انتقل إلى المحتوى

مرجع ل ultralytics/data/dataset.py

ملاحظه

هذا الملف متاح في https://github.com/ultralytics/ultralytics/ نقطة / الرئيسية /ultralytics/البيانات/dataset.py. إذا اكتشفت مشكلة ، فيرجى المساعدة في إصلاحها من خلال المساهمة في طلب 🛠️ سحب. شكرا لك 🙏!



ultralytics.data.dataset.YOLODataset

قواعد: BaseDataset

فئة مجموعة البيانات لتحميل تسميات الكشف عن الكائنات و / أو التجزئة في YOLO تنسيق.

البارامترات:

اسم نوع وصف افتراضي
data dict

قاموس YAML لمجموعة البيانات. الإعدادات الافتراضية إلى لا شيء.

None
task str

arg صريح للإشارة إلى المهمة الحالية ، الإعدادات الافتراضية ل "الكشف".

'detect'

ارجاع:

نوع وصف
Dataset

A PyTorch كائن مجموعة البيانات التي يمكن استخدامها لتدريب نموذج الكشف عن الكائنات.

شفرة المصدر في ultralytics/data/dataset.py
class YOLODataset(BaseDataset):
    """
    Dataset class for loading object detection and/or segmentation labels in YOLO format.

    Args:
        data (dict, optional): A dataset YAML dictionary. Defaults to None.
        task (str): An explicit arg to point current task, Defaults to 'detect'.

    Returns:
        (torch.utils.data.Dataset): A PyTorch dataset object that can be used for training an object detection model.
    """

    def __init__(self, *args, data=None, task="detect", **kwargs):
        """Initializes the YOLODataset with optional configurations for segments and keypoints."""
        self.use_segments = task == "segment"
        self.use_keypoints = task == "pose"
        self.use_obb = task == "obb"
        self.data = data
        assert not (self.use_segments and self.use_keypoints), "Can not use both segments and keypoints."
        super().__init__(*args, **kwargs)

    def cache_labels(self, path=Path("./labels.cache")):
        """
        Cache dataset labels, check images and read shapes.

        Args:
            path (Path): Path where to save the cache file. Default is Path('./labels.cache').

        Returns:
            (dict): labels.
        """
        x = {"labels": []}
        nm, nf, ne, nc, msgs = 0, 0, 0, 0, []  # number missing, found, empty, corrupt, messages
        desc = f"{self.prefix}Scanning {path.parent / path.stem}..."
        total = len(self.im_files)
        nkpt, ndim = self.data.get("kpt_shape", (0, 0))
        if self.use_keypoints and (nkpt <= 0 or ndim not in {2, 3}):
            raise ValueError(
                "'kpt_shape' in data.yaml missing or incorrect. Should be a list with [number of "
                "keypoints, number of dims (2 for x,y or 3 for x,y,visible)], i.e. 'kpt_shape: [17, 3]'"
            )
        with ThreadPool(NUM_THREADS) as pool:
            results = pool.imap(
                func=verify_image_label,
                iterable=zip(
                    self.im_files,
                    self.label_files,
                    repeat(self.prefix),
                    repeat(self.use_keypoints),
                    repeat(len(self.data["names"])),
                    repeat(nkpt),
                    repeat(ndim),
                ),
            )
            pbar = TQDM(results, desc=desc, total=total)
            for im_file, lb, shape, segments, keypoint, 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["labels"].append(
                        {
                            "im_file": im_file,
                            "shape": shape,
                            "cls": lb[:, 0:1],  # n, 1
                            "bboxes": lb[:, 1:],  # n, 4
                            "segments": segments,
                            "keypoints": keypoint,
                            "normalized": True,
                            "bbox_format": "xywh",
                        }
                    )
                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"{self.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
        save_dataset_cache_file(self.prefix, path, x, DATASET_CACHE_VERSION)
        return x

    def get_labels(self):
        """Returns dictionary of labels for YOLO training."""
        self.label_files = img2label_paths(self.im_files)
        cache_path = Path(self.label_files[0]).parent.with_suffix(".cache")
        try:
            cache, exists = load_dataset_cache_file(cache_path), True  # attempt to load a *.cache file
            assert cache["version"] == DATASET_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), 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=self.prefix + d, total=n, initial=n)  # display results
            if cache["msgs"]:
                LOGGER.info("\n".join(cache["msgs"]))  # display warnings

        # Read cache
        [cache.pop(k) for k in ("hash", "version", "msgs")]  # remove items
        labels = cache["labels"]
        if not labels:
            LOGGER.warning(f"WARNING ⚠️ No images found in {cache_path}, training may not work correctly. {HELP_URL}")
        self.im_files = [lb["im_file"] for lb in labels]  # update im_files

        # Check if the dataset is all boxes or all segments
        lengths = ((len(lb["cls"]), len(lb["bboxes"]), len(lb["segments"])) for lb in labels)
        len_cls, len_boxes, len_segments = (sum(x) for x in zip(*lengths))
        if len_segments and len_boxes != len_segments:
            LOGGER.warning(
                f"WARNING ⚠️ Box and segment counts should be equal, but got len(segments) = {len_segments}, "
                f"len(boxes) = {len_boxes}. To resolve this only boxes will be used and all segments will be removed. "
                "To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset."
            )
            for lb in labels:
                lb["segments"] = []
        if len_cls == 0:
            LOGGER.warning(f"WARNING ⚠️ No labels found in {cache_path}, training may not work correctly. {HELP_URL}")
        return labels

    def build_transforms(self, hyp=None):
        """Builds and appends transforms to the list."""
        if self.augment:
            hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0
            hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
            transforms = v8_transforms(self, self.imgsz, hyp)
        else:
            transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), scaleup=False)])
        transforms.append(
            Format(
                bbox_format="xywh",
                normalize=True,
                return_mask=self.use_segments,
                return_keypoint=self.use_keypoints,
                return_obb=self.use_obb,
                batch_idx=True,
                mask_ratio=hyp.mask_ratio,
                mask_overlap=hyp.overlap_mask,
                bgr=hyp.bgr if self.augment else 0.0,  # only affect training.
            )
        )
        return transforms

    def close_mosaic(self, hyp):
        """Sets mosaic, copy_paste and mixup options to 0.0 and builds transformations."""
        hyp.mosaic = 0.0  # set mosaic ratio=0.0
        hyp.copy_paste = 0.0  # keep the same behavior as previous v8 close-mosaic
        hyp.mixup = 0.0  # keep the same behavior as previous v8 close-mosaic
        self.transforms = self.build_transforms(hyp)

    def update_labels_info(self, label):
        """
        Custom your label format here.

        Note:
            cls is not with bboxes now, classification and semantic segmentation need an independent cls label
            Can also support classification and semantic segmentation by adding or removing dict keys there.
        """
        bboxes = label.pop("bboxes")
        segments = label.pop("segments", [])
        keypoints = label.pop("keypoints", None)
        bbox_format = label.pop("bbox_format")
        normalized = label.pop("normalized")

        # NOTE: do NOT resample oriented boxes
        segment_resamples = 100 if self.use_obb else 1000
        if len(segments) > 0:
            # list[np.array(1000, 2)] * num_samples
            # (N, 1000, 2)
            segments = np.stack(resample_segments(segments, n=segment_resamples), axis=0)
        else:
            segments = np.zeros((0, segment_resamples, 2), dtype=np.float32)
        label["instances"] = Instances(bboxes, segments, keypoints, bbox_format=bbox_format, normalized=normalized)
        return label

    @staticmethod
    def collate_fn(batch):
        """Collates data samples into batches."""
        new_batch = {}
        keys = batch[0].keys()
        values = list(zip(*[list(b.values()) for b in batch]))
        for i, k in enumerate(keys):
            value = values[i]
            if k == "img":
                value = torch.stack(value, 0)
            if k in {"masks", "keypoints", "bboxes", "cls", "segments", "obb"}:
                value = torch.cat(value, 0)
            new_batch[k] = value
        new_batch["batch_idx"] = list(new_batch["batch_idx"])
        for i in range(len(new_batch["batch_idx"])):
            new_batch["batch_idx"][i] += i  # add target image index for build_targets()
        new_batch["batch_idx"] = torch.cat(new_batch["batch_idx"], 0)
        return new_batch

__init__(*args, data=None, task='detect', **kwargs)

تهيئة YOLODataset مع تكوينات اختيارية للمقاطع والنقاط الرئيسية.

شفرة المصدر في ultralytics/data/dataset.py
def __init__(self, *args, data=None, task="detect", **kwargs):
    """Initializes the YOLODataset with optional configurations for segments and keypoints."""
    self.use_segments = task == "segment"
    self.use_keypoints = task == "pose"
    self.use_obb = task == "obb"
    self.data = data
    assert not (self.use_segments and self.use_keypoints), "Can not use both segments and keypoints."
    super().__init__(*args, **kwargs)

build_transforms(hyp=None)

يبني ويلحق التحويلات إلى القائمة.

شفرة المصدر في ultralytics/data/dataset.py
def build_transforms(self, hyp=None):
    """Builds and appends transforms to the list."""
    if self.augment:
        hyp.mosaic = hyp.mosaic if self.augment and not self.rect else 0.0
        hyp.mixup = hyp.mixup if self.augment and not self.rect else 0.0
        transforms = v8_transforms(self, self.imgsz, hyp)
    else:
        transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), scaleup=False)])
    transforms.append(
        Format(
            bbox_format="xywh",
            normalize=True,
            return_mask=self.use_segments,
            return_keypoint=self.use_keypoints,
            return_obb=self.use_obb,
            batch_idx=True,
            mask_ratio=hyp.mask_ratio,
            mask_overlap=hyp.overlap_mask,
            bgr=hyp.bgr if self.augment else 0.0,  # only affect training.
        )
    )
    return transforms

cache_labels(path=Path('./labels.cache'))

قم بتخزين تسميات مجموعة البيانات مؤقتا وتحقق من الصور واقرأ الأشكال.

البارامترات:

اسم نوع وصف افتراضي
path Path

مسار مكان حفظ ملف ذاكرة التخزين المؤقت. الافتراضي هو المسار ('./labels.cache').

Path('./labels.cache')

ارجاع:

نوع وصف
dict

تسميات.

شفرة المصدر في ultralytics/data/dataset.py
def cache_labels(self, path=Path("./labels.cache")):
    """
    Cache dataset labels, check images and read shapes.

    Args:
        path (Path): Path where to save the cache file. Default is Path('./labels.cache').

    Returns:
        (dict): labels.
    """
    x = {"labels": []}
    nm, nf, ne, nc, msgs = 0, 0, 0, 0, []  # number missing, found, empty, corrupt, messages
    desc = f"{self.prefix}Scanning {path.parent / path.stem}..."
    total = len(self.im_files)
    nkpt, ndim = self.data.get("kpt_shape", (0, 0))
    if self.use_keypoints and (nkpt <= 0 or ndim not in {2, 3}):
        raise ValueError(
            "'kpt_shape' in data.yaml missing or incorrect. Should be a list with [number of "
            "keypoints, number of dims (2 for x,y or 3 for x,y,visible)], i.e. 'kpt_shape: [17, 3]'"
        )
    with ThreadPool(NUM_THREADS) as pool:
        results = pool.imap(
            func=verify_image_label,
            iterable=zip(
                self.im_files,
                self.label_files,
                repeat(self.prefix),
                repeat(self.use_keypoints),
                repeat(len(self.data["names"])),
                repeat(nkpt),
                repeat(ndim),
            ),
        )
        pbar = TQDM(results, desc=desc, total=total)
        for im_file, lb, shape, segments, keypoint, 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["labels"].append(
                    {
                        "im_file": im_file,
                        "shape": shape,
                        "cls": lb[:, 0:1],  # n, 1
                        "bboxes": lb[:, 1:],  # n, 4
                        "segments": segments,
                        "keypoints": keypoint,
                        "normalized": True,
                        "bbox_format": "xywh",
                    }
                )
            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"{self.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
    save_dataset_cache_file(self.prefix, path, x, DATASET_CACHE_VERSION)
    return x

close_mosaic(hyp)

يضبط خيارات الفسيفساء copy_paste والمزج على 0.0 ويبني التحويلات.

شفرة المصدر في ultralytics/data/dataset.py
def close_mosaic(self, hyp):
    """Sets mosaic, copy_paste and mixup options to 0.0 and builds transformations."""
    hyp.mosaic = 0.0  # set mosaic ratio=0.0
    hyp.copy_paste = 0.0  # keep the same behavior as previous v8 close-mosaic
    hyp.mixup = 0.0  # keep the same behavior as previous v8 close-mosaic
    self.transforms = self.build_transforms(hyp)

collate_fn(batch) staticmethod

يجمع عينات البيانات على دفعات.

شفرة المصدر في ultralytics/data/dataset.py
@staticmethod
def collate_fn(batch):
    """Collates data samples into batches."""
    new_batch = {}
    keys = batch[0].keys()
    values = list(zip(*[list(b.values()) for b in batch]))
    for i, k in enumerate(keys):
        value = values[i]
        if k == "img":
            value = torch.stack(value, 0)
        if k in {"masks", "keypoints", "bboxes", "cls", "segments", "obb"}:
            value = torch.cat(value, 0)
        new_batch[k] = value
    new_batch["batch_idx"] = list(new_batch["batch_idx"])
    for i in range(len(new_batch["batch_idx"])):
        new_batch["batch_idx"][i] += i  # add target image index for build_targets()
    new_batch["batch_idx"] = torch.cat(new_batch["batch_idx"], 0)
    return new_batch

get_labels()

إرجاع قاموس التسميات ل YOLO تدريب.

شفرة المصدر في ultralytics/data/dataset.py
def get_labels(self):
    """Returns dictionary of labels for YOLO training."""
    self.label_files = img2label_paths(self.im_files)
    cache_path = Path(self.label_files[0]).parent.with_suffix(".cache")
    try:
        cache, exists = load_dataset_cache_file(cache_path), True  # attempt to load a *.cache file
        assert cache["version"] == DATASET_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), 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=self.prefix + d, total=n, initial=n)  # display results
        if cache["msgs"]:
            LOGGER.info("\n".join(cache["msgs"]))  # display warnings

    # Read cache
    [cache.pop(k) for k in ("hash", "version", "msgs")]  # remove items
    labels = cache["labels"]
    if not labels:
        LOGGER.warning(f"WARNING ⚠️ No images found in {cache_path}, training may not work correctly. {HELP_URL}")
    self.im_files = [lb["im_file"] for lb in labels]  # update im_files

    # Check if the dataset is all boxes or all segments
    lengths = ((len(lb["cls"]), len(lb["bboxes"]), len(lb["segments"])) for lb in labels)
    len_cls, len_boxes, len_segments = (sum(x) for x in zip(*lengths))
    if len_segments and len_boxes != len_segments:
        LOGGER.warning(
            f"WARNING ⚠️ Box and segment counts should be equal, but got len(segments) = {len_segments}, "
            f"len(boxes) = {len_boxes}. To resolve this only boxes will be used and all segments will be removed. "
            "To avoid this please supply either a detect or segment dataset, not a detect-segment mixed dataset."
        )
        for lb in labels:
            lb["segments"] = []
    if len_cls == 0:
        LOGGER.warning(f"WARNING ⚠️ No labels found in {cache_path}, training may not work correctly. {HELP_URL}")
    return labels

update_labels_info(label)

قم بتخصيص تنسيق التسمية الخاص بك هنا.

ملاحظه

CLS ليس مع bboxes الآن ، يحتاج التصنيف والتجزئة الدلالية إلى تسمية CLS مستقلة يمكن أيضا دعم التصنيف والتجزئة الدلالية عن طريق إضافة أو إزالة مفاتيح dict هناك.

شفرة المصدر في ultralytics/data/dataset.py
def update_labels_info(self, label):
    """
    Custom your label format here.

    Note:
        cls is not with bboxes now, classification and semantic segmentation need an independent cls label
        Can also support classification and semantic segmentation by adding or removing dict keys there.
    """
    bboxes = label.pop("bboxes")
    segments = label.pop("segments", [])
    keypoints = label.pop("keypoints", None)
    bbox_format = label.pop("bbox_format")
    normalized = label.pop("normalized")

    # NOTE: do NOT resample oriented boxes
    segment_resamples = 100 if self.use_obb else 1000
    if len(segments) > 0:
        # list[np.array(1000, 2)] * num_samples
        # (N, 1000, 2)
        segments = np.stack(resample_segments(segments, n=segment_resamples), axis=0)
    else:
        segments = np.zeros((0, segment_resamples, 2), dtype=np.float32)
    label["instances"] = Instances(bboxes, segments, keypoints, bbox_format=bbox_format, normalized=normalized)
    return label



ultralytics.data.dataset.YOLOMultiModalDataset

قواعد: YOLODataset

فئة مجموعة البيانات لتحميل تسميات الكشف عن الكائنات و / أو التجزئة في YOLO تنسيق.

البارامترات:

اسم نوع وصف افتراضي
data dict

قاموس YAML لمجموعة البيانات. الإعدادات الافتراضية إلى لا شيء.

None
task str

arg صريح للإشارة إلى المهمة الحالية ، الإعدادات الافتراضية ل "الكشف".

'detect'

ارجاع:

نوع وصف
Dataset

A PyTorch كائن مجموعة البيانات التي يمكن استخدامها لتدريب نموذج الكشف عن الكائنات.

شفرة المصدر في ultralytics/data/dataset.py
class YOLOMultiModalDataset(YOLODataset):
    """
    Dataset class for loading object detection and/or segmentation labels in YOLO format.

    Args:
        data (dict, optional): A dataset YAML dictionary. Defaults to None.
        task (str): An explicit arg to point current task, Defaults to 'detect'.

    Returns:
        (torch.utils.data.Dataset): A PyTorch dataset object that can be used for training an object detection model.
    """

    def __init__(self, *args, data=None, task="detect", **kwargs):
        """Initializes a dataset object for object detection tasks with optional specifications."""
        super().__init__(*args, data=data, task=task, **kwargs)

    def update_labels_info(self, label):
        """Add texts information for multi modal model training."""
        labels = super().update_labels_info(label)
        # NOTE: some categories are concatenated with its synonyms by `/`.
        labels["texts"] = [v.split("/") for _, v in self.data["names"].items()]
        return labels

    def build_transforms(self, hyp=None):
        """Enhances data transformations with optional text augmentation for multi-modal training."""
        transforms = super().build_transforms(hyp)
        if self.augment:
            # NOTE: hard-coded the args for now.
            transforms.insert(-1, RandomLoadText(max_samples=min(self.data["nc"], 80), padding=True))
        return transforms

__init__(*args, data=None, task='detect', **kwargs)

تهيئة كائن مجموعة بيانات لمهام الكشف عن الكائنات بمواصفات اختيارية.

شفرة المصدر في ultralytics/data/dataset.py
def __init__(self, *args, data=None, task="detect", **kwargs):
    """Initializes a dataset object for object detection tasks with optional specifications."""
    super().__init__(*args, data=data, task=task, **kwargs)

build_transforms(hyp=None)

يحسن تحويلات البيانات من خلال زيادة النص الاختيارية للتدريب متعدد الوسائط.

شفرة المصدر في ultralytics/data/dataset.py
def build_transforms(self, hyp=None):
    """Enhances data transformations with optional text augmentation for multi-modal training."""
    transforms = super().build_transforms(hyp)
    if self.augment:
        # NOTE: hard-coded the args for now.
        transforms.insert(-1, RandomLoadText(max_samples=min(self.data["nc"], 80), padding=True))
    return transforms

update_labels_info(label)

إضافة معلومات نصية للتدريب على النموذج متعدد الوسائط.

شفرة المصدر في ultralytics/data/dataset.py
def update_labels_info(self, label):
    """Add texts information for multi modal model training."""
    labels = super().update_labels_info(label)
    # NOTE: some categories are concatenated with its synonyms by `/`.
    labels["texts"] = [v.split("/") for _, v in self.data["names"].items()]
    return labels



ultralytics.data.dataset.GroundingDataset

قواعد: YOLODataset

شفرة المصدر في ultralytics/data/dataset.py
class GroundingDataset(YOLODataset):
    def __init__(self, *args, task="detect", json_file, **kwargs):
        """Initializes a GroundingDataset for object detection, loading annotations from a specified JSON file."""
        assert task == "detect", "`GroundingDataset` only support `detect` task for now!"
        self.json_file = json_file
        super().__init__(*args, task=task, data={}, **kwargs)

    def get_img_files(self, img_path):
        """The image files would be read in `get_labels` function, return empty list here."""
        return []

    def get_labels(self):
        """Loads annotations from a JSON file, filters, and normalizes bounding boxes for each image."""
        labels = []
        LOGGER.info("Loading annotation file...")
        with open(self.json_file, "r") as f:
            annotations = json.load(f)
        images = {f'{x["id"]:d}': x for x in annotations["images"]}
        imgToAnns = defaultdict(list)
        for ann in annotations["annotations"]:
            imgToAnns[ann["image_id"]].append(ann)
        for img_id, anns in TQDM(imgToAnns.items(), desc=f"Reading annotations {self.json_file}"):
            img = images[f"{img_id:d}"]
            h, w, f = img["height"], img["width"], img["file_name"]
            im_file = Path(self.img_path) / f
            if not im_file.exists():
                continue
            self.im_files.append(str(im_file))
            bboxes = []
            cat2id = {}
            texts = []
            for ann in anns:
                if ann["iscrowd"]:
                    continue
                box = np.array(ann["bbox"], dtype=np.float32)
                box[:2] += box[2:] / 2
                box[[0, 2]] /= float(w)
                box[[1, 3]] /= float(h)
                if box[2] <= 0 or box[3] <= 0:
                    continue

                cat_name = " ".join([img["caption"][t[0] : t[1]] for t in ann["tokens_positive"]])
                if cat_name not in cat2id:
                    cat2id[cat_name] = len(cat2id)
                    texts.append([cat_name])
                cls = cat2id[cat_name]  # class
                box = [cls] + box.tolist()
                if box not in bboxes:
                    bboxes.append(box)
            lb = np.array(bboxes, dtype=np.float32) if len(bboxes) else np.zeros((0, 5), dtype=np.float32)
            labels.append(
                {
                    "im_file": im_file,
                    "shape": (h, w),
                    "cls": lb[:, 0:1],  # n, 1
                    "bboxes": lb[:, 1:],  # n, 4
                    "normalized": True,
                    "bbox_format": "xywh",
                    "texts": texts,
                }
            )
        return labels

    def build_transforms(self, hyp=None):
        """Configures augmentations for training with optional text loading; `hyp` adjusts augmentation intensity."""
        transforms = super().build_transforms(hyp)
        if self.augment:
            # NOTE: hard-coded the args for now.
            transforms.insert(-1, RandomLoadText(max_samples=80, padding=True))
        return transforms

__init__(*args, task='detect', json_file, **kwargs)

تهيئة مجموعة GroundingDataset للكشف عن الكائنات، وتحميل التعليقات التوضيحية من ملف JSON محدد.

شفرة المصدر في ultralytics/data/dataset.py
def __init__(self, *args, task="detect", json_file, **kwargs):
    """Initializes a GroundingDataset for object detection, loading annotations from a specified JSON file."""
    assert task == "detect", "`GroundingDataset` only support `detect` task for now!"
    self.json_file = json_file
    super().__init__(*args, task=task, data={}, **kwargs)

build_transforms(hyp=None)

تكوين التعزيزات للتدريب مع تحميل النص الاختياري ؛ hyp يضبط شدة الزيادة.

شفرة المصدر في ultralytics/data/dataset.py
def build_transforms(self, hyp=None):
    """Configures augmentations for training with optional text loading; `hyp` adjusts augmentation intensity."""
    transforms = super().build_transforms(hyp)
    if self.augment:
        # NOTE: hard-coded the args for now.
        transforms.insert(-1, RandomLoadText(max_samples=80, padding=True))
    return transforms

get_img_files(img_path)

ستتم قراءة ملفات الصور في get_labels وظيفة ، إرجاع قائمة فارغة هنا.

شفرة المصدر في ultralytics/data/dataset.py
def get_img_files(self, img_path):
    """The image files would be read in `get_labels` function, return empty list here."""
    return []

get_labels()

تحميل التعليقات التوضيحية من ملف JSON، وتصفية المربعات المحيطة لكل صورة وتطبيعها.

شفرة المصدر في ultralytics/data/dataset.py
def get_labels(self):
    """Loads annotations from a JSON file, filters, and normalizes bounding boxes for each image."""
    labels = []
    LOGGER.info("Loading annotation file...")
    with open(self.json_file, "r") as f:
        annotations = json.load(f)
    images = {f'{x["id"]:d}': x for x in annotations["images"]}
    imgToAnns = defaultdict(list)
    for ann in annotations["annotations"]:
        imgToAnns[ann["image_id"]].append(ann)
    for img_id, anns in TQDM(imgToAnns.items(), desc=f"Reading annotations {self.json_file}"):
        img = images[f"{img_id:d}"]
        h, w, f = img["height"], img["width"], img["file_name"]
        im_file = Path(self.img_path) / f
        if not im_file.exists():
            continue
        self.im_files.append(str(im_file))
        bboxes = []
        cat2id = {}
        texts = []
        for ann in anns:
            if ann["iscrowd"]:
                continue
            box = np.array(ann["bbox"], dtype=np.float32)
            box[:2] += box[2:] / 2
            box[[0, 2]] /= float(w)
            box[[1, 3]] /= float(h)
            if box[2] <= 0 or box[3] <= 0:
                continue

            cat_name = " ".join([img["caption"][t[0] : t[1]] for t in ann["tokens_positive"]])
            if cat_name not in cat2id:
                cat2id[cat_name] = len(cat2id)
                texts.append([cat_name])
            cls = cat2id[cat_name]  # class
            box = [cls] + box.tolist()
            if box not in bboxes:
                bboxes.append(box)
        lb = np.array(bboxes, dtype=np.float32) if len(bboxes) else np.zeros((0, 5), dtype=np.float32)
        labels.append(
            {
                "im_file": im_file,
                "shape": (h, w),
                "cls": lb[:, 0:1],  # n, 1
                "bboxes": lb[:, 1:],  # n, 4
                "normalized": True,
                "bbox_format": "xywh",
                "texts": texts,
            }
        )
    return labels



ultralytics.data.dataset.YOLOConcatDataset

قواعد: ConcatDataset

مجموعة البيانات كسلسلة من مجموعات بيانات متعددة.

هذه الفئة مفيدة لتجميع مجموعات البيانات المختلفة الموجودة.

شفرة المصدر في ultralytics/data/dataset.py
class YOLOConcatDataset(ConcatDataset):
    """
    Dataset as a concatenation of multiple datasets.

    This class is useful to assemble different existing datasets.
    """

    @staticmethod
    def collate_fn(batch):
        """Collates data samples into batches."""
        return YOLODataset.collate_fn(batch)

collate_fn(batch) staticmethod

يجمع عينات البيانات على دفعات.

شفرة المصدر في ultralytics/data/dataset.py
@staticmethod
def collate_fn(batch):
    """Collates data samples into batches."""
    return YOLODataset.collate_fn(batch)



ultralytics.data.dataset.SemanticDataset

قواعد: BaseDataset

مجموعة بيانات التجزئة الدلالية.

هذه الفئة مسؤولة عن معالجة مجموعات البيانات المستخدمة لمهام التجزئة الدلالية. يرث الوظائف من فئة مجموعة البيانات الأساسية.

ملاحظه

هذه الفئة حاليا عنصر نائب وتحتاج إلى ملئها بأساليب وسمات للدعم مهام التجزئة الدلالية.

شفرة المصدر في ultralytics/data/dataset.py
class SemanticDataset(BaseDataset):
    """
    Semantic Segmentation Dataset.

    This class is responsible for handling datasets used for semantic segmentation tasks. It inherits functionalities
    from the BaseDataset class.

    Note:
        This class is currently a placeholder and needs to be populated with methods and attributes for supporting
        semantic segmentation tasks.
    """

    def __init__(self):
        """Initialize a SemanticDataset object."""
        super().__init__()

__init__()

تهيئة كائن SemanticDataset.

شفرة المصدر في ultralytics/data/dataset.py
def __init__(self):
    """Initialize a SemanticDataset object."""
    super().__init__()



ultralytics.data.dataset.ClassificationDataset

يوسع مجلد صورة الشعلة لدعم YOLO مهام التصنيف ، وتقديم وظائف مثل الصورة التعزيز والتخزين المؤقت والتحقق. إنه مصمم للتعامل بكفاءة مع مجموعات البيانات الكبيرة للتدريب العميق نماذج التعلم ، مع تحويلات الصور الاختيارية وآليات التخزين المؤقت لتسريع التدريب.

يسمح هذا الفصل بالتعزيزات باستخدام كل من مكتبات torchvision و Albumentations ، ويدعم التخزين المؤقت للصور في ذاكرة الوصول العشوائي أو على القرص لتقليل الحمل IO أثناء التدريب. بالإضافة إلى ذلك ، فإنه ينفذ عملية تحقق قوية لضمان سلامة البيانات واتساقها.

سمات:

اسم نوع وصف
cache_ram bool

يشير إلى ما إذا كان التخزين المؤقت في ذاكرة الوصول العشوائي ممكنا.

cache_disk bool

يشير إلى ما إذا كان التخزين المؤقت على القرص ممكنا.

samples list

قائمة بالمجموعات ، يحتوي كل منها على المسار إلى صورة ، وفهرس الفئة الخاص بها ، والمسار إلى ذاكرة التخزين المؤقت .npy الخاصة بها (في حالة التخزين المؤقت على القرص) ، واختياريا صفيف الصور المحملة (في حالة التخزين المؤقت في ذاكرة الوصول العشوائي).

torch_transforms callable

PyTorch التحويلات ليتم تطبيقها على الصور.

شفرة المصدر في ultralytics/data/dataset.py
class ClassificationDataset:
    """
    Extends torchvision ImageFolder to support YOLO classification tasks, offering functionalities like image
    augmentation, caching, and verification. It's designed to efficiently handle large datasets for training deep
    learning models, with optional image transformations and caching mechanisms to speed up training.

    This class allows for augmentations using both torchvision and Albumentations libraries, and supports caching images
    in RAM or on disk to reduce IO overhead during training. Additionally, it implements a robust verification process
    to ensure data integrity and consistency.

    Attributes:
        cache_ram (bool): Indicates if caching in RAM is enabled.
        cache_disk (bool): Indicates if caching on disk is enabled.
        samples (list): A list of tuples, each containing the path to an image, its class index, path to its .npy cache
                        file (if caching on disk), and optionally the loaded image array (if caching in RAM).
        torch_transforms (callable): PyTorch transforms to be applied to the images.
    """

    def __init__(self, root, args, augment=False, prefix=""):
        """
        Initialize YOLO object with root, image size, augmentations, and cache settings.

        Args:
            root (str): Path to the dataset directory where images are stored in a class-specific folder structure.
            args (Namespace): Configuration containing dataset-related settings such as image size, augmentation
                parameters, and cache settings. It includes attributes like `imgsz` (image size), `fraction` (fraction
                of data to use), `scale`, `fliplr`, `flipud`, `cache` (disk or RAM caching for faster training),
                `auto_augment`, `hsv_h`, `hsv_s`, `hsv_v`, and `crop_fraction`.
            augment (bool, optional): Whether to apply augmentations to the dataset. Default is False.
            prefix (str, optional): Prefix for logging and cache filenames, aiding in dataset identification and
                debugging. Default is an empty string.
        """
        import torchvision  # scope for faster 'import ultralytics'

        # Base class assigned as attribute rather than used as base class to allow for scoping slow torchvision import
        self.base = torchvision.datasets.ImageFolder(root=root)
        self.samples = self.base.samples
        self.root = self.base.root

        # Initialize attributes
        if augment and args.fraction < 1.0:  # reduce training fraction
            self.samples = self.samples[: round(len(self.samples) * args.fraction)]
        self.prefix = colorstr(f"{prefix}: ") if prefix else ""
        self.cache_ram = args.cache is True or str(args.cache).lower() == "ram"  # cache images into RAM
        self.cache_disk = str(args.cache).lower() == "disk"  # cache images on hard drive as uncompressed *.npy files
        self.samples = self.verify_images()  # filter out bad images
        self.samples = [list(x) + [Path(x[0]).with_suffix(".npy"), None] for x in self.samples]  # file, index, npy, im
        scale = (1.0 - args.scale, 1.0)  # (0.08, 1.0)
        self.torch_transforms = (
            classify_augmentations(
                size=args.imgsz,
                scale=scale,
                hflip=args.fliplr,
                vflip=args.flipud,
                erasing=args.erasing,
                auto_augment=args.auto_augment,
                hsv_h=args.hsv_h,
                hsv_s=args.hsv_s,
                hsv_v=args.hsv_v,
            )
            if augment
            else classify_transforms(size=args.imgsz, crop_fraction=args.crop_fraction)
        )

    def __getitem__(self, i):
        """Returns subset of data and targets corresponding to given indices."""
        f, j, fn, im = self.samples[i]  # filename, index, filename.with_suffix('.npy'), image
        if self.cache_ram:
            if im is None:  # Warning: two separate if statements required here, do not combine this with previous line
                im = self.samples[i][3] = cv2.imread(f)
        elif self.cache_disk:
            if not fn.exists():  # load npy
                np.save(fn.as_posix(), cv2.imread(f), allow_pickle=False)
            im = np.load(fn)
        else:  # read image
            im = cv2.imread(f)  # BGR
        # Convert NumPy array to PIL image
        im = Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))
        sample = self.torch_transforms(im)
        return {"img": sample, "cls": j}

    def __len__(self) -> int:
        """Return the total number of samples in the dataset."""
        return len(self.samples)

    def verify_images(self):
        """Verify all images in dataset."""
        desc = f"{self.prefix}Scanning {self.root}..."
        path = Path(self.root).with_suffix(".cache")  # *.cache file path

        with contextlib.suppress(FileNotFoundError, AssertionError, AttributeError):
            cache = load_dataset_cache_file(path)  # attempt to load a *.cache file
            assert cache["version"] == DATASET_CACHE_VERSION  # matches current version
            assert cache["hash"] == get_hash([x[0] for x in self.samples])  # identical hash
            nf, nc, n, samples = cache.pop("results")  # found, missing, empty, corrupt, total
            if LOCAL_RANK in {-1, 0}:
                d = f"{desc} {nf} images, {nc} corrupt"
                TQDM(None, desc=d, total=n, initial=n)
                if cache["msgs"]:
                    LOGGER.info("\n".join(cache["msgs"]))  # display warnings
            return samples

        # Run scan if *.cache retrieval failed
        nf, nc, msgs, samples, x = 0, 0, [], [], {}
        with ThreadPool(NUM_THREADS) as pool:
            results = pool.imap(func=verify_image, iterable=zip(self.samples, repeat(self.prefix)))
            pbar = TQDM(results, desc=desc, total=len(self.samples))
            for sample, nf_f, nc_f, msg in pbar:
                if nf_f:
                    samples.append(sample)
                if msg:
                    msgs.append(msg)
                nf += nf_f
                nc += nc_f
                pbar.desc = f"{desc} {nf} images, {nc} corrupt"
            pbar.close()
        if msgs:
            LOGGER.info("\n".join(msgs))
        x["hash"] = get_hash([x[0] for x in self.samples])
        x["results"] = nf, nc, len(samples), samples
        x["msgs"] = msgs  # warnings
        save_dataset_cache_file(self.prefix, path, x, DATASET_CACHE_VERSION)
        return samples

__getitem__(i)

إرجاع مجموعة فرعية من البيانات والأهداف المقابلة لمؤشرات معينة.

شفرة المصدر في ultralytics/data/dataset.py
def __getitem__(self, i):
    """Returns subset of data and targets corresponding to given indices."""
    f, j, fn, im = self.samples[i]  # filename, index, filename.with_suffix('.npy'), image
    if self.cache_ram:
        if im is None:  # Warning: two separate if statements required here, do not combine this with previous line
            im = self.samples[i][3] = cv2.imread(f)
    elif self.cache_disk:
        if not fn.exists():  # load npy
            np.save(fn.as_posix(), cv2.imread(f), allow_pickle=False)
        im = np.load(fn)
    else:  # read image
        im = cv2.imread(f)  # BGR
    # Convert NumPy array to PIL image
    im = Image.fromarray(cv2.cvtColor(im, cv2.COLOR_BGR2RGB))
    sample = self.torch_transforms(im)
    return {"img": sample, "cls": j}

__init__(root, args, augment=False, prefix='')

تهيئه YOLO كائن مع الجذر وحجم الصورة والتعزيزات وإعدادات ذاكرة التخزين المؤقت.

البارامترات:

اسم نوع وصف افتراضي
root str

المسار إلى دليل مجموعة البيانات حيث يتم تخزين الصور في بنية مجلد خاصة بالفئة.

مطلوب
args Namespace

التكوين الذي يحتوي على الإعدادات المتعلقة بمجموعة البيانات مثل حجم الصورة وزيادة المعلمات ، وإعدادات ذاكرة التخزين المؤقت. يتضمن سمات مثل imgsz (حجم الصورة) ، fraction (جزء من البيانات المراد استخدامها) ، scale, fliplr, flipud, cache (التخزين المؤقت للقرص أو ذاكرة الوصول العشوائي لتدريب أسرع) ، auto_augment, hsv_h, hsv_s, hsv_vو crop_fraction.

مطلوب
augment bool

ما إذا كان سيتم تطبيق التعزيزات على مجموعة البيانات. الافتراضي هو خطأ.

False
prefix str

بادئة لتسجيل أسماء ملفات التخزين المؤقت والتخزين المؤقت ، مما يساعد في تحديد مجموعة البيانات و تصحيح. الافتراضي هو سلسلة فارغة.

''
شفرة المصدر في ultralytics/data/dataset.py
def __init__(self, root, args, augment=False, prefix=""):
    """
    Initialize YOLO object with root, image size, augmentations, and cache settings.

    Args:
        root (str): Path to the dataset directory where images are stored in a class-specific folder structure.
        args (Namespace): Configuration containing dataset-related settings such as image size, augmentation
            parameters, and cache settings. It includes attributes like `imgsz` (image size), `fraction` (fraction
            of data to use), `scale`, `fliplr`, `flipud`, `cache` (disk or RAM caching for faster training),
            `auto_augment`, `hsv_h`, `hsv_s`, `hsv_v`, and `crop_fraction`.
        augment (bool, optional): Whether to apply augmentations to the dataset. Default is False.
        prefix (str, optional): Prefix for logging and cache filenames, aiding in dataset identification and
            debugging. Default is an empty string.
    """
    import torchvision  # scope for faster 'import ultralytics'

    # Base class assigned as attribute rather than used as base class to allow for scoping slow torchvision import
    self.base = torchvision.datasets.ImageFolder(root=root)
    self.samples = self.base.samples
    self.root = self.base.root

    # Initialize attributes
    if augment and args.fraction < 1.0:  # reduce training fraction
        self.samples = self.samples[: round(len(self.samples) * args.fraction)]
    self.prefix = colorstr(f"{prefix}: ") if prefix else ""
    self.cache_ram = args.cache is True or str(args.cache).lower() == "ram"  # cache images into RAM
    self.cache_disk = str(args.cache).lower() == "disk"  # cache images on hard drive as uncompressed *.npy files
    self.samples = self.verify_images()  # filter out bad images
    self.samples = [list(x) + [Path(x[0]).with_suffix(".npy"), None] for x in self.samples]  # file, index, npy, im
    scale = (1.0 - args.scale, 1.0)  # (0.08, 1.0)
    self.torch_transforms = (
        classify_augmentations(
            size=args.imgsz,
            scale=scale,
            hflip=args.fliplr,
            vflip=args.flipud,
            erasing=args.erasing,
            auto_augment=args.auto_augment,
            hsv_h=args.hsv_h,
            hsv_s=args.hsv_s,
            hsv_v=args.hsv_v,
        )
        if augment
        else classify_transforms(size=args.imgsz, crop_fraction=args.crop_fraction)
    )

__len__()

إرجاع العدد الإجمالي للعينات في مجموعة البيانات.

شفرة المصدر في ultralytics/data/dataset.py
def __len__(self) -> int:
    """Return the total number of samples in the dataset."""
    return len(self.samples)

verify_images()

تحقق من جميع الصور في مجموعة البيانات.

شفرة المصدر في ultralytics/data/dataset.py
def verify_images(self):
    """Verify all images in dataset."""
    desc = f"{self.prefix}Scanning {self.root}..."
    path = Path(self.root).with_suffix(".cache")  # *.cache file path

    with contextlib.suppress(FileNotFoundError, AssertionError, AttributeError):
        cache = load_dataset_cache_file(path)  # attempt to load a *.cache file
        assert cache["version"] == DATASET_CACHE_VERSION  # matches current version
        assert cache["hash"] == get_hash([x[0] for x in self.samples])  # identical hash
        nf, nc, n, samples = cache.pop("results")  # found, missing, empty, corrupt, total
        if LOCAL_RANK in {-1, 0}:
            d = f"{desc} {nf} images, {nc} corrupt"
            TQDM(None, desc=d, total=n, initial=n)
            if cache["msgs"]:
                LOGGER.info("\n".join(cache["msgs"]))  # display warnings
        return samples

    # Run scan if *.cache retrieval failed
    nf, nc, msgs, samples, x = 0, 0, [], [], {}
    with ThreadPool(NUM_THREADS) as pool:
        results = pool.imap(func=verify_image, iterable=zip(self.samples, repeat(self.prefix)))
        pbar = TQDM(results, desc=desc, total=len(self.samples))
        for sample, nf_f, nc_f, msg in pbar:
            if nf_f:
                samples.append(sample)
            if msg:
                msgs.append(msg)
            nf += nf_f
            nc += nc_f
            pbar.desc = f"{desc} {nf} images, {nc} corrupt"
        pbar.close()
    if msgs:
        LOGGER.info("\n".join(msgs))
    x["hash"] = get_hash([x[0] for x in self.samples])
    x["results"] = nf, nc, len(samples), samples
    x["msgs"] = msgs  # warnings
    save_dataset_cache_file(self.prefix, path, x, DATASET_CACHE_VERSION)
    return samples





Created 2023-11-12, Updated 2024-06-02
Authors: glenn-jocher (6), Burhan-Q (1), Laughing-q (1)