सामग्री पर जाएं

के लिए संदर्भ ultralytics/data/base.py

नोट

यह फ़ाइल यहाँ उपलब्ध है https://github.com/ultralytics/ultralytics/बूँद/मुख्य/ultralytics/data/base.py का उपयोग करें। यदि आप कोई समस्या देखते हैं तो कृपया पुल अनुरोध का योगदान करके इसे ठीक करने में मदद करें 🛠️। 🙏 धन्यवाद !



ultralytics.data.base.BaseDataset

का रूप: Dataset

छवि डेटा लोड करने और संसाधित करने के लिए बेस डेटासेट क्लास।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
img_path str

छवियों वाले फ़ोल्डर का पथ।

आवश्यक
imgsz int

छवि का आकार। 640 के लिए डिफ़ॉल्ट।

640
cache bool

प्रशिक्षण के दौरान RAM या डिस्क पर छवियों को कैश करें। डिफ़ॉल्ट रूप से गलत है.

False
augment bool

यदि सही है, तो डेटा वृद्धि लागू की जाती है। सही करने के लिए डिफ़ॉल्ट।

True
hyp dict

डेटा वृद्धि लागू करने के लिए हाइपरपैरामीटर। कोई नहीं करने के लिए डिफ़ॉल्ट।

DEFAULT_CFG
prefix str

लॉग संदेशों में प्रिंट करने के लिए उपसर्ग। '' के लिए डिफ़ॉल्ट।

''
rect bool

यदि सच है, तो आयताकार प्रशिक्षण का उपयोग किया जाता है। डिफ़ॉल्ट रूप से गलत है.

False
batch_size int

बैचों का आकार। कोई नहीं करने के लिए डिफ़ॉल्ट।

16
stride int

डग। 32 के लिए डिफ़ॉल्ट।

32
pad float

गद्दी। 0.0 के लिए डिफ़ॉल्ट।

0.5
single_cls bool

यदि सच है, तो एकल वर्ग प्रशिक्षण का उपयोग किया जाता है। डिफ़ॉल्ट रूप से गलत है.

False
classes list

शामिल वर्गों की सूची। डिफ़ॉल्ट कोई नहीं है।

None
fraction float

उपयोग करने के लिए डेटासेट का अंश। डिफ़ॉल्ट 1.0 है (सभी डेटा का उपयोग करें)।

1.0

विशेषताएँ:

नाम प्रकार विवरण: __________
im_files list

छवि फ़ाइल पथों की सूची।

labels list

लेबल डेटा शब्दकोशों की सूची।

ni int

डेटासेट में छवियों की संख्या।

ims list

लोड की गई छवियों की सूची।

npy_files list

सुन्न फ़ाइल पथों की सूची।

transforms callable

छवि परिवर्तन समारोह।

में स्रोत कोड ultralytics/data/base.py
class BaseDataset(Dataset):
    """
    Base dataset class for loading and processing image data.

    Args:
        img_path (str): Path to the folder containing images.
        imgsz (int, optional): Image size. Defaults to 640.
        cache (bool, optional): Cache images to RAM or disk during training. Defaults to False.
        augment (bool, optional): If True, data augmentation is applied. Defaults to True.
        hyp (dict, optional): Hyperparameters to apply data augmentation. Defaults to None.
        prefix (str, optional): Prefix to print in log messages. Defaults to ''.
        rect (bool, optional): If True, rectangular training is used. Defaults to False.
        batch_size (int, optional): Size of batches. Defaults to None.
        stride (int, optional): Stride. Defaults to 32.
        pad (float, optional): Padding. Defaults to 0.0.
        single_cls (bool, optional): If True, single class training is used. Defaults to False.
        classes (list): List of included classes. Default is None.
        fraction (float): Fraction of dataset to utilize. Default is 1.0 (use all data).

    Attributes:
        im_files (list): List of image file paths.
        labels (list): List of label data dictionaries.
        ni (int): Number of images in the dataset.
        ims (list): List of loaded images.
        npy_files (list): List of numpy file paths.
        transforms (callable): Image transformation function.
    """

    def __init__(
        self,
        img_path,
        imgsz=640,
        cache=False,
        augment=True,
        hyp=DEFAULT_CFG,
        prefix="",
        rect=False,
        batch_size=16,
        stride=32,
        pad=0.5,
        single_cls=False,
        classes=None,
        fraction=1.0,
    ):
        """Initialize BaseDataset with given configuration and options."""
        super().__init__()
        self.img_path = img_path
        self.imgsz = imgsz
        self.augment = augment
        self.single_cls = single_cls
        self.prefix = prefix
        self.fraction = fraction
        self.im_files = self.get_img_files(self.img_path)
        self.labels = self.get_labels()
        self.update_labels(include_class=classes)  # single_cls and include_class
        self.ni = len(self.labels)  # number of images
        self.rect = rect
        self.batch_size = batch_size
        self.stride = stride
        self.pad = pad
        if self.rect:
            assert self.batch_size is not None
            self.set_rectangle()

        # Buffer thread for mosaic images
        self.buffer = []  # buffer size = batch size
        self.max_buffer_length = min((self.ni, self.batch_size * 8, 1000)) if self.augment else 0

        # Cache images
        if cache == "ram" and not self.check_cache_ram():
            cache = False
        self.ims, self.im_hw0, self.im_hw = [None] * self.ni, [None] * self.ni, [None] * self.ni
        self.npy_files = [Path(f).with_suffix(".npy") for f in self.im_files]
        if cache:
            self.cache_images(cache)

        # Transforms
        self.transforms = self.build_transforms(hyp=hyp)

    def get_img_files(self, img_path):
        """Read image files."""
        try:
            f = []  # image files
            for p in img_path if isinstance(img_path, list) else [img_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) if x.startswith("./") else x for x in t]  # local to global path
                        # F += [p.parent / x.lstrip(os.sep) for x in t]  # local to global path (pathlib)
                else:
                    raise FileNotFoundError(f"{self.prefix}{p} does not exist")
            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 im_files, f"{self.prefix}No images found in {img_path}"
        except Exception as e:
            raise FileNotFoundError(f"{self.prefix}Error loading data from {img_path}\n{HELP_URL}") from e
        if self.fraction < 1:
            im_files = im_files[: round(len(im_files) * self.fraction)]
        return im_files

    def update_labels(self, include_class: Optional[list]):
        """Update labels to include only these classes (optional)."""
        include_class_array = np.array(include_class).reshape(1, -1)
        for i in range(len(self.labels)):
            if include_class is not None:
                cls = self.labels[i]["cls"]
                bboxes = self.labels[i]["bboxes"]
                segments = self.labels[i]["segments"]
                keypoints = self.labels[i]["keypoints"]
                j = (cls == include_class_array).any(1)
                self.labels[i]["cls"] = cls[j]
                self.labels[i]["bboxes"] = bboxes[j]
                if segments:
                    self.labels[i]["segments"] = [segments[si] for si, idx in enumerate(j) if idx]
                if keypoints is not None:
                    self.labels[i]["keypoints"] = keypoints[j]
            if self.single_cls:
                self.labels[i]["cls"][:, 0] = 0

    def load_image(self, i, rect_mode=True):
        """Loads 1 image from dataset index 'i', returns (im, 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
                try:
                    im = np.load(fn)
                except Exception as e:
                    LOGGER.warning(f"{self.prefix}WARNING ⚠️ Removing corrupt *.npy image file {fn} due to: {e}")
                    Path(fn).unlink(missing_ok=True)
                    im = cv2.imread(f)  # BGR
            else:  # read image
                im = cv2.imread(f)  # BGR
            if im is None:
                raise FileNotFoundError(f"Image Not Found {f}")

            h0, w0 = im.shape[:2]  # orig hw
            if rect_mode:  # resize long side to imgsz while maintaining aspect ratio
                r = self.imgsz / max(h0, w0)  # ratio
                if r != 1:  # if sizes are not equal
                    w, h = (min(math.ceil(w0 * r), self.imgsz), min(math.ceil(h0 * r), self.imgsz))
                    im = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
            elif not (h0 == w0 == self.imgsz):  # resize by stretching image to square imgsz
                im = cv2.resize(im, (self.imgsz, self.imgsz), interpolation=cv2.INTER_LINEAR)

            # Add to buffer if training with augmentations
            if self.augment:
                self.ims[i], self.im_hw0[i], self.im_hw[i] = im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
                self.buffer.append(i)
                if len(self.buffer) >= self.max_buffer_length:
                    j = self.buffer.pop(0)
                    self.ims[j], self.im_hw0[j], self.im_hw[j] = None, None, None

            return im, (h0, w0), im.shape[:2]

        return self.ims[i], self.im_hw0[i], self.im_hw[i]

    def cache_images(self, cache):
        """Cache images to memory or disk."""
        b, gb = 0, 1 << 30  # bytes of cached images, bytes per gigabytes
        fcn = self.cache_images_to_disk if cache == "disk" else self.load_image
        with ThreadPool(NUM_THREADS) as pool:
            results = pool.imap(fcn, range(self.ni))
            pbar = TQDM(enumerate(results), total=self.ni, disable=LOCAL_RANK > 0)
            for i, x in pbar:
                if cache == "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"{self.prefix}Caching images ({b / gb:.1f}GB {cache})"
            pbar.close()

    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]), allow_pickle=False)

    def check_cache_ram(self, safety_margin=0.5):
        """Check image caching requirements vs available memory."""
        b, gb = 0, 1 << 30  # bytes of cached images, bytes per gigabytes
        n = min(self.ni, 30)  # extrapolate from 30 random images
        for _ in range(n):
            im = cv2.imread(random.choice(self.im_files))  # sample image
            ratio = self.imgsz / max(im.shape[0], im.shape[1])  # max(h, w)  # ratio
            b += im.nbytes * ratio**2
        mem_required = b * self.ni / n * (1 + safety_margin)  # GB required to cache dataset into RAM
        mem = psutil.virtual_memory()
        cache = mem_required < mem.available  # to cache or not to cache, that is the question
        if not cache:
            LOGGER.info(
                f'{self.prefix}{mem_required / gb:.1f}GB RAM required to cache images '
                f'with {int(safety_margin * 100)}% safety margin but only '
                f'{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, '
                f"{'caching images ✅' if cache else 'not caching images ⚠️'}"
            )
        return cache

    def set_rectangle(self):
        """Sets the shape of bounding boxes for YOLO detections as rectangles."""
        bi = np.floor(np.arange(self.ni) / self.batch_size).astype(int)  # batch index
        nb = bi[-1] + 1  # number of batches

        s = np.array([x.pop("shape") for x in self.labels])  # hw
        ar = s[:, 0] / s[:, 1]  # aspect ratio
        irect = ar.argsort()
        self.im_files = [self.im_files[i] for i in irect]
        self.labels = [self.labels[i] for i in irect]
        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) * self.imgsz / self.stride + self.pad).astype(int) * self.stride
        self.batch = bi  # batch index of image

    def __getitem__(self, index):
        """Returns transformed label information for given index."""
        return self.transforms(self.get_image_and_label(index))

    def get_image_and_label(self, index):
        """Get and return label information from the dataset."""
        label = deepcopy(self.labels[index])  # requires deepcopy() https://github.com/ultralytics/ultralytics/pull/1948
        label.pop("shape", None)  # shape is for rect, remove it
        label["img"], label["ori_shape"], label["resized_shape"] = self.load_image(index)
        label["ratio_pad"] = (
            label["resized_shape"][0] / label["ori_shape"][0],
            label["resized_shape"][1] / label["ori_shape"][1],
        )  # for evaluation
        if self.rect:
            label["rect_shape"] = self.batch_shapes[self.batch[index]]
        return self.update_labels_info(label)

    def __len__(self):
        """Returns the length of the labels list for the dataset."""
        return len(self.labels)

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

    def build_transforms(self, hyp=None):
        """
        Users can customize augmentations here.

        Example:
            ```python
            if self.augment:
                # Training transforms
                return Compose([])
            else:
                # Val transforms
                return Compose([])
            ```
        """
        raise NotImplementedError

    def get_labels(self):
        """
        Users can customize their own format here.

        Note:
            Ensure output is a dictionary with the following keys:
            ```python
            dict(
                im_file=im_file,
                shape=shape,  # format: (height, width)
                cls=cls,
                bboxes=bboxes, # xywh
                segments=segments,  # xy
                keypoints=keypoints, # xy
                normalized=True, # or False
                bbox_format="xyxy",  # or xywh, ltwh
            )
            ```
        """
        raise NotImplementedError

__getitem__(index)

दिए गए सूचकांक के लिए लेबल जानकारी को बदल देता है।

में स्रोत कोड ultralytics/data/base.py
def __getitem__(self, index):
    """Returns transformed label information for given index."""
    return self.transforms(self.get_image_and_label(index))

__init__(img_path, imgsz=640, cache=False, augment=True, hyp=DEFAULT_CFG, prefix='', rect=False, batch_size=16, stride=32, pad=0.5, single_cls=False, classes=None, fraction=1.0)

दिए गए कॉन्फ़िगरेशन और विकल्पों के साथ BaseDataset को प्रारंभ करें।

में स्रोत कोड ultralytics/data/base.py
49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 747576777879808182 83 84 85 86 87 88 899091929394 95969798
def __init__(
    self,
    img_path,
    imgsz=640,
    cache=False,
    augment=True,
    hyp=DEFAULT_CFG,
    prefix="",
    rect=False,
    batch_size=16,
    stride=32,
    pad=0.5,
    single_cls=False,
    classes=None,
    fraction=1.0,
):
    """Initialize BaseDataset with given configuration and options."""
    super().__init__()
    self.img_path = img_path
    self.imgsz = imgsz
    self.augment = augment
    self.single_cls = single_cls
    self.prefix = prefix
    self.fraction = fraction
    self.im_files = self.get_img_files(self.img_path)
    self.labels = self.get_labels()
    self.update_labels(include_class=classes)  # single_cls and include_class
    self.ni = len(self.labels)  # number of images
    self.rect = rect
    self.batch_size = batch_size
    self.stride = stride
    self.pad = pad
    if self.rect:
        assert self.batch_size is not None
        self.set_rectangle()

    # Buffer thread for mosaic images
    self.buffer = []  # buffer size = batch size
    self.max_buffer_length = min((self.ni, self.batch_size * 8, 1000)) if self.augment else 0

    # Cache images
    if cache == "ram" and not self.check_cache_ram():
        cache = False
    self.ims, self.im_hw0, self.im_hw = [None] * self.ni, [None] * self.ni, [None] * self.ni
    self.npy_files = [Path(f).with_suffix(".npy") for f in self.im_files]
    if cache:
        self.cache_images(cache)

    # Transforms
    self.transforms = self.build_transforms(hyp=hyp)

__len__()

डेटासेट के लिए लेबल सूची की लंबाई लौटाता है।

में स्रोत कोड ultralytics/data/base.py
def __len__(self):
    """Returns the length of the labels list for the dataset."""
    return len(self.labels)

build_transforms(hyp=None)

उपयोगकर्ता यहां वृद्धि को अनुकूलित कर सकते हैं।

उदाहरण
if self.augment:
    # Training transforms
    return Compose([])
else:
    # Val transforms
    return Compose([])
में स्रोत कोड ultralytics/data/base.py
274 275 276 277 278 279 280 281 282 283 284 285 286287288
def build_transforms(self, hyp=None):
    """
    Users can customize augmentations here.

    Example:
        ```python
        if self.augment:
            # Training transforms
            return Compose([])
        else:
            # Val transforms
            return Compose([])
        ```
    """
    raise NotImplementedError

cache_images(cache)

मेमोरी या डिस्क पर छवियों को कैश करें।

में स्रोत कोड ultralytics/data/base.py
182 183 184 185 186 187 188 189 190 191 192 193 194195196
def cache_images(self, cache):
    """Cache images to memory or disk."""
    b, gb = 0, 1 << 30  # bytes of cached images, bytes per gigabytes
    fcn = self.cache_images_to_disk if cache == "disk" else self.load_image
    with ThreadPool(NUM_THREADS) as pool:
        results = pool.imap(fcn, range(self.ni))
        pbar = TQDM(enumerate(results), total=self.ni, disable=LOCAL_RANK > 0)
        for i, x in pbar:
            if cache == "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"{self.prefix}Caching images ({b / gb:.1f}GB {cache})"
        pbar.close()

cache_images_to_disk(i)

तेजी से लोड करने के लिए एक *.npy फ़ाइल के रूप में एक छवि सहेजता है।

में स्रोत कोड ultralytics/data/base.py
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]), allow_pickle=False)

check_cache_ram(safety_margin=0.5)

छवि कैशिंग आवश्यकताओं बनाम उपलब्ध स्मृति की जाँच करें।

में स्रोत कोड ultralytics/data/base.py
204 205 206 207 208209 210 211 212 213 214 215 216 217 218 219 220221 222
def check_cache_ram(self, safety_margin=0.5):
    """Check image caching requirements vs available memory."""
    b, gb = 0, 1 << 30  # bytes of cached images, bytes per gigabytes
    n = min(self.ni, 30)  # extrapolate from 30 random images
    for _ in range(n):
        im = cv2.imread(random.choice(self.im_files))  # sample image
        ratio = self.imgsz / max(im.shape[0], im.shape[1])  # max(h, w)  # ratio
        b += im.nbytes * ratio**2
    mem_required = b * self.ni / n * (1 + safety_margin)  # GB required to cache dataset into RAM
    mem = psutil.virtual_memory()
    cache = mem_required < mem.available  # to cache or not to cache, that is the question
    if not cache:
        LOGGER.info(
            f'{self.prefix}{mem_required / gb:.1f}GB RAM required to cache images '
            f'with {int(safety_margin * 100)}% safety margin but only '
            f'{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, '
            f"{'caching images ✅' if cache else 'not caching images ⚠️'}"
        )
    return cache

get_image_and_label(index)

डेटासेट से लेबल जानकारी प्राप्त करें और लौटाएं।

में स्रोत कोड ultralytics/data/base.py
253 254 255 256 257 258259 260 261 262 263264
def get_image_and_label(self, index):
    """Get and return label information from the dataset."""
    label = deepcopy(self.labels[index])  # requires deepcopy() https://github.com/ultralytics/ultralytics/pull/1948
    label.pop("shape", None)  # shape is for rect, remove it
    label["img"], label["ori_shape"], label["resized_shape"] = self.load_image(index)
    label["ratio_pad"] = (
        label["resized_shape"][0] / label["ori_shape"][0],
        label["resized_shape"][1] / label["ori_shape"][1],
    )  # for evaluation
    if self.rect:
        label["rect_shape"] = self.batch_shapes[self.batch[index]]
    return self.update_labels_info(label)

get_img_files(img_path)

छवि फ़ाइलें पढ़ें।

में स्रोत कोड ultralytics/data/base.py
100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118119 120121 122123 124
def get_img_files(self, img_path):
    """Read image files."""
    try:
        f = []  # image files
        for p in img_path if isinstance(img_path, list) else [img_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) if x.startswith("./") else x for x in t]  # local to global path
                    # F += [p.parent / x.lstrip(os.sep) for x in t]  # local to global path (pathlib)
            else:
                raise FileNotFoundError(f"{self.prefix}{p} does not exist")
        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 im_files, f"{self.prefix}No images found in {img_path}"
    except Exception as e:
        raise FileNotFoundError(f"{self.prefix}Error loading data from {img_path}\n{HELP_URL}") from e
    if self.fraction < 1:
        im_files = im_files[: round(len(im_files) * self.fraction)]
    return im_files

get_labels()

उपयोगकर्ता यहां अपने स्वयं के प्रारूप को अनुकूलित कर सकते हैं।

नोट

सुनिश्चित करें कि आउटपुट निम्नलिखित कुंजियों के साथ एक शब्दकोश है:

dict(
    im_file=im_file,
    shape=shape,  # format: (height, width)
    cls=cls,
    bboxes=bboxes, # xywh
    segments=segments,  # xy
    keypoints=keypoints, # xy
    normalized=True, # or False
    bbox_format="xyxy",  # or xywh, ltwh
)

में स्रोत कोड ultralytics/data/base.py
290 291 292 293 294 295 296 297 298 299300 301 302 303 304 305 306 307308 309
def get_labels(self):
    """
    Users can customize their own format here.

    Note:
        Ensure output is a dictionary with the following keys:
        ```python
        dict(
            im_file=im_file,
            shape=shape,  # format: (height, width)
            cls=cls,
            bboxes=bboxes, # xywh
            segments=segments,  # xy
            keypoints=keypoints, # xy
            normalized=True, # or False
            bbox_format="xyxy",  # or xywh, ltwh
        )
        ```
    """
    raise NotImplementedError

load_image(i, rect_mode=True)

डेटासेट इंडेक्स 'i' से 1 छवि लोड करता है, रिटर्न (im, आकार hw)।

में स्रोत कोड ultralytics/data/base.py
145 146 147 148 149 150 151 152 153 154 155 156 157 158159 160 161 162 163 164 165 166 167 168 169 170171 172 173 174 175 176177178 179180
def load_image(self, i, rect_mode=True):
    """Loads 1 image from dataset index 'i', returns (im, 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
            try:
                im = np.load(fn)
            except Exception as e:
                LOGGER.warning(f"{self.prefix}WARNING ⚠️ Removing corrupt *.npy image file {fn} due to: {e}")
                Path(fn).unlink(missing_ok=True)
                im = cv2.imread(f)  # BGR
        else:  # read image
            im = cv2.imread(f)  # BGR
        if im is None:
            raise FileNotFoundError(f"Image Not Found {f}")

        h0, w0 = im.shape[:2]  # orig hw
        if rect_mode:  # resize long side to imgsz while maintaining aspect ratio
            r = self.imgsz / max(h0, w0)  # ratio
            if r != 1:  # if sizes are not equal
                w, h = (min(math.ceil(w0 * r), self.imgsz), min(math.ceil(h0 * r), self.imgsz))
                im = cv2.resize(im, (w, h), interpolation=cv2.INTER_LINEAR)
        elif not (h0 == w0 == self.imgsz):  # resize by stretching image to square imgsz
            im = cv2.resize(im, (self.imgsz, self.imgsz), interpolation=cv2.INTER_LINEAR)

        # Add to buffer if training with augmentations
        if self.augment:
            self.ims[i], self.im_hw0[i], self.im_hw[i] = im, (h0, w0), im.shape[:2]  # im, hw_original, hw_resized
            self.buffer.append(i)
            if len(self.buffer) >= self.max_buffer_length:
                j = self.buffer.pop(0)
                self.ims[j], self.im_hw0[j], self.im_hw[j] = None, None, None

        return im, (h0, w0), im.shape[:2]

    return self.ims[i], self.im_hw0[i], self.im_hw[i]

set_rectangle()

के लिए बाउंडिंग बॉक्स का आकार सेट करता है YOLO आयतों के रूप में पता लगाता है।

में स्रोत कोड ultralytics/data/base.py
224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240241 242 243 244 245246 247
def set_rectangle(self):
    """Sets the shape of bounding boxes for YOLO detections as rectangles."""
    bi = np.floor(np.arange(self.ni) / self.batch_size).astype(int)  # batch index
    nb = bi[-1] + 1  # number of batches

    s = np.array([x.pop("shape") for x in self.labels])  # hw
    ar = s[:, 0] / s[:, 1]  # aspect ratio
    irect = ar.argsort()
    self.im_files = [self.im_files[i] for i in irect]
    self.labels = [self.labels[i] for i in irect]
    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) * self.imgsz / self.stride + self.pad).astype(int) * self.stride
    self.batch = bi  # batch index of image

update_labels(include_class)

केवल इन वर्गों को शामिल करने के लिए लेबल अपडेट करें (वैकल्पिक)।

में स्रोत कोड ultralytics/data/base.py
 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140141142143
def update_labels(self, include_class: Optional[list]):
    """Update labels to include only these classes (optional)."""
    include_class_array = np.array(include_class).reshape(1, -1)
    for i in range(len(self.labels)):
        if include_class is not None:
            cls = self.labels[i]["cls"]
            bboxes = self.labels[i]["bboxes"]
            segments = self.labels[i]["segments"]
            keypoints = self.labels[i]["keypoints"]
            j = (cls == include_class_array).any(1)
            self.labels[i]["cls"] = cls[j]
            self.labels[i]["bboxes"] = bboxes[j]
            if segments:
                self.labels[i]["segments"] = [segments[si] for si, idx in enumerate(j) if idx]
            if keypoints is not None:
                self.labels[i]["keypoints"] = keypoints[j]
        if self.single_cls:
            self.labels[i]["cls"][:, 0] = 0

update_labels_info(label)

अपने लेबल प्रारूप को यहां अनुकूलित करें।

में स्रोत कोड ultralytics/data/base.py
def update_labels_info(self, label):
    """Custom your label format here."""
    return label





2023-11-12 बनाया गया, अपडेट किया गया 2023-11-25
लेखक: ग्लेन-जोचर (3)