."""
        im0 = np.array(self.sct.grab(self.monitor))[:, :, :3]  # [:, :, :3] BGRA to BGR
        s = f'screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: '

        if self.transforms:
            im = self.transforms(im0)  # transforms
        else:
            im = letterbox(im0, self.img_size, stride=self.stride, auto=self.auto)[0]  # padded resize
            im = im.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
            im = np.ascontiguousarray(im)  # contiguous
        self.frame += 1
        return str(self.screen), im, im0, None, s  # screen, img, original img, im0s, s

class LoadImages:
    # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
    def __init__(self, path, img_size=640, stride=32, auto=True, transforms=None, vid_stride=1):
        """Initialize instance variables and check for valid input."""
        if isinstance(path, str) and Path(path).suffix == '.txt':  # *.txt file with img/vid/dir on each line
            path = Path(path).read_text().rsplit()
        files = []
        for p in sorted(path) if isinstance(path, (list, tuple)) else [path]:
            p = str(Path(p).resolve())
            if '*' in p:
                files.extend(sorted(glob.glob(p, recursive=True)))  # glob
            elif os.path.isdir(p):
                files.extend(sorted(glob.glob(os.path.join(p, '*.*'))))  # dir
            elif os.path.isfile(p):
                files.append(p)  # files
            else:
                raise FileNotFoundError(f'{p} does not exist')

        images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
        videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
        ni, nv = len(images), len(videos)

        self.img_size = img_size
        self.stride = stride
        self.files = images + videos
        self.nf = ni + nv  # number of files
        self.video_flag = [False] * ni + [True] * nv
        self.mode = 'image'
        self.auto = auto
        self.transforms = transforms  # optional
        self.vid_stride = vid_stride  # video frame-rate stride
        if any(videos):
            self._new_video(videos[0])  # new video
        else:
            self.cap = None
        assert self.nf > 0, f'No images or videos found in {p}. ' \
                            f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}'

    def __iter__(self):
        """Returns an iterator object for iterating over images or videos found in a directory."""
        self.count = 0
        return self

    def __next__(self):
        """Iterator's next item, performs transformation on image and returns path, transformed image, original image, capture and size."""
        if self.count == self.nf:
            raise StopIteration
        path = self.files[self.count]

        if self.video_flag[self.count]:
            # Read video
            self.mode = 'video'
            for _ in range(self.vid_stride):
                self.cap.grab()
            ret_val, im0 = self.cap.retrieve()
            while not ret_val:
                self.count += 1
                self.cap.release()
                if self.count == self.nf:  # last video
                    raise StopIteration
                path = self.files[self.count]
                self._new_video(path)
                ret_val, im0 = self.cap.read()

            self.frame += 1
            # im0 = self._cv2_rotate(im0)  # for use if cv2 autorotation is False
            s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '

        else:
            # Read image
            self.count += 1
            im0 = cv2.imread(path)  # BGR
            assert im0 is not None, f'Image Not Found {path}'
            s = f'image {self.count}/{self.nf} {path}: '

        if self.transforms:
            im = self.transforms(im0)  # transforms
        else:
            im = letterbox(im0, self.img_size, stride=self.stride, auto=self.auto)[0]  # padded resize
            im = im.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
            im = np.ascontiguousarray(im)  # contiguous

        return path, im, im0, self.cap, s

    def _new_video(self, path):
        """Create a new video capture object."""
        self.frame = 0
        self.cap = cv2.VideoCapture(path)
        self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT) / self.vid_stride)
        self.orientation = int(self.cap.get(cv2.CAP_PROP_ORIENTATION_META))  # rotation degrees
        # self.cap.set(cv2.CAP_PROP_ORIENTATION_AUTO, 0)  # disable https://github.com/ultralytics/yolov5/issues/8493

    def _cv2_rotate(self, im):
        """Rotate a cv2 video manually."""
        if self.orientation == 0:
            return cv2.rotate(im, cv2.ROTATE_90_CLOCKWISE)
        elif self.orientation == 180:
            return cv2.rotate(im, cv2.ROTATE_90_COUNTERCLOCKWISE)
        elif self.orientation == 90:
            return cv2.rotate(im, cv2.ROTATE_180)
        return im

    def __len__(self):
        """Returns the number of files in the class instance."""
        return self.nf  # number of files

class LoadStreams:
    # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP streams`
    def __init__(self, sources='file.streams', img_size=640, stride=32, auto=True, transforms=None, vid_stride=1):
        """Initialize YOLO detector with optional transforms and check input shapes."""
        torch.backends.cudnn.benchmark = True  # faster for fixed-size inference
        self.mode = 'stream'
        self.img_size = img_size
        self.stride = stride
        self.vid_stride = vid_stride  # video frame-rate stride
        sources = Path(sources).read_text().rsplit() if os.path.isfile(sources) else [sources]
        n = len(sources)
        self.sources = [clean_str(x) for x in sources]  # clean source names for later
        self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
        for i, s in enumerate(sources):  # index, source
            # Start thread to read frames from video stream
            st = f'{i + 1}/{n}: {s}... '
            if urlparse(s).hostname in ('www.youtube.com', 'youtube.com', 'youtu.be'):  # if source is YouTube video
                # YouTube format i.e. 'https://www.youtube.com/watch?v=Zgi9g1ksQHc' or 'https://youtu.be/Zgi9g1ksQHc'
                check_requirements(('pafy', 'youtube_dl==2020.12.2'))
                import pafy
                s = pafy.new(s).getbest(preftype='mp4').url  # YouTube URL
            s = eval(s) if s.isnumeric() else s  # i.e. s = '0' local webcam
            if s == 0:
                assert not is_colab(), '--source 0 webcam unsupported on Colab. Rerun command in a local environment.'
                assert not is_kaggle(), '--source 0 webcam unsupported on Kaggle. Rerun command in a local environment.'
            cap = cv2.VideoCapture(s)
            assert cap.isOpened(), f'{st}Failed to open {s}'
            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
            fps = cap.get(cv2.CAP_PROP_FPS)  # warning: may return 0 or nan
            self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf')  # infinite stream fallback
            self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30  # 30 FPS fallback

            _, self.imgs[i] = cap.read()  # guarantee first frame
            self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
            LOGGER.info(f'{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)')
            self.threads[i].start()
        LOGGER.info('')  # newline

        # Check for common shapes
        s = np.stack([letterbox(x, img_size, stride=stride, auto=auto)[0].shape for x in self.imgs])
        self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
        self.auto = auto and self.rect
        self.transforms = transforms  # optional
        if not self.rect:
            LOGGER.warning('WARNING ⚠️ Stream shapes differ. For optimal performance supply similarly-shaped streams.')

    def update(self, i, cap, stream):
        """Read stream `i` frames in daemon thread."""
        n, f = 0, self.frames[i]  # frame number, frame array
        while cap.isOpened() and n < f:
            n += 1
            cap.grab()  # .read() = .grab() followed by .retrieve()
            if n % self.vid_stride == 0:
                success, im = cap.retrieve()
                if success:
                    self.imgs[i] = im
                else:
                    LOGGER.warning('WARNING ⚠️ Video stream unresponsive, please check your IP camera connection.')
                    self.imgs[i] = np.zeros_like(self.imgs[i])
                    cap.open(stream)  # re-open stream if signal was lost
            time.sleep(0.0)  # wait time

    def __iter__(self):
        """Iterator that returns the class instance."""
        self.count = -1
        return self

    def __next__(self):
        """Return a tuple containing transformed and resized image data."""
        self.count += 1
        if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'):  # q to quit
            cv2.destroyAllWindows()
            raise StopIteration

        im0 = self.imgs.copy()
        if self.transforms:
            im = np.stack([self.transforms(x) for x in im0])  # transforms
        else:
            im = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0] for x in im0])  # resize
            im = im[..., ::-1].transpose((0, 3, 1, 2))  # BGR to RGB, BHWC to BCHW
            im = np.ascontiguousarray(im)  # contiguous

        return self.sources, im, im0, None, ''

    def __len__(self):
        """Returns the number of sources as the length of the object."""
        return len(self.sources)  # 1E12 frames = 32 streams at 30 FPS for 30 years

class LoadImagesAndLabels(Dataset):
    """YOLOv5 train_loader/val_loader, loads images and labels for training and validation."""
    cache_version = 0.6  # dataset labels *.cache version
    rand_interp_methods = [cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4]

    def __init__(self,
                 path,
                 img_size=640,
                 batch_size=16,
                 augment=False,
                 hyp=None,
                 rect=False,
                 image_weights=False,
                 cache_images=False,
                 single_cls=False,
                 stride=32,
                 pad=0.0,
                 min_items=0,
                 prefix=''):
        self.img_size = img_size
        self.augment = augment
        self.hyp = hyp
        self.image_weights = image_weights
        self.rect = False if image_weights else rect
        self.mosaic = self.augment and not self.rect  # load 4 images at a time into a mosaic (only during training)
        self.mosaic_border = [-img_size // 2, -img_size // 2]
        self.stride = stride
        self.path = path
        self.albumentations = Albumentations(size=img_size) if augment else None

        try:
            f = []  # image files
            for p in path if isinstance(path, list) else [path]:
                p = Path(p)  # os-agnostic
                if p.is_dir():  # dir
                    f += glob.glob(str(p / '**' / '*.*'), recursive=True)
                    # f = list(p.rglob('*.*'))  # pathlib
                elif p.is_file():  # file
                    with open(p) as t:
                        t = t.read().strip().splitlines()
                        parent = str(p.parent) + os.sep
                        f += [x.replace('./', parent, 1) if x.startswith('./') else x for x in t]  # to global path
                        # f += [p.parent / x.lstrip(os.sep) for x in t]  # to global path (pathlib)
                else:
                    raise FileNotFoundError(f'{prefix}{p} does not exist')
            self.im_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS)
            # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS])  # pathlib
            assert self.im_files, f'{prefix}No images found'
        except Exception as e:
            raise FileNotFoundError(f'{prefix}Error loading data from {path}: {e}\n{HELP_URL}') from e

        # Check cache
        self.label_files = img2label_paths(self.im_files)  # labels
        cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
        try:
            cache, exists = np.load(cache_path, allow_pickle=True).item(), True  # load dict
            assert cache['version'] == self.cache_version  # matches current version
            assert cache['hash'] == get_hash(self.label_files + self.im_files)  # identical hash
        except (FileNotFoundError, AssertionError, AttributeError):
            cache, exists = self.cache_labels(cache_path, prefix), False  # run cache ops

        # Display cache
        nf, nm, ne, nc, n = cache.pop('results')  # found, missing, empty, corrupt, total
        if exists and LOCAL_RANK in (-1, 0):
            d = f'Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt'
            tqdm(None, desc=prefix + d, total=n, initial=n, bar_format=TQDM_BAR_FORMAT)  # display cache results
            if cache['msgs']:
                LOGGER.info('\n'.join(cache['msgs']))  # display warnings
        assert nf > 0 or not augment, f'{prefix}No labels found in {cache_path}, can not start training. {HELP_URL}'

        # Read cache
        [cache.pop(k) for k in ('hash', 'version', 'msgs')]  # remove items
        labels, shapes, self.segments = zip(*cache.values())
        nl = len(np.concatenate(labels, 0))  # number of labels
        assert nl > 0 or not augment, f'{prefix}All labels empty in {cache_path}, can not start training. {HELP_URL}'
        self.labels = list(labels)
        self.shapes = np.array(shapes)
        self.im_files = list(cache.keys())  # update
        self.label_files = img2label_paths(cache.keys())  # update

        # Filter images
        if min_items:
            include = np.array([len(x) >= min_items for x in self.labels]).nonzero()[0].astype(int)
            LOGGER.info(f'{prefix}{n - len(include)}/{n} images filtered from dataset')
            self.im_files = [self.im_files[i] for i in include]
            self.label_files = [self.label_files[i] for i in include]
            self.labels = [self.labels[i] for i in include]
            self.segments = [self.segments[i] for i in include]
            self.shapes = self.shapes[include]  # wh

        # Create indices
        n = len(self.shapes)  # number of images
        bi = np.floor(np.arange(n) / batch_size).astype(int)  # batch index
        nb = bi[-1] + 1  # number of batches
        self.batch = bi  # batch index of image
        self.n = n
        self.indices = range(n)

        # Update labels
        include_class = []  # filter labels to include only these classes (optional)
        include_class_array = np.array(include_class).reshape(1, -1)
        for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
            if include_class:
                j = (label[:, 0:1] == include_class_array).any(1)
                self.labels[i] = label[j]
                if segment:
                    self.segments[i] = [segment[si] for si, idx in enumerate(j) if idx]
            if single_cls:  # single-class training, merge all classes into 0
                self.labels[i][:, 0] = 0

        # Rectangular Training
        if self.rect:
            # Sort by aspect ratio
            s = self.shapes  # wh
            ar = s[:, 1] / s[:, 0]  # aspect ratio
            irect = ar.argsort()
            self.im_files = [self.im_files[i] for i in irect]
            self.label_files = [self.label_files[i] for i in irect]
            self.labels = [self.labels[i] for i in irect]
            self.segments = [self.segments[i] for i in irect]
            self.shapes = s[irect]  # wh
            ar = ar[irect]

            # Set training image shapes
            shapes = [[1, 1]] * nb
            for i in range(nb):
                ari = ar[bi == i]
                mini, maxi = ari.min(), ari.max()
                if maxi < 1:
                    shapes[i] = [maxi, 1]
                elif mini > 1:
                    shapes[i] = [1, 1 / mini]

            self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(int) * stride

        # Cache images into RAM/disk for faster training
        if cache_images == 'ram' and not self.check_cache_ram(prefix=prefix):
            cache_images = False
        self.ims = [None] * n
        self.npy_files = [Path(f).with_suffix('.npy') for f in self.im_files]
        if cache_images:
            b, gb = 0, 1 << 30  # bytes of cached images, bytes per gigabytes
            self.im_hw0, self.im_hw = [None] * n, [None] * n
            fcn = self.cache_images_to_disk if cache_images == 'disk' else self.load_image
            with ThreadPool(NUM_THREADS) as pool:
                results = pool.imap(fcn, range(n))
                pbar = tqdm(enumerate(results), total=n, bar_format=TQDM_BAR_FORMAT, disable=LOCAL_RANK > 0)
                for i, x in pbar:
                    if cache_images == 'disk':
                        b += self.npy_files[i].stat().st_size
                    else:  # 'ram'
                        self.ims[i], self.im_hw0[i], self.im_hw[i] = x  # im, hw_orig, hw_resized = load_image(self, i)
                        b += self.ims[i].nbytes
                    pbar.desc = f'{prefix}Caching images ({b / gb:.1f}GB {cache_images})'
                pbar.close()

    def check_cache_ram(self, safety_margin=0.1, prefix=''):
        """Check image caching requirements vs available memory."""
        b, gb = 0, 1 << 30  # bytes of cached images, bytes per gigabytes
        n = min(self.n, 30)  # extrapolate from 30 random images
        for _ in range(n):
            im = cv2.imread(random.choice(self.im_files))  # sample image
            ratio = self.img_size / max(im.shape[0], im.shape[1])  # max(h, w)  # ratio
            b += im.nbytes * ratio ** 2
        mem_required = b * self.n / n  # GB required to cache dataset into RAM
        mem = psutil.virtual_memory()
        cache = mem_required * (1 + safety_margin) < mem.available  # to cache or not to cache, that is the question
        if not cache:
            LOGGER.info(f'{prefix}{mem_required / gb:.1f}GB RAM required, '
                        f'{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, '
                        f"{'caching images ✅' if cache else 'not caching images ⚠️'}")
        return cache

    def cache_labels(self, path=Path('./labels.cache'), prefix=''):
        """Cache labels and save as numpy file for next time."""
        # Cache dataset labels, check images and read shapes
        if path.exists():
            path.unlink()  # remove *.cache file if exists
        x = {}  # dict
        nm, nf, ne, nc, msgs = 0, 0, 0, 0, []  # number missing, found, empty, corrupt, messages
        desc = f'{prefix}Scanning {path.parent / path.stem}...'
        total = len(self.im_files)
        with ThreadPool(NUM_THREADS) as pool:
            results = pool.imap(verify_image_label, zip(self.im_files, self.label_files, repeat(prefix)))
            pbar = tqdm(results, desc=desc, total=total, bar_format=TQDM_BAR_FORMAT)
            for im_file, lb, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
                nm += nm_f
                nf += nf_f
                ne += ne_f
                nc += nc_f
                if im_file:
                    x[im_file] = [lb, shape, segments]
                if msg:
                    msgs.append(msg)
                pbar.desc = f'{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt'
            pbar.close()

        if msgs:
            LOGGER.info('\n'.join(msgs))
        if nf == 0:
            LOGGER.warning(f'{prefix}WARNING ⚠️ No labels found in {path}. {HELP_URL}')
        x['hash'] = get_hash(self.label_files + self.im_files)
        x['results'] = nf, nm, ne, nc, len(self.im_files)
        x['msgs'] = msgs  # warnings
        x['version'] = self.cache_version  # cache version
        if is_dir_writeable(path.parent):
            np.save(str(path), x)  # save cache for next time
            path.with_suffix('.cache.npy').rename(path)  # remove .npy suffix
            LOGGER.info(f'{prefix}New cache created: {path}')
        else:
            LOGGER.warning(f'{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable')  # not writeable
        return x

    def __len__(self):
        """Returns the length of 'im_files' attribute."""
        return len(self.im_files)

    def __getitem__(self, index):
        """Get a sample and its corresponding label, filename and shape from the dataset."""
        index = self.indices[index]  # linear, shuffled, or image_weights

        hyp = self.hyp
        mosaic = self.mosaic and random.random() < hyp['mosaic']
        if mosaic:
            # Load mosaic
            img, labels = self.load_mosaic(index)
            shapes = None

            # MixUp augmentation
            if random.random() < hyp['mixup']:
                img, labels = mixup(img, labels, *self.load_mosaic(random.randint(0, self.n - 1)))

        else:
            # Load image
            img, (h0, w0), (h, w) = self.load_image(index)

            # Letterbox
            shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size  # final letterboxed shape
            img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
            shapes = (h0, w0), ((h / h0, w / w0), pad)  # for COCO mAP rescaling

            labels = self.labels[index].copy()
            if labels.size:  # normalized xywh to pixel xyxy format
                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])

            if self.augment:
                img, labels = random_perspective(img,
                                                 labels,
                                                 degrees=hyp['degrees'],
                                                 translate=hyp['translate'],
                                                 scale=hyp['scale'],
                                                 shear=hyp['shear'],
                                                 perspective=hyp['perspective'])

        nl = len(labels)  # number of labels
        if nl:
            labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3)

        if self.augment:
            # Albumentations
            img, labels = self.albumentations(img, labels)
            nl = len(labels)  # update after albumentations

            # HSV color-space
            augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])

            # Flip up-down
            if random.random() < hyp['flipud']:
                img = np.flipud(img)
                if nl:
                    labels[:, 2] = 1 - labels[:, 2]

            # Flip left-right
            if random.random() < hyp['fliplr']:
                img = np.fliplr(img)
                if nl:
                    labels[:, 1] = 1 - labels[:, 1]

            # Cutouts
            # labels = cutout(img, labels, p=0.5)
            # nl = len(labels)  # update after cutout

        labels_out = torch.zeros((nl, 6))
        if nl:
            labels_out[:, 1:] = torch.from_numpy(labels)

        # Convert
        img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
        img = np.ascontiguousarray(img)

        return torch.from_numpy(img), labels_out, self.im_files[index], shapes

    def load_image(self, i):
        """Loads 1 image from dataset index 'i', returns (im, original hw, resized hw)."""
        im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i],
        if im is None:  # not cached in RAM
            if fn.exists():  # load npy
                im = np.load(fn)
            else:  # read image
                im = cv2.imread(f)  # BGR
                assert im is not None, f'Image Not Found {f}'
            h0, w0 = im.shape[:2]  # orig hw
            r = self.img_size / max(h0, w0)  # ratio
            if r != 1:  # if sizes are not equal
                interp = cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA
                im = cv2.resize(im, (math.ceil(w0 * r), math.ceil(h0 * r)), interpolation=interp)
            return im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
        return self.ims[i], self.im_hw0[i], self.im_hw[i]  # im, hw_original, hw_resized

    def cache_images_to_disk(self, i):
        """Saves an image as an *.npy file for faster loading."""
        f = self.npy_files[i]
        if not f.exists():
            np.save(f.as_posix(), cv2.imread(self.im_files[i]))

    def load_mosaic(self, index):
        """YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic."""
        labels4, segments4 = [], []
        s = self.img_size
        yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border)  # mosaic center x, y
        indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
        random.shuffle(indices)
        for i, index in enumerate(indices):
            # Load image
            img, _, (h, w) = self.load_image(index)

            # Place img in img4
            if i == 0:  # top left
                img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
                x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
                x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
            elif i == 1:  # top right
                x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
                x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
            elif i == 2:  # bottom left
                x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
                x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
            elif i == 3:  # bottom right
                x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
                x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)

            img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
            padw = x1a - x1b
            padh = y1a - y1b

            # Labels
            labels, segments = self.labels[index].copy(), self.segments[index].copy()
            if labels.size:
                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh)  # normalized xywh to pixel xyxy format
                segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
            labels4.append(labels)
            segments4.extend(segments)

        # Concat/clip labels
        labels4 = np.concatenate(labels4, 0)
        for x in (labels4[:, 1:], *segments4):
            np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
        # img4, labels4 = replicate(img4, labels4)  # replicate

        # Augment
        img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
        img4, labels4 = random_perspective(img4,
                                           labels4,
                                           segments4,
                                           degrees=self.hyp['degrees'],
                                           translate=self.hyp['translate'],
                                           scale=self.hyp['scale'],
                                           shear=self.hyp['shear'],
                                           perspective=self.hyp['perspective'],
                                           border=self.mosaic_border)  # border to remove

        return img4, labels4

    def load_mosaic9(self, index):
        """YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic."""
        labels9, segments9 = [], []
        s = self.img_size
        indices = [index] + random.choices(self.indices, k=8)  # 8 additional image indices
        random.shuffle(indices)
        hp, wp = -1, -1  # height, width previous
        for i, index in enumerate(indices):
            # Load image
            img, _, (h, w) = self.load_image(index)

            # Place img in img9
            if i == 0:  # center
                img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
                h0, w0 = h, w
                c = s, s, s + w, s + h  # xmin, ymin, xmax, ymax (base) coordinates
            elif i == 1:  # top
                c = s, s - h, s + w, s
            elif i == 2:  # top right
                c = s + wp, s - h, s + wp + w, s
            elif i == 3:  # right
                c = s + w0, s, s + w0 + w, s + h
            elif i == 4:  # bottom right
                c = s + w0, s + hp, s + w0 + w, s + hp + h
            elif i == 5:  # bottom
                c = s + w0 - w, s + h0, s + w0, s + h0 + h
            elif i == 6:  # bottom left
                c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
            elif i == 7:  # left
                c = s - w, s + h0 - h, s, s + h0
            elif i == 8:  # top left
                c = s - w, s + h0 - hp - h, s, s + h0 - hp

            padx, pady = c[:2]
            x1, y1, x2, y2 = (max(x, 0) for x in c)  # allocate coords

            # Labels
            labels, segments = self.labels[index].copy(), self.segments[index].copy()
            if labels.size:
                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady)  # normalized xywh to pixel xyxy format
                segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
            labels9.append(labels)
            segments9.extend(segments)

            # Image
            img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:]  # img9[ymin:ymax, xmin:xmax]
            hp, wp = h, w  # height, width previous

        # Offset
        yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border)  # mosaic center x, y
        img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]

        # Concat/clip labels
        labels9 = np.concatenate(labels9, 0)
        labels9[:, [1, 3]] -= xc
        labels9[:, [2, 4]] -= yc
        c = np.array([xc, yc])  # centers
        segments9 = [x - c for x in segments9]

        for x in (labels9[:, 1:], *segments9):
            np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
        # img9, labels9 = replicate(img9, labels9)  # replicate

        # Augment
        img9, labels9, segments9 = copy_paste(img9, labels9, segments9, p=self.hyp['copy_paste'])
        img9, labels9 = random_perspective(img9,
                                           labels9,
                                           segments9,
                                           degrees=self.hyp['degrees'],
                                           translate=self.hyp['translate'],
                                           scale=self.hyp['scale'],
                                           shear=self.hyp['shear'],
                                           perspective=self.hyp['perspective'],
                                           border=self.mosaic_border)  # border to remove

        return img9, labels9

    @staticmethod
    def collate_fn(batch):
        """YOLOv8 collate function, outputs dict."""
        im, label, path, shapes = zip(*batch)  # transposed
        for i, lb in enumerate(label):
            lb[:, 0] = i  # add target image index for build_targets()
        batch_idx, cls, bboxes = torch.cat(label, 0).split((1, 1, 4), dim=1)
        return {
            'ori_shape': tuple((x[0] if x else None) for x in shapes),
            'ratio_pad': tuple((x[1] if x else None) for x in shapes),
            'im_file': path,
            'img': torch.stack(im, 0),
            'cls': cls,
            'bboxes': bboxes,
            'batch_idx': batch_idx.view(-1)}

    @staticmethod
    def collate_fn_old(batch):
        """YOLOv5 original collate function."""
        im, label, path, shapes = zip(*batch)  # transposed
        for i, lb in enumerate(label):
            lb[:, 0] = i  # add target image index for build_targets()
        return torch.stack(im, 0), torch.cat(label, 0), path, shapes