انتقل إلى المحتوى

مرجع ل ultralytics/nn/tasks.py

ملاحظه

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



ultralytics.nn.tasks.BaseModel

قواعد: Module

تعمل فئة BaseModel كفئة أساسية لجميع الطرز في Ultralytics YOLO أسرة.

شفرة المصدر في ultralytics/nn/tasks.py
class BaseModel(nn.Module):
    """The BaseModel class serves as a base class for all the models in the Ultralytics YOLO family."""

    def forward(self, x, *args, **kwargs):
        """
        Forward pass of the model on a single scale. Wrapper for `_forward_once` method.

        Args:
            x (torch.Tensor | dict): The input image tensor or a dict including image tensor and gt labels.

        Returns:
            (torch.Tensor): The output of the network.
        """
        if isinstance(x, dict):  # for cases of training and validating while training.
            return self.loss(x, *args, **kwargs)
        return self.predict(x, *args, **kwargs)

    def predict(self, x, profile=False, visualize=False, augment=False, embed=None):
        """
        Perform a forward pass through the network.

        Args:
            x (torch.Tensor): The input tensor to the model.
            profile (bool):  Print the computation time of each layer if True, defaults to False.
            visualize (bool): Save the feature maps of the model if True, defaults to False.
            augment (bool): Augment image during prediction, defaults to False.
            embed (list, optional): A list of feature vectors/embeddings to return.

        Returns:
            (torch.Tensor): The last output of the model.
        """
        if augment:
            return self._predict_augment(x)
        return self._predict_once(x, profile, visualize, embed)

    def _predict_once(self, x, profile=False, visualize=False, embed=None):
        """
        Perform a forward pass through the network.

        Args:
            x (torch.Tensor): The input tensor to the model.
            profile (bool):  Print the computation time of each layer if True, defaults to False.
            visualize (bool): Save the feature maps of the model if True, defaults to False.
            embed (list, optional): A list of feature vectors/embeddings to return.

        Returns:
            (torch.Tensor): The last output of the model.
        """
        y, dt, embeddings = [], [], []  # outputs
        for m in self.model:
            if m.f != -1:  # if not from previous layer
                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
            if profile:
                self._profile_one_layer(m, x, dt)
            x = m(x)  # run
            y.append(x if m.i in self.save else None)  # save output
            if visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)
            if embed and m.i in embed:
                embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
                if m.i == max(embed):
                    return torch.unbind(torch.cat(embeddings, 1), dim=0)
        return x

    def _predict_augment(self, x):
        """Perform augmentations on input image x and return augmented inference."""
        LOGGER.warning(
            f"WARNING ⚠️ {self.__class__.__name__} does not support augmented inference yet. "
            f"Reverting to single-scale inference instead."
        )
        return self._predict_once(x)

    def _profile_one_layer(self, m, x, dt):
        """
        Profile the computation time and FLOPs of a single layer of the model on a given input. Appends the results to
        the provided list.

        Args:
            m (nn.Module): The layer to be profiled.
            x (torch.Tensor): The input data to the layer.
            dt (list): A list to store the computation time of the layer.

        Returns:
            None
        """
        c = m == self.model[-1] and isinstance(x, list)  # is final layer list, copy input as inplace fix
        flops = thop.profile(m, inputs=[x.copy() if c else x], verbose=False)[0] / 1e9 * 2 if thop else 0  # FLOPs
        t = time_sync()
        for _ in range(10):
            m(x.copy() if c else x)
        dt.append((time_sync() - t) * 100)
        if m == self.model[0]:
            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  module")
        LOGGER.info(f"{dt[-1]:10.2f} {flops:10.2f} {m.np:10.0f}  {m.type}")
        if c:
            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")

    def fuse(self, verbose=True):
        """
        Fuse the `Conv2d()` and `BatchNorm2d()` layers of the model into a single layer, in order to improve the
        computation efficiency.

        Returns:
            (nn.Module): The fused model is returned.
        """
        if not self.is_fused():
            for m in self.model.modules():
                if isinstance(m, (Conv, Conv2, DWConv)) and hasattr(m, "bn"):
                    if isinstance(m, Conv2):
                        m.fuse_convs()
                    m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                    delattr(m, "bn")  # remove batchnorm
                    m.forward = m.forward_fuse  # update forward
                if isinstance(m, ConvTranspose) and hasattr(m, "bn"):
                    m.conv_transpose = fuse_deconv_and_bn(m.conv_transpose, m.bn)
                    delattr(m, "bn")  # remove batchnorm
                    m.forward = m.forward_fuse  # update forward
                if isinstance(m, RepConv):
                    m.fuse_convs()
                    m.forward = m.forward_fuse  # update forward
            self.info(verbose=verbose)

        return self

    def is_fused(self, thresh=10):
        """
        Check if the model has less than a certain threshold of BatchNorm layers.

        Args:
            thresh (int, optional): The threshold number of BatchNorm layers. Default is 10.

        Returns:
            (bool): True if the number of BatchNorm layers in the model is less than the threshold, False otherwise.
        """
        bn = tuple(v for k, v in nn.__dict__.items() if "Norm" in k)  # normalization layers, i.e. BatchNorm2d()
        return sum(isinstance(v, bn) for v in self.modules()) < thresh  # True if < 'thresh' BatchNorm layers in model

    def info(self, detailed=False, verbose=True, imgsz=640):
        """
        Prints model information.

        Args:
            detailed (bool): if True, prints out detailed information about the model. Defaults to False
            verbose (bool): if True, prints out the model information. Defaults to False
            imgsz (int): the size of the image that the model will be trained on. Defaults to 640
        """
        return model_info(self, detailed=detailed, verbose=verbose, imgsz=imgsz)

    def _apply(self, fn):
        """
        Applies a function to all the tensors in the model that are not parameters or registered buffers.

        Args:
            fn (function): the function to apply to the model

        Returns:
            (BaseModel): An updated BaseModel object.
        """
        self = super()._apply(fn)
        m = self.model[-1]  # Detect()
        if isinstance(m, Detect):  # includes all Detect subclasses like Segment, Pose, OBB, WorldDetect
            m.stride = fn(m.stride)
            m.anchors = fn(m.anchors)
            m.strides = fn(m.strides)
        return self

    def load(self, weights, verbose=True):
        """
        Load the weights into the model.

        Args:
            weights (dict | torch.nn.Module): The pre-trained weights to be loaded.
            verbose (bool, optional): Whether to log the transfer progress. Defaults to True.
        """
        model = weights["model"] if isinstance(weights, dict) else weights  # torchvision models are not dicts
        csd = model.float().state_dict()  # checkpoint state_dict as FP32
        csd = intersect_dicts(csd, self.state_dict())  # intersect
        self.load_state_dict(csd, strict=False)  # load
        if verbose:
            LOGGER.info(f"Transferred {len(csd)}/{len(self.model.state_dict())} items from pretrained weights")

    def loss(self, batch, preds=None):
        """
        Compute loss.

        Args:
            batch (dict): Batch to compute loss on
            preds (torch.Tensor | List[torch.Tensor]): Predictions.
        """
        if not hasattr(self, "criterion"):
            self.criterion = self.init_criterion()

        preds = self.forward(batch["img"]) if preds is None else preds
        return self.criterion(preds, batch)

    def init_criterion(self):
        """Initialize the loss criterion for the BaseModel."""
        raise NotImplementedError("compute_loss() needs to be implemented by task heads")

forward(x, *args, **kwargs)

تمرير إلى الأمام من النموذج على مقياس واحد. غلاف ل _forward_once أسلوب.

البارامترات:

اسم نوع وصف افتراضي
x Tensor | dict

صورة الإدخال tensor أو إملاء بما في ذلك الصورة tensor وتسميات GT.

مطلوب

ارجاع:

نوع وصف
Tensor

إخراج الشبكة.

شفرة المصدر في ultralytics/nn/tasks.py
def forward(self, x, *args, **kwargs):
    """
    Forward pass of the model on a single scale. Wrapper for `_forward_once` method.

    Args:
        x (torch.Tensor | dict): The input image tensor or a dict including image tensor and gt labels.

    Returns:
        (torch.Tensor): The output of the network.
    """
    if isinstance(x, dict):  # for cases of training and validating while training.
        return self.loss(x, *args, **kwargs)
    return self.predict(x, *args, **kwargs)

fuse(verbose=True)

دمج Conv2d() و BatchNorm2d() طبقات النموذج في طبقة واحدة ، من أجل تحسين كفاءة الحساب.

ارجاع:

نوع وصف
Module

يتم إرجاع النموذج المنصهر.

شفرة المصدر في ultralytics/nn/tasks.py
165 166 167 168 169 170 171 172 173 174 175 176 177 178179 180 181 182 183 184 185 186187188189190
def fuse(self, verbose=True):
    """
    Fuse the `Conv2d()` and `BatchNorm2d()` layers of the model into a single layer, in order to improve the
    computation efficiency.

    Returns:
        (nn.Module): The fused model is returned.
    """
    if not self.is_fused():
        for m in self.model.modules():
            if isinstance(m, (Conv, Conv2, DWConv)) and hasattr(m, "bn"):
                if isinstance(m, Conv2):
                    m.fuse_convs()
                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                delattr(m, "bn")  # remove batchnorm
                m.forward = m.forward_fuse  # update forward
            if isinstance(m, ConvTranspose) and hasattr(m, "bn"):
                m.conv_transpose = fuse_deconv_and_bn(m.conv_transpose, m.bn)
                delattr(m, "bn")  # remove batchnorm
                m.forward = m.forward_fuse  # update forward
            if isinstance(m, RepConv):
                m.fuse_convs()
                m.forward = m.forward_fuse  # update forward
        self.info(verbose=verbose)

    return self

info(detailed=False, verbose=True, imgsz=640)

يطبع معلومات النموذج.

البارامترات:

اسم نوع وصف افتراضي
detailed bool

إذا كان True ، يطبع معلومات مفصلة حول النموذج. الإعدادات الافتراضية إلى خطأ

False
verbose bool

إذا كان True ، يطبع معلومات النموذج. الإعدادات الافتراضية إلى خطأ

True
imgsz int

حجم الصورة التي سيتم تدريب النموذج عليها. الإعدادات الافتراضية إلى 640

640
شفرة المصدر في ultralytics/nn/tasks.py
205 206 207 208 209 210 211 212 213 214
def info(self, detailed=False, verbose=True, imgsz=640):
    """
    Prints model information.

    Args:
        detailed (bool): if True, prints out detailed information about the model. Defaults to False
        verbose (bool): if True, prints out the model information. Defaults to False
        imgsz (int): the size of the image that the model will be trained on. Defaults to 640
    """
    return model_info(self, detailed=detailed, verbose=verbose, imgsz=imgsz)

init_criterion()

تهيئة معيار الخسارة ل BaseModel.

شفرة المصدر في ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the BaseModel."""
    raise NotImplementedError("compute_loss() needs to be implemented by task heads")

is_fused(thresh=10)

تحقق مما إذا كان النموذج يحتوي على أقل من حد معين من طبقات BatchNorm.

البارامترات:

اسم نوع وصف افتراضي
thresh int

عدد عتبة طبقات BatchNorm. الافتراضي هو 10.

10

ارجاع:

نوع وصف
bool

صحيح إذا كان عدد طبقات BatchNorm في النموذج أقل من الحد ، خطأ خلاف ذلك.

شفرة المصدر في ultralytics/nn/tasks.py
192 193 194 195 196 197 198199 200 201 202203
def is_fused(self, thresh=10):
    """
    Check if the model has less than a certain threshold of BatchNorm layers.

    Args:
        thresh (int, optional): The threshold number of BatchNorm layers. Default is 10.

    Returns:
        (bool): True if the number of BatchNorm layers in the model is less than the threshold, False otherwise.
    """
    bn = tuple(v for k, v in nn.__dict__.items() if "Norm" in k)  # normalization layers, i.e. BatchNorm2d()
    return sum(isinstance(v, bn) for v in self.modules()) < thresh  # True if < 'thresh' BatchNorm layers in model

load(weights, verbose=True)

قم بتحميل الأوزان في النموذج.

البارامترات:

اسم نوع وصف افتراضي
weights dict | Module

الأوزان المدربة مسبقا المراد تحميلها.

مطلوب
verbose bool

ما إذا كنت تريد تسجيل تقدم النقل. الإعدادات الافتراضية إلى صواب.

True
شفرة المصدر في ultralytics/nn/tasks.py
234 235 236 237 238 239 240 241 242 243 244 245 246247
def load(self, weights, verbose=True):
    """
    Load the weights into the model.

    Args:
        weights (dict | torch.nn.Module): The pre-trained weights to be loaded.
        verbose (bool, optional): Whether to log the transfer progress. Defaults to True.
    """
    model = weights["model"] if isinstance(weights, dict) else weights  # torchvision models are not dicts
    csd = model.float().state_dict()  # checkpoint state_dict as FP32
    csd = intersect_dicts(csd, self.state_dict())  # intersect
    self.load_state_dict(csd, strict=False)  # load
    if verbose:
        LOGGER.info(f"Transferred {len(csd)}/{len(self.model.state_dict())} items from pretrained weights")

loss(batch, preds=None)

حساب الخسارة.

البارامترات:

اسم نوع وصف افتراضي
batch dict

دفعة لحساب الخسارة على

مطلوب
preds Tensor | List[Tensor]

التنبؤات.

None
شفرة المصدر في ultralytics/nn/tasks.py
249 250 251 252 253 254 255 256 257 258259260261
def loss(self, batch, preds=None):
    """
    Compute loss.

    Args:
        batch (dict): Batch to compute loss on
        preds (torch.Tensor | List[torch.Tensor]): Predictions.
    """
    if not hasattr(self, "criterion"):
        self.criterion = self.init_criterion()

    preds = self.forward(batch["img"]) if preds is None else preds
    return self.criterion(preds, batch)

predict(x, profile=False, visualize=False, augment=False, embed=None)

قم بإجراء تمريرة أمامية عبر الشبكة.

البارامترات:

اسم نوع وصف افتراضي
x Tensor

المدخلات tensor إلى النموذج.

مطلوب
profile bool

اطبع وقت الحساب لكل طبقة إذا كان True ، افتراضيا إلى False.

False
visualize bool

احفظ خرائط المعالم الخاصة بالنموذج إذا كان True ، افتراضيا إلى False.

False
augment bool

تكبير الصورة أثناء التنبؤ ، افتراضيا إلى خطأ.

False
embed list

قائمة بمتجهات / تضمينات الميزات المراد إرجاعها.

None

ارجاع:

نوع وصف
Tensor

الناتج الأخير للنموذج.

شفرة المصدر في ultralytics/nn/tasks.py
85 86 87 88 89 90 91 92 93 94  95 96 97 98         99 100 101
def predict(self, x, profile=False, visualize=False, augment=False, embed=None):
    """
    Perform a forward pass through the network.

    Args:
        x (torch.Tensor): The input tensor to the model.
        profile (bool):  Print the computation time of each layer if True, defaults to False.
        visualize (bool): Save the feature maps of the model if True, defaults to False.
        augment (bool): Augment image during prediction, defaults to False.
        embed (list, optional): A list of feature vectors/embeddings to return.

    Returns:
        (torch.Tensor): The last output of the model.
    """
    if augment:
        return self._predict_augment(x)
    return self._predict_once(x, profile, visualize, embed)



ultralytics.nn.tasks.DetectionModel

قواعد: BaseModel

YOLOv8 نموذج الكشف.

شفرة المصدر في ultralytics/nn/tasks.py
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326327 328 329 330 331 332 333 334 335 336 337 338 339340341
class DetectionModel(BaseModel):
    """YOLOv8 detection model."""

    def __init__(self, cfg="yolov8n.yaml", ch=3, nc=None, verbose=True):  # model, input channels, number of classes
        """Initialize the YOLOv8 detection model with the given config and parameters."""
        super().__init__()
        self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg)  # cfg dict

        # Define model
        ch = self.yaml["ch"] = self.yaml.get("ch", ch)  # input channels
        if nc and nc != self.yaml["nc"]:
            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
            self.yaml["nc"] = nc  # override YAML value
        self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose)  # model, savelist
        self.names = {i: f"{i}" for i in range(self.yaml["nc"])}  # default names dict
        self.inplace = self.yaml.get("inplace", True)

        # Build strides
        m = self.model[-1]  # Detect()
        if isinstance(m, Detect):  # includes all Detect subclasses like Segment, Pose, OBB, WorldDetect
            s = 256  # 2x min stride
            m.inplace = self.inplace
            forward = lambda x: self.forward(x)[0] if isinstance(m, (Segment, Pose, OBB)) else self.forward(x)
            m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
            self.stride = m.stride
            m.bias_init()  # only run once
        else:
            self.stride = torch.Tensor([32])  # default stride for i.e. RTDETR

        # Init weights, biases
        initialize_weights(self)
        if verbose:
            self.info()
            LOGGER.info("")

    def _predict_augment(self, x):
        """Perform augmentations on input image x and return augmented inference and train outputs."""
        img_size = x.shape[-2:]  # height, width
        s = [1, 0.83, 0.67]  # scales
        f = [None, 3, None]  # flips (2-ud, 3-lr)
        y = []  # outputs
        for si, fi in zip(s, f):
            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
            yi = super().predict(xi)[0]  # forward
            yi = self._descale_pred(yi, fi, si, img_size)
            y.append(yi)
        y = self._clip_augmented(y)  # clip augmented tails
        return torch.cat(y, -1), None  # augmented inference, train

    @staticmethod
    def _descale_pred(p, flips, scale, img_size, dim=1):
        """De-scale predictions following augmented inference (inverse operation)."""
        p[:, :4] /= scale  # de-scale
        x, y, wh, cls = p.split((1, 1, 2, p.shape[dim] - 4), dim)
        if flips == 2:
            y = img_size[0] - y  # de-flip ud
        elif flips == 3:
            x = img_size[1] - x  # de-flip lr
        return torch.cat((x, y, wh, cls), dim)

    def _clip_augmented(self, y):
        """Clip YOLO augmented inference tails."""
        nl = self.model[-1].nl  # number of detection layers (P3-P5)
        g = sum(4**x for x in range(nl))  # grid points
        e = 1  # exclude layer count
        i = (y[0].shape[-1] // g) * sum(4**x for x in range(e))  # indices
        y[0] = y[0][..., :-i]  # large
        i = (y[-1].shape[-1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
        y[-1] = y[-1][..., i:]  # small
        return y

    def init_criterion(self):
        """Initialize the loss criterion for the DetectionModel."""
        return v8DetectionLoss(self)

__init__(cfg='yolov8n.yaml', ch=3, nc=None, verbose=True)

تهيئة YOLOv8 نموذج الكشف مع التكوين والمعلمات المحددة.

شفرة المصدر في ultralytics/nn/tasks.py
271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288289 290 291 292 293 294 295 296 297 298 299 300 301
def __init__(self, cfg="yolov8n.yaml", ch=3, nc=None, verbose=True):  # model, input channels, number of classes
    """Initialize the YOLOv8 detection model with the given config and parameters."""
    super().__init__()
    self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg)  # cfg dict

    # Define model
    ch = self.yaml["ch"] = self.yaml.get("ch", ch)  # input channels
    if nc and nc != self.yaml["nc"]:
        LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
        self.yaml["nc"] = nc  # override YAML value
    self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose)  # model, savelist
    self.names = {i: f"{i}" for i in range(self.yaml["nc"])}  # default names dict
    self.inplace = self.yaml.get("inplace", True)

    # Build strides
    m = self.model[-1]  # Detect()
    if isinstance(m, Detect):  # includes all Detect subclasses like Segment, Pose, OBB, WorldDetect
        s = 256  # 2x min stride
        m.inplace = self.inplace
        forward = lambda x: self.forward(x)[0] if isinstance(m, (Segment, Pose, OBB)) else self.forward(x)
        m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
        self.stride = m.stride
        m.bias_init()  # only run once
    else:
        self.stride = torch.Tensor([32])  # default stride for i.e. RTDETR

    # Init weights, biases
    initialize_weights(self)
    if verbose:
        self.info()
        LOGGER.info("")

init_criterion()

تهيئة معيار الخسارة ل DetectionModel.

شفرة المصدر في ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the DetectionModel."""
    return v8DetectionLoss(self)



ultralytics.nn.tasks.OBBModel

قواعد: DetectionModel

YOLOv8 نموذج الصندوق المحيط الموجه (OBB).

شفرة المصدر في ultralytics/nn/tasks.py
344 345 346 347 348349 350 351 352 353
class OBBModel(DetectionModel):
    """YOLOv8 Oriented Bounding Box (OBB) model."""

    def __init__(self, cfg="yolov8n-obb.yaml", ch=3, nc=None, verbose=True):
        """Initialize YOLOv8 OBB model with given config and parameters."""
        super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

    def init_criterion(self):
        """Initialize the loss criterion for the model."""
        return v8OBBLoss(self)

__init__(cfg='yolov8n-obb.yaml', ch=3, nc=None, verbose=True)

تهيئه YOLOv8 نموذج OBB مع التكوين والمعلمات المحددة.

شفرة المصدر في ultralytics/nn/tasks.py
def __init__(self, cfg="yolov8n-obb.yaml", ch=3, nc=None, verbose=True):
    """Initialize YOLOv8 OBB model with given config and parameters."""
    super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

init_criterion()

تهيئة معيار الخسارة للنموذج.

شفرة المصدر في ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the model."""
    return v8OBBLoss(self)



ultralytics.nn.tasks.SegmentationModel

قواعد: DetectionModel

YOLOv8 نموذج التجزئة.

شفرة المصدر في ultralytics/nn/tasks.py
356 357 358 359 360 361 362 363 364 365
class SegmentationModel(DetectionModel):
    """YOLOv8 segmentation model."""

    def __init__(self, cfg="yolov8n-seg.yaml", ch=3, nc=None, verbose=True):
        """Initialize YOLOv8 segmentation model with given config and parameters."""
        super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

    def init_criterion(self):
        """Initialize the loss criterion for the SegmentationModel."""
        return v8SegmentationLoss(self)

__init__(cfg='yolov8n-seg.yaml', ch=3, nc=None, verbose=True)

تهيئه YOLOv8 نموذج التجزئة مع التكوين والمعلمات المحددة.

شفرة المصدر في ultralytics/nn/tasks.py
def __init__(self, cfg="yolov8n-seg.yaml", ch=3, nc=None, verbose=True):
    """Initialize YOLOv8 segmentation model with given config and parameters."""
    super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

init_criterion()

تهيئة معيار الخسارة لنموذج التجزئة.

شفرة المصدر في ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the SegmentationModel."""
    return v8SegmentationLoss(self)



ultralytics.nn.tasks.PoseModel

قواعد: DetectionModel

YOLOv8 تشكل نموذجا.

شفرة المصدر في ultralytics/nn/tasks.py
368 369 370 371 372 373 374 375 376 377 378379 380381 382
class PoseModel(DetectionModel):
    """YOLOv8 pose model."""

    def __init__(self, cfg="yolov8n-pose.yaml", ch=3, nc=None, data_kpt_shape=(None, None), verbose=True):
        """Initialize YOLOv8 Pose model."""
        if not isinstance(cfg, dict):
            cfg = yaml_model_load(cfg)  # load model YAML
        if any(data_kpt_shape) and list(data_kpt_shape) != list(cfg["kpt_shape"]):
            LOGGER.info(f"Overriding model.yaml kpt_shape={cfg['kpt_shape']} with kpt_shape={data_kpt_shape}")
            cfg["kpt_shape"] = data_kpt_shape
        super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

    def init_criterion(self):
        """Initialize the loss criterion for the PoseModel."""
        return v8PoseLoss(self)

__init__(cfg='yolov8n-pose.yaml', ch=3, nc=None, data_kpt_shape=(None, None), verbose=True)

تهيئه YOLOv8 تشكل نموذج.

شفرة المصدر في ultralytics/nn/tasks.py
371 372 373 374 375 376 377 378
def __init__(self, cfg="yolov8n-pose.yaml", ch=3, nc=None, data_kpt_shape=(None, None), verbose=True):
    """Initialize YOLOv8 Pose model."""
    if not isinstance(cfg, dict):
        cfg = yaml_model_load(cfg)  # load model YAML
    if any(data_kpt_shape) and list(data_kpt_shape) != list(cfg["kpt_shape"]):
        LOGGER.info(f"Overriding model.yaml kpt_shape={cfg['kpt_shape']} with kpt_shape={data_kpt_shape}")
        cfg["kpt_shape"] = data_kpt_shape
    super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

init_criterion()

تهيئة معيار الخسارة ل PoseModel.

شفرة المصدر في ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the PoseModel."""
    return v8PoseLoss(self)



ultralytics.nn.tasks.ClassificationModel

قواعد: BaseModel

YOLOv8 نموذج التصنيف.

شفرة المصدر في ultralytics/nn/tasks.py
385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408409 410411 412413 414  415 416417 418 419 420 421 422 423 424 425426 427 428 429430431 432
class ClassificationModel(BaseModel):
    """YOLOv8 classification model."""

    def __init__(self, cfg="yolov8n-cls.yaml", ch=3, nc=None, verbose=True):
        """Init ClassificationModel with YAML, channels, number of classes, verbose flag."""
        super().__init__()
        self._from_yaml(cfg, ch, nc, verbose)

    def _from_yaml(self, cfg, ch, nc, verbose):
        """Set YOLOv8 model configurations and define the model architecture."""
        self.yaml = cfg if isinstance(cfg, dict) else yaml_model_load(cfg)  # cfg dict

        # Define model
        ch = self.yaml["ch"] = self.yaml.get("ch", ch)  # input channels
        if nc and nc != self.yaml["nc"]:
            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
            self.yaml["nc"] = nc  # override YAML value
        elif not nc and not self.yaml.get("nc", None):
            raise ValueError("nc not specified. Must specify nc in model.yaml or function arguments.")
        self.model, self.save = parse_model(deepcopy(self.yaml), ch=ch, verbose=verbose)  # model, savelist
        self.stride = torch.Tensor([1])  # no stride constraints
        self.names = {i: f"{i}" for i in range(self.yaml["nc"])}  # default names dict
        self.info()

    @staticmethod
    def reshape_outputs(model, nc):
        """Update a TorchVision classification model to class count 'n' if required."""
        name, m = list((model.model if hasattr(model, "model") else model).named_children())[-1]  # last module
        if isinstance(m, Classify):  # YOLO Classify() head
            if m.linear.out_features != nc:
                m.linear = nn.Linear(m.linear.in_features, nc)
        elif isinstance(m, nn.Linear):  # ResNet, EfficientNet
            if m.out_features != nc:
                setattr(model, name, nn.Linear(m.in_features, nc))
        elif isinstance(m, nn.Sequential):
            types = [type(x) for x in m]
            if nn.Linear in types:
                i = types.index(nn.Linear)  # nn.Linear index
                if m[i].out_features != nc:
                    m[i] = nn.Linear(m[i].in_features, nc)
            elif nn.Conv2d in types:
                i = types.index(nn.Conv2d)  # nn.Conv2d index
                if m[i].out_channels != nc:
                    m[i] = nn.Conv2d(m[i].in_channels, nc, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None)

    def init_criterion(self):
        """Initialize the loss criterion for the ClassificationModel."""
        return v8ClassificationLoss()

__init__(cfg='yolov8n-cls.yaml', ch=3, nc=None, verbose=True)

Init ClassificationModel مع YAML ، القنوات ، عدد الفئات ، العلم المطول.

شفرة المصدر في ultralytics/nn/tasks.py
def __init__(self, cfg="yolov8n-cls.yaml", ch=3, nc=None, verbose=True):
    """Init ClassificationModel with YAML, channels, number of classes, verbose flag."""
    super().__init__()
    self._from_yaml(cfg, ch, nc, verbose)

init_criterion()

تهيئة معيار الخسارة لنموذج التصنيف.

شفرة المصدر في ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the ClassificationModel."""
    return v8ClassificationLoss()

reshape_outputs(model, nc) staticmethod

قم بتحديث نموذج تصنيف TorchVision إلى عدد الفئات 'n' إذا لزم الأمر.

شفرة المصدر في ultralytics/nn/tasks.py
409 410 411 412 413 414 415 416 417 418419 420 421 422 423 424 425426427 428
@staticmethod
def reshape_outputs(model, nc):
    """Update a TorchVision classification model to class count 'n' if required."""
    name, m = list((model.model if hasattr(model, "model") else model).named_children())[-1]  # last module
    if isinstance(m, Classify):  # YOLO Classify() head
        if m.linear.out_features != nc:
            m.linear = nn.Linear(m.linear.in_features, nc)
    elif isinstance(m, nn.Linear):  # ResNet, EfficientNet
        if m.out_features != nc:
            setattr(model, name, nn.Linear(m.in_features, nc))
    elif isinstance(m, nn.Sequential):
        types = [type(x) for x in m]
        if nn.Linear in types:
            i = types.index(nn.Linear)  # nn.Linear index
            if m[i].out_features != nc:
                m[i] = nn.Linear(m[i].in_features, nc)
        elif nn.Conv2d in types:
            i = types.index(nn.Conv2d)  # nn.Conv2d index
            if m[i].out_channels != nc:
                m[i] = nn.Conv2d(m[i].in_channels, nc, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None)



ultralytics.nn.tasks.RTDETRDetectionModel

قواعد: DetectionModel

RTDETR (DEtection في الوقت الحقيقي والتتبع باستخدام المحولات) فئة نموذج الكشف.

هذه الفئة مسؤولة عن بناء بنية RTDETR ، وتحديد وظائف الخسارة ، وتسهيل كل من عمليات التدريب والاستدلال. RTDETR هو نموذج للكشف عن الكائنات وتتبعها يمتد من الكشف عن فئة قاعدة النموذج.

سمات:

اسم نوع وصف
cfg str

مسار ملف التكوين أو سلسلة الإعداد المسبق. الافتراضي هو "rtdetr-l.yaml".

ch int

عدد قنوات الإدخال. الافتراضي هو 3 (RGB).

nc int

عدد الفئات للكشف عن الكائنات. الافتراضي هو بلا.

verbose bool

يحدد ما إذا كانت الإحصائيات الموجزة ستظهر أثناء التهيئة. الافتراضي هو صواب.

أساليب:

اسم وصف
init_criterion

تهيئة المعيار المستخدم لحساب الخسارة.

loss

يحسب ويعيد الخسارة أثناء التدريب.

predict

ينفذ تمريرة أمامية عبر الشبكة ويعيد الإخراج.

شفرة المصدر في ultralytics/nn/tasks.py
435 436 437 438 439 440 441 442 443 444 445 446 447 448449 450 451 452 453 454 455 456 457 458459460 461462 463 464 465466467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485486487 488 489 490 491 492 493494495496497 498 499 500 501 502 503 504 505 506 507508509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524525 526 527 528 529 530 531 532 533 534 535 536 537 538539 540 541 542 543 544 545 546547548 549
class RTDETRDetectionModel(DetectionModel):
    """
    RTDETR (Real-time DEtection and Tracking using Transformers) Detection Model class.

    This class is responsible for constructing the RTDETR architecture, defining loss functions, and facilitating both
    the training and inference processes. RTDETR is an object detection and tracking model that extends from the
    DetectionModel base class.

    Attributes:
        cfg (str): The configuration file path or preset string. Default is 'rtdetr-l.yaml'.
        ch (int): Number of input channels. Default is 3 (RGB).
        nc (int, optional): Number of classes for object detection. Default is None.
        verbose (bool): Specifies if summary statistics are shown during initialization. Default is True.

    Methods:
        init_criterion: Initializes the criterion used for loss calculation.
        loss: Computes and returns the loss during training.
        predict: Performs a forward pass through the network and returns the output.
    """

    def __init__(self, cfg="rtdetr-l.yaml", ch=3, nc=None, verbose=True):
        """
        Initialize the RTDETRDetectionModel.

        Args:
            cfg (str): Configuration file name or path.
            ch (int): Number of input channels.
            nc (int, optional): Number of classes. Defaults to None.
            verbose (bool, optional): Print additional information during initialization. Defaults to True.
        """
        super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

    def init_criterion(self):
        """Initialize the loss criterion for the RTDETRDetectionModel."""
        from ultralytics.models.utils.loss import RTDETRDetectionLoss

        return RTDETRDetectionLoss(nc=self.nc, use_vfl=True)

    def loss(self, batch, preds=None):
        """
        Compute the loss for the given batch of data.

        Args:
            batch (dict): Dictionary containing image and label data.
            preds (torch.Tensor, optional): Precomputed model predictions. Defaults to None.

        Returns:
            (tuple): A tuple containing the total loss and main three losses in a tensor.
        """
        if not hasattr(self, "criterion"):
            self.criterion = self.init_criterion()

        img = batch["img"]
        # NOTE: preprocess gt_bbox and gt_labels to list.
        bs = len(img)
        batch_idx = batch["batch_idx"]
        gt_groups = [(batch_idx == i).sum().item() for i in range(bs)]
        targets = {
            "cls": batch["cls"].to(img.device, dtype=torch.long).view(-1),
            "bboxes": batch["bboxes"].to(device=img.device),
            "batch_idx": batch_idx.to(img.device, dtype=torch.long).view(-1),
            "gt_groups": gt_groups,
        }

        preds = self.predict(img, batch=targets) if preds is None else preds
        dec_bboxes, dec_scores, enc_bboxes, enc_scores, dn_meta = preds if self.training else preds[1]
        if dn_meta is None:
            dn_bboxes, dn_scores = None, None
        else:
            dn_bboxes, dec_bboxes = torch.split(dec_bboxes, dn_meta["dn_num_split"], dim=2)
            dn_scores, dec_scores = torch.split(dec_scores, dn_meta["dn_num_split"], dim=2)

        dec_bboxes = torch.cat([enc_bboxes.unsqueeze(0), dec_bboxes])  # (7, bs, 300, 4)
        dec_scores = torch.cat([enc_scores.unsqueeze(0), dec_scores])

        loss = self.criterion(
            (dec_bboxes, dec_scores), targets, dn_bboxes=dn_bboxes, dn_scores=dn_scores, dn_meta=dn_meta
        )
        # NOTE: There are like 12 losses in RTDETR, backward with all losses but only show the main three losses.
        return sum(loss.values()), torch.as_tensor(
            [loss[k].detach() for k in ["loss_giou", "loss_class", "loss_bbox"]], device=img.device
        )

    def predict(self, x, profile=False, visualize=False, batch=None, augment=False, embed=None):
        """
        Perform a forward pass through the model.

        Args:
            x (torch.Tensor): The input tensor.
            profile (bool, optional): If True, profile the computation time for each layer. Defaults to False.
            visualize (bool, optional): If True, save feature maps for visualization. Defaults to False.
            batch (dict, optional): Ground truth data for evaluation. Defaults to None.
            augment (bool, optional): If True, perform data augmentation during inference. Defaults to False.
            embed (list, optional): A list of feature vectors/embeddings to return.

        Returns:
            (torch.Tensor): Model's output tensor.
        """
        y, dt, embeddings = [], [], []  # outputs
        for m in self.model[:-1]:  # except the head part
            if m.f != -1:  # if not from previous layer
                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
            if profile:
                self._profile_one_layer(m, x, dt)
            x = m(x)  # run
            y.append(x if m.i in self.save else None)  # save output
            if visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)
            if embed and m.i in embed:
                embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
                if m.i == max(embed):
                    return torch.unbind(torch.cat(embeddings, 1), dim=0)
        head = self.model[-1]
        x = head([y[j] for j in head.f], batch)  # head inference
        return x

__init__(cfg='rtdetr-l.yaml', ch=3, nc=None, verbose=True)

تهيئة RTDETRDetectionModel.

البارامترات:

اسم نوع وصف افتراضي
cfg str

اسم ملف التكوين أو المسار.

'rtdetr-l.yaml'
ch int

عدد قنوات الإدخال.

3
nc int

عدد الفصول. الإعدادات الافتراضية إلى لا شيء.

None
verbose bool

طباعة معلومات إضافية أثناء التهيئة. الإعدادات الافتراضية إلى صواب.

True
شفرة المصدر في ultralytics/nn/tasks.py
455 456 457 458 459 460 461 462 463464465
def __init__(self, cfg="rtdetr-l.yaml", ch=3, nc=None, verbose=True):
    """
    Initialize the RTDETRDetectionModel.

    Args:
        cfg (str): Configuration file name or path.
        ch (int): Number of input channels.
        nc (int, optional): Number of classes. Defaults to None.
        verbose (bool, optional): Print additional information during initialization. Defaults to True.
    """
    super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

init_criterion()

تهيئة معيار الخسارة لنموذج RTDETRDetectionModel.

شفرة المصدر في ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the RTDETRDetectionModel."""
    from ultralytics.models.utils.loss import RTDETRDetectionLoss

    return RTDETRDetectionLoss(nc=self.nc, use_vfl=True)

loss(batch, preds=None)

احسب الخسارة لمجموعة معينة من البيانات.

البارامترات:

اسم نوع وصف افتراضي
batch dict

قاموس يحتوي على بيانات الصورة والتسمية.

مطلوب
preds Tensor

تنبؤات النموذج المحسوبة مسبقا. الإعدادات الافتراضية إلى لا شيء.

None

ارجاع:

نوع وصف
tuple

مجموعة تحتوي على إجمالي الخسارة والخسائر الثلاث الرئيسية في أ tensor.

شفرة المصدر في ultralytics/nn/tasks.py
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488489 490 491 492 493 494 495 496 497 498 499500501 502 503 504505 506 507 508 509 510 511 512 513 514515516
def loss(self, batch, preds=None):
    """
    Compute the loss for the given batch of data.

    Args:
        batch (dict): Dictionary containing image and label data.
        preds (torch.Tensor, optional): Precomputed model predictions. Defaults to None.

    Returns:
        (tuple): A tuple containing the total loss and main three losses in a tensor.
    """
    if not hasattr(self, "criterion"):
        self.criterion = self.init_criterion()

    img = batch["img"]
    # NOTE: preprocess gt_bbox and gt_labels to list.
    bs = len(img)
    batch_idx = batch["batch_idx"]
    gt_groups = [(batch_idx == i).sum().item() for i in range(bs)]
    targets = {
        "cls": batch["cls"].to(img.device, dtype=torch.long).view(-1),
        "bboxes": batch["bboxes"].to(device=img.device),
        "batch_idx": batch_idx.to(img.device, dtype=torch.long).view(-1),
        "gt_groups": gt_groups,
    }

    preds = self.predict(img, batch=targets) if preds is None else preds
    dec_bboxes, dec_scores, enc_bboxes, enc_scores, dn_meta = preds if self.training else preds[1]
    if dn_meta is None:
        dn_bboxes, dn_scores = None, None
    else:
        dn_bboxes, dec_bboxes = torch.split(dec_bboxes, dn_meta["dn_num_split"], dim=2)
        dn_scores, dec_scores = torch.split(dec_scores, dn_meta["dn_num_split"], dim=2)

    dec_bboxes = torch.cat([enc_bboxes.unsqueeze(0), dec_bboxes])  # (7, bs, 300, 4)
    dec_scores = torch.cat([enc_scores.unsqueeze(0), dec_scores])

    loss = self.criterion(
        (dec_bboxes, dec_scores), targets, dn_bboxes=dn_bboxes, dn_scores=dn_scores, dn_meta=dn_meta
    )
    # NOTE: There are like 12 losses in RTDETR, backward with all losses but only show the main three losses.
    return sum(loss.values()), torch.as_tensor(
        [loss[k].detach() for k in ["loss_giou", "loss_class", "loss_bbox"]], device=img.device
    )

predict(x, profile=False, visualize=False, batch=None, augment=False, embed=None)

قم بإجراء تمريرة أمامية عبر النموذج.

البارامترات:

اسم نوع وصف افتراضي
x Tensor

المدخلات tensor.

مطلوب
profile bool

إذا كان هذا صحيحا، فقم بتعريف وقت الحساب لكل طبقة. الإعدادات الافتراضية إلى خطأ.

False
visualize bool

إذا كان هذا صحيحا، فاحفظ خرائط المعالم للمرئيات. الإعدادات الافتراضية إلى خطأ.

False
batch dict

بيانات الحقيقة الأساسية للتقييم. الإعدادات الافتراضية إلى لا شيء.

None
augment bool

إذا كان هذا صحيحا، فقم بإجراء زيادة البيانات أثناء الاستدلال. الإعدادات الافتراضية إلى خطأ.

False
embed list

قائمة بمتجهات / تضمينات الميزات المراد إرجاعها.

None

ارجاع:

نوع وصف
Tensor

إخراج النموذج tensor.

شفرة المصدر في ultralytics/nn/tasks.py
518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538539 540541 542 543 544 545 546 547548 549
def predict(self, x, profile=False, visualize=False, batch=None, augment=False, embed=None):
    """
    Perform a forward pass through the model.

    Args:
        x (torch.Tensor): The input tensor.
        profile (bool, optional): If True, profile the computation time for each layer. Defaults to False.
        visualize (bool, optional): If True, save feature maps for visualization. Defaults to False.
        batch (dict, optional): Ground truth data for evaluation. Defaults to None.
        augment (bool, optional): If True, perform data augmentation during inference. Defaults to False.
        embed (list, optional): A list of feature vectors/embeddings to return.

    Returns:
        (torch.Tensor): Model's output tensor.
    """
    y, dt, embeddings = [], [], []  # outputs
    for m in self.model[:-1]:  # except the head part
        if m.f != -1:  # if not from previous layer
            x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
        if profile:
            self._profile_one_layer(m, x, dt)
        x = m(x)  # run
        y.append(x if m.i in self.save else None)  # save output
        if visualize:
            feature_visualization(x, m.type, m.i, save_dir=visualize)
        if embed and m.i in embed:
            embeddings.append(nn.functional.adaptive_avg_pool2d(x, (1, 1)).squeeze(-1).squeeze(-1))  # flatten
            if m.i == max(embed):
                return torch.unbind(torch.cat(embeddings, 1), dim=0)
    head = self.model[-1]
    x = head([y[j] for j in head.f], batch)  # head inference
    return x



ultralytics.nn.tasks.Ensemble

قواعد: ModuleList

مجموعة من النماذج.

شفرة المصدر في ultralytics/nn/tasks.py
623 624 625 626 627 628629 630 631 632 633 634635 636
class Ensemble(nn.ModuleList):
    """Ensemble of models."""

    def __init__(self):
        """Initialize an ensemble of models."""
        super().__init__()

    def forward(self, x, augment=False, profile=False, visualize=False):
        """Function generates the YOLO network's final layer."""
        y = [module(x, augment, profile, visualize)[0] for module in self]
        # y = torch.stack(y).max(0)[0]  # max ensemble
        # y = torch.stack(y).mean(0)  # mean ensemble
        y = torch.cat(y, 2)  # nms ensemble, y shape(B, HW, C)
        return y, None  # inference, train output

__init__()

تهيئة مجموعة من النماذج.

شفرة المصدر في ultralytics/nn/tasks.py
def __init__(self):
    """Initialize an ensemble of models."""
    super().__init__()

forward(x, augment=False, profile=False, visualize=False)

تولد الوظيفة YOLO الطبقة النهائية للشبكة.

شفرة المصدر في ultralytics/nn/tasks.py
630 631 632 633 634 635 636
def forward(self, x, augment=False, profile=False, visualize=False):
    """Function generates the YOLO network's final layer."""
    y = [module(x, augment, profile, visualize)[0] for module in self]
    # y = torch.stack(y).max(0)[0]  # max ensemble
    # y = torch.stack(y).mean(0)  # mean ensemble
    y = torch.cat(y, 2)  # nms ensemble, y shape(B, HW, C)
    return y, None  # inference, train output



ultralytics.nn.tasks.temporary_modules(modules=None)

مدير السياق لإضافة أو تعديل الوحدات مؤقتا في Pythonذاكرة التخزين المؤقت للوحدة النمطية (sys.modules).

يمكن استخدام هذه الوظيفة لتغيير مسارات الوحدة أثناء وقت التشغيل. إنه مفيد عند إعادة بناء التعليمات البرمجية ، حيث قمت بنقل وحدة نمطية من موقع إلى آخر ، ولكنك لا تزال تريد دعم الاستيراد القديم مسارات للتوافق مع الإصدارات السابقة.

البارامترات:

اسم نوع وصف افتراضي
modules dict

قاموس يعين مسارات الوحدة القديمة إلى مسارات الوحدة النمطية الجديدة.

None
مثل
with temporary_modules({'old.module.path': 'new.module.path'}):
    import old.module.path  # this will now import new.module.path
ملاحظه

التغييرات سارية المفعول فقط داخل مدير السياق ويتم التراجع عنها بمجرد خروج مدير السياق. كن على علم بأن التلاعب المباشر sys.modules يمكن أن يؤدي إلى نتائج غير متوقعة ، خاصة في أكبر التطبيقات أو المكتبات. استخدم هذه الوظيفة بحذر.

شفرة المصدر في ultralytics/nn/tasks.py
642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658659 660 661 662 663 664 665 666 667 668669 670671672673 674 675 676 677 678 679680 681
@contextlib.contextmanager
def temporary_modules(modules=None):
    """
    Context manager for temporarily adding or modifying modules in Python's module cache (`sys.modules`).

    This function can be used to change the module paths during runtime. It's useful when refactoring code,
    where you've moved a module from one location to another, but you still want to support the old import
    paths for backwards compatibility.

    Args:
        modules (dict, optional): A dictionary mapping old module paths to new module paths.

    Example:
        ```python
        with temporary_modules({'old.module.path': 'new.module.path'}):
            import old.module.path  # this will now import new.module.path
        ```

    Note:
        The changes are only in effect inside the context manager and are undone once the context manager exits.
        Be aware that directly manipulating `sys.modules` can lead to unpredictable results, especially in larger
        applications or libraries. Use this function with caution.
    """
    if not modules:
        modules = {}

    import importlib
    import sys

    try:
        # Set modules in sys.modules under their old name
        for old, new in modules.items():
            sys.modules[old] = importlib.import_module(new)

        yield
    finally:
        # Remove the temporary module paths
        for old in modules:
            if old in sys.modules:
                del sys.modules[old]



ultralytics.nn.tasks.torch_safe_load(weight)

تحاول هذه الدالة تحميل ملف PyTorch نموذج مع torchالدالة .load(). إذا تم رفع خطأ في الوحدة النمطية ، يكتشف الخطأ ، ويسجل رسالة تحذير ، ويحاول تثبيت الوحدة المفقودة عبر check_requirements () وظيفة. بعد التثبيت ، تحاول الوظيفة مرة أخرى تحميل النموذج باستخدام torch.load().

البارامترات:

اسم نوع وصف افتراضي
weight str

مسار ملف PyTorch نموذج.

مطلوب

ارجاع:

نوع وصف
dict

المحملة PyTorch نموذج.

شفرة المصدر في ultralytics/nn/tasks.py
684 685 686 687 688689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708709710 711 712 713 714715716 717 718 719 720 721 722 723 724 725 726 727 728729 730 731 732 733 734 735 736 737 738
def torch_safe_load(weight):
    """
    This function attempts to load a PyTorch model with the torch.load() function. If a ModuleNotFoundError is raised,
    it catches the error, logs a warning message, and attempts to install the missing module via the
    check_requirements() function. After installation, the function again attempts to load the model using torch.load().

    Args:
        weight (str): The file path of the PyTorch model.

    Returns:
        (dict): The loaded PyTorch model.
    """
    from ultralytics.utils.downloads import attempt_download_asset

    check_suffix(file=weight, suffix=".pt")
    file = attempt_download_asset(weight)  # search online if missing locally
    try:
        with temporary_modules(
            {
                "ultralytics.yolo.utils": "ultralytics.utils",
                "ultralytics.yolo.v8": "ultralytics.models.yolo",
                "ultralytics.yolo.data": "ultralytics.data",
            }
        ):  # for legacy 8.0 Classify and Pose models
            ckpt = torch.load(file, map_location="cpu")

    except ModuleNotFoundError as e:  # e.name is missing module name
        if e.name == "models":
            raise TypeError(
                emojis(
                    f"ERROR ❌️ {weight} appears to be an Ultralytics YOLOv5 model originally trained "
                    f"with https://github.com/ultralytics/yolov5.\nThis model is NOT forwards compatible with "
                    f"YOLOv8 at https://github.com/ultralytics/ultralytics."
                    f"\nRecommend fixes are to train a new model using the latest 'ultralytics' package or to "
                    f"run a command with an official YOLOv8 model, i.e. 'yolo predict model=yolov8n.pt'"
                )
            ) from e
        LOGGER.warning(
            f"WARNING ⚠️ {weight} appears to require '{e.name}', which is not in ultralytics requirements."
            f"\nAutoInstall will run now for '{e.name}' but this feature will be removed in the future."
            f"\nRecommend fixes are to train a new model using the latest 'ultralytics' package or to "
            f"run a command with an official YOLOv8 model, i.e. 'yolo predict model=yolov8n.pt'"
        )
        check_requirements(e.name)  # install missing module
        ckpt = torch.load(file, map_location="cpu")

    if not isinstance(ckpt, dict):
        # File is likely a YOLO instance saved with i.e. torch.save(model, "saved_model.pt")
        LOGGER.warning(
            f"WARNING ⚠️ The file '{weight}' appears to be improperly saved or formatted. "
            f"For optimal results, use model.save('filename.pt') to correctly save YOLO models."
        )
        ckpt = {"model": ckpt.model}

    return ckpt, file  # load



ultralytics.nn.tasks.attempt_load_weights(weights, device=None, inplace=True, fuse=False)

يحمل مجموعة من أوزان النماذج = [أ ، ب ، ج] أو أوزان نموذج واحد = [أ] أو أوزان = أ.

شفرة المصدر في ultralytics/nn/tasks.py
741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758759 760 761 762 763 764 765 766 767 768769 770 771772 773 774 775 776 777
def attempt_load_weights(weights, device=None, inplace=True, fuse=False):
    """Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a."""

    ensemble = Ensemble()
    for w in weights if isinstance(weights, list) else [weights]:
        ckpt, w = torch_safe_load(w)  # load ckpt
        args = {**DEFAULT_CFG_DICT, **ckpt["train_args"]} if "train_args" in ckpt else None  # combined args
        model = (ckpt.get("ema") or ckpt["model"]).to(device).float()  # FP32 model

        # Model compatibility updates
        model.args = args  # attach args to model
        model.pt_path = w  # attach *.pt file path to model
        model.task = guess_model_task(model)
        if not hasattr(model, "stride"):
            model.stride = torch.tensor([32.0])

        # Append
        ensemble.append(model.fuse().eval() if fuse and hasattr(model, "fuse") else model.eval())  # model in eval mode

    # Module updates
    for m in ensemble.modules():
        if hasattr(m, "inplace"):
            m.inplace = inplace
        elif isinstance(m, nn.Upsample) and not hasattr(m, "recompute_scale_factor"):
            m.recompute_scale_factor = None  # torch 1.11.0 compatibility

    # Return model
    if len(ensemble) == 1:
        return ensemble[-1]

    # Return ensemble
    LOGGER.info(f"Ensemble created with {weights}\n")
    for k in "names", "nc", "yaml":
        setattr(ensemble, k, getattr(ensemble[0], k))
    ensemble.stride = ensemble[int(torch.argmax(torch.tensor([m.stride.max() for m in ensemble])))].stride
    assert all(ensemble[0].nc == m.nc for m in ensemble), f"Models differ in class counts {[m.nc for m in ensemble]}"
    return ensemble



ultralytics.nn.tasks.attempt_load_one_weight(weight, device=None, inplace=True, fuse=False)

يحمل أوزان نموذج واحد.

شفرة المصدر في ultralytics/nn/tasks.py
780 781 782 783 784 785 786 787 788789 790 791 792 793 794 795796797798 799 800 801 802803
def attempt_load_one_weight(weight, device=None, inplace=True, fuse=False):
    """Loads a single model weights."""
    ckpt, weight = torch_safe_load(weight)  # load ckpt
    args = {**DEFAULT_CFG_DICT, **(ckpt.get("train_args", {}))}  # combine model and default args, preferring model args
    model = (ckpt.get("ema") or ckpt["model"]).to(device).float()  # FP32 model

    # Model compatibility updates
    model.args = {k: v for k, v in args.items() if k in DEFAULT_CFG_KEYS}  # attach args to model
    model.pt_path = weight  # attach *.pt file path to model
    model.task = guess_model_task(model)
    if not hasattr(model, "stride"):
        model.stride = torch.tensor([32.0])

    model = model.fuse().eval() if fuse and hasattr(model, "fuse") else model.eval()  # model in eval mode

    # Module updates
    for m in model.modules():
        if hasattr(m, "inplace"):
            m.inplace = inplace
        elif isinstance(m, nn.Upsample) and not hasattr(m, "recompute_scale_factor"):
            m.recompute_scale_factor = None  # torch 1.11.0 compatibility

    # Return model and ckpt
    return model, ckpt



ultralytics.nn.tasks.parse_model(d, ch, verbose=True)

تحليل أ YOLO قاموس model.yaml في ملف PyTorch نموذج.

شفرة المصدر في ultralytics/nn/tasks.py
806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828829 830831832 833 834 835 836837838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857858859 860 861 862 863 864 865866867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909
def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
    """Parse a YOLO model.yaml dictionary into a PyTorch model."""
    import ast

    # Args
    max_channels = float("inf")
    nc, act, scales = (d.get(x) for x in ("nc", "activation", "scales"))
    depth, width, kpt_shape = (d.get(x, 1.0) for x in ("depth_multiple", "width_multiple", "kpt_shape"))
    if scales:
        scale = d.get("scale")
        if not scale:
            scale = tuple(scales.keys())[0]
            LOGGER.warning(f"WARNING ⚠️ no model scale passed. Assuming scale='{scale}'.")
        depth, width, max_channels = scales[scale]

    if act:
        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
        if verbose:
            LOGGER.info(f"{colorstr('activation:')} {act}")  # print

    if verbose:
        LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10}  {'module':<45}{'arguments':<30}")
    ch = [ch]
    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
    for i, (f, n, m, args) in enumerate(d["backbone"] + d["head"]):  # from, number, module, args
        m = getattr(torch.nn, m[3:]) if "nn." in m else globals()[m]  # get module
        for j, a in enumerate(args):
            if isinstance(a, str):
                with contextlib.suppress(ValueError):
                    args[j] = locals()[a] if a in locals() else ast.literal_eval(a)

        n = n_ = max(round(n * depth), 1) if n > 1 else n  # depth gain
        if m in (
            Classify,
            Conv,
            ConvTranspose,
            GhostConv,
            Bottleneck,
            GhostBottleneck,
            SPP,
            SPPF,
            DWConv,
            Focus,
            BottleneckCSP,
            C1,
            C2,
            C2f,
            C2fAttn,
            C3,
            C3TR,
            C3Ghost,
            nn.ConvTranspose2d,
            DWConvTranspose2d,
            C3x,
            RepC3,
        ):
            c1, c2 = ch[f], args[0]
            if c2 != nc:  # if c2 not equal to number of classes (i.e. for Classify() output)
                c2 = make_divisible(min(c2, max_channels) * width, 8)
            if m is C2fAttn:
                args[1] = make_divisible(min(args[1], max_channels // 2) * width, 8)  # embed channels
                args[2] = int(
                    max(round(min(args[2], max_channels // 2 // 32)) * width, 1) if args[2] > 1 else args[2]
                )  # num heads

            args = [c1, c2, *args[1:]]
            if m in (BottleneckCSP, C1, C2, C2f, C2fAttn, C3, C3TR, C3Ghost, C3x, RepC3):
                args.insert(2, n)  # number of repeats
                n = 1
        elif m is AIFI:
            args = [ch[f], *args]
        elif m in (HGStem, HGBlock):
            c1, cm, c2 = ch[f], args[0], args[1]
            args = [c1, cm, c2, *args[2:]]
            if m is HGBlock:
                args.insert(4, n)  # number of repeats
                n = 1
        elif m is ResNetLayer:
            c2 = args[1] if args[3] else args[1] * 4
        elif m is nn.BatchNorm2d:
            args = [ch[f]]
        elif m is Concat:
            c2 = sum(ch[x] for x in f)
        elif m in (Detect, WorldDetect, Segment, Pose, OBB, ImagePoolingAttn):
            args.append([ch[x] for x in f])
            if m is Segment:
                args[2] = make_divisible(min(args[2], max_channels) * width, 8)
        elif m is RTDETRDecoder:  # special case, channels arg must be passed in index 1
            args.insert(1, [ch[x] for x in f])
        else:
            c2 = ch[f]

        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
        t = str(m)[8:-2].replace("__main__.", "")  # module type
        m.np = sum(x.numel() for x in m_.parameters())  # number params
        m_.i, m_.f, m_.type = i, f, t  # attach index, 'from' index, type
        if verbose:
            LOGGER.info(f"{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f}  {t:<45}{str(args):<30}")  # print
        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
        layers.append(m_)
        if i == 0:
            ch = []
        ch.append(c2)
    return nn.Sequential(*layers), sorted(save)



ultralytics.nn.tasks.yaml_model_load(path)

تحميل أ YOLOv8 نموذج من ملف YAML.

شفرة المصدر في ultralytics/nn/tasks.py
912 913 914 915 916 917 918919 920 921 922 923 924 925 926 927
def yaml_model_load(path):
    """Load a YOLOv8 model from a YAML file."""
    import re

    path = Path(path)
    if path.stem in (f"yolov{d}{x}6" for x in "nsmlx" for d in (5, 8)):
        new_stem = re.sub(r"(\d+)([nslmx])6(.+)?$", r"\1\2-p6\3", path.stem)
        LOGGER.warning(f"WARNING ⚠️ Ultralytics YOLO P6 models now use -p6 suffix. Renaming {path.stem} to {new_stem}.")
        path = path.with_name(new_stem + path.suffix)

    unified_path = re.sub(r"(\d+)([nslmx])(.+)?$", r"\1\3", str(path))  # i.e. yolov8x.yaml -> yolov8.yaml
    yaml_file = check_yaml(unified_path, hard=False) or check_yaml(path)
    d = yaml_load(yaml_file)  # model dict
    d["scale"] = guess_model_scale(path)
    d["yaml_file"] = str(path)
    return d



ultralytics.nn.tasks.guess_model_scale(model_path)

يأخذ طريقا إلى YOLO ملف YAML الخاص بالنموذج كإدخال ويستخرج حرف حجم مقياس النموذج. الوظيفة يستخدم مطابقة التعبير العادية للعثور على نمط مقياس النموذج في اسم ملف YAML ، والذي يشار إليه بالرمز n أو s أو m أو l أو x. ترجع الدالة حرف الحجم لمقياس النموذج كسلسلة.

البارامترات:

اسم نوع وصف افتراضي
model_path str | Path

الطريق إلى YOLO ملف YAML الخاص بالنموذج.

مطلوب

ارجاع:

نوع وصف
str

حرف الحجم لمقياس النموذج ، والذي يمكن أن يكون n أو s أو m أو l أو x.

شفرة المصدر في ultralytics/nn/tasks.py
930 931 932 933 934 935 936 937938 939 940941 942 943 944 945946
def guess_model_scale(model_path):
    """
    Takes a path to a YOLO model's YAML file as input and extracts the size character of the model's scale. The function
    uses regular expression matching to find the pattern of the model scale in the YAML file name, which is denoted by
    n, s, m, l, or x. The function returns the size character of the model scale as a string.

    Args:
        model_path (str | Path): The path to the YOLO model's YAML file.

    Returns:
        (str): The size character of the model's scale, which can be n, s, m, l, or x.
    """
    with contextlib.suppress(AttributeError):
        import re

        return re.search(r"yolov\d+([nslmx])", Path(model_path).stem).group(1)  # n, s, m, l, or x
    return ""



ultralytics.nn.tasks.guess_model_task(model)

تخمين مهمة أ PyTorch نموذج من بنيته أو تكوينه.

البارامترات:

اسم نوع وصف افتراضي
model Module | dict

PyTorch نموذج أو تكوين نموذج بتنسيق YAML.

مطلوب

ارجاع:

نوع وصف
str

مهمة النموذج ("كشف" ، "شريحة" ، "تصنيف" ، "وضع").

يثير:

نوع وصف
SyntaxError

إذا تعذر تحديد مهمة النموذج.

شفرة المصدر في ultralytics/nn/tasks.py
949 950 951 952 953 954 955 956 957      958 959 960 961 962 963 964 965  966 967 968 969 970 971 972 973  974 975 976  977 978 979 980                 981 982 983 984 985 986 987     988 989 990 991 992 993 994 995 996 997  998         999 1000 1001  1002 1003 1004 1005 1006 1007  1008  100910101011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 
def guess_model_task(model):
    """
    Guess the task of a PyTorch model from its architecture or configuration.

    Args:
        model (nn.Module | dict): PyTorch model or model configuration in YAML format.

    Returns:
        (str): Task of the model ('detect', 'segment', 'classify', 'pose').

    Raises:
        SyntaxError: If the task of the model could not be determined.
    """

    def cfg2task(cfg):
        """Guess from YAML dictionary."""
        m = cfg["head"][-1][-2].lower()  # output module name
        if m in ("classify", "classifier", "cls", "fc"):
            return "classify"
        if m == "detect":
            return "detect"
        if m == "segment":
            return "segment"
        if m == "pose":
            return "pose"
        if m == "obb":
            return "obb"

    # Guess from model cfg
    if isinstance(model, dict):
        with contextlib.suppress(Exception):
            return cfg2task(model)

    # Guess from PyTorch model
    if isinstance(model, nn.Module):  # PyTorch model
        for x in "model.args", "model.model.args", "model.model.model.args":
            with contextlib.suppress(Exception):
                return eval(x)["task"]
        for x in "model.yaml", "model.model.yaml", "model.model.model.yaml":
            with contextlib.suppress(Exception):
                return cfg2task(eval(x))

        for m in model.modules():
            if isinstance(m, Segment):
                return "segment"
            elif isinstance(m, Classify):
                return "classify"
            elif isinstance(m, Pose):
                return "pose"
            elif isinstance(m, OBB):
                return "obb"
            elif isinstance(m, (Detect, WorldDetect)):
                return "detect"

    # Guess from model filename
    if isinstance(model, (str, Path)):
        model = Path(model)
        if "-seg" in model.stem or "segment" in model.parts:
            return "segment"
        elif "-cls" in model.stem or "classify" in model.parts:
            return "classify"
        elif "-pose" in model.stem or "pose" in model.parts:
            return "pose"
        elif "-obb" in model.stem or "obb" in model.parts:
            return "obb"
        elif "detect" in model.parts:
            return "detect"

    # Unable to determine task from model
    LOGGER.warning(
        "WARNING ⚠️ Unable to automatically guess model task, assuming 'task=detect'. "
        "Explicitly define task for your model, i.e. 'task=detect', 'segment', 'classify','pose' or 'obb'."
    )
    return "detect"  # assume detect





تم إنشاؤه في 2023-11-12, اخر تحديث 2024-01-05
المؤلفون: جلين جوشر (5) ، يضحك س (1)