सामग्री पर जाएं

के लिए संदर्भ ultralytics/nn/tasks.py

नोट

यह फ़ाइल यहाँ उपलब्ध है https://github.com/ultralytics/ultralytics/बूँद/मुख्य/ultralytics/nn/tasks.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.nn.tasks.BaseModel

का रूप: Module

बेसमोडेल क्लास सभी मॉडलों के लिए बेस क्लास के रूप में कार्य करता है Ultralytics YOLO परिवार।

में स्रोत कोड 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)

एक ही पैमाने पर मॉडल का फॉरवर्ड पास। के लिए आवरण _forward_once विधि।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
x Tensor | dict

इनपुट छवि tensor या छवि सहित एक डिक्ट tensor और जीटी लेबल।

आवश्यक

देता:

प्रकार विवरण: __________
Tensor

नेटवर्क का आउटपुट.

में स्रोत कोड 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)

फ्यूज Conv2d() और BatchNorm2d() मॉडल की परतों को एक परत में बदलने के लिए, गणना दक्षता।

देता:

प्रकार विवरण: __________
Module

फ्यूज्ड मॉडल वापस आ गया है।

में स्रोत कोड ultralytics/nn/tasks.py
165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188189190
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)

मॉडल की जानकारी प्रिंट करता है।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
detailed bool

यदि सही है, तो मॉडल के बारे में विस्तृत जानकारी प्रिंट करता है। डिफ़ॉल्ट से गलत

False
verbose bool

यदि सही है, तो मॉडल की जानकारी प्रिंट करता है। डिफ़ॉल्ट से गलत

True
imgsz int

छवि का आकार जिस पर मॉडल को प्रशिक्षित किया जाएगा। 640 के लिए डिफ़ॉल्ट

640
में स्रोत कोड 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()

BaseModel के लिए हानि मानदंड प्रारंभ करें।

में स्रोत कोड 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)

जांचें कि क्या मॉडल में BatchNorm परतों की एक निश्चित सीमा से कम है।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
thresh int

BatchNorm परतों की थ्रेशोल्ड संख्या। डिफ़ॉल्ट 10 है।

10

देता:

प्रकार विवरण: __________
bool

सच है अगर मॉडल में BatchNorm परतों की संख्या सीमा से कम है, अन्यथा गलत।

में स्रोत कोड ultralytics/nn/tasks.py
192 193 194 195 196 197 198199200 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)

मॉडल में वजन लोड करें।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
weights dict | Module

लोड किए जाने वाले पूर्व-प्रशिक्षित भार।

आवश्यक
verbose bool

स्थानांतरण प्रगति को लॉग करना है या नहीं। सही करने के लिए डिफ़ॉल्ट।

True
में स्रोत कोड ultralytics/nn/tasks.py
234 235 236 237 238239 240 241 242 243 244 245 246 247
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)

नुकसान की गणना करें।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
batch dict

नुकसान की गणना करने के लिए बैच

आवश्यक
preds Tensor | List[Tensor]

भविष्यवाणियों।

None
में स्रोत कोड 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)

नेटवर्क के माध्यम से एक फॉरवर्ड पास करें।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
x Tensor

इनपुट tensor मॉडल के लिए।

आवश्यक
profile bool

प्रत्येक परत का गणना समय प्रिंट करें यदि True, डिफ़ॉल्ट रूप से गलत है।

False
visualize bool

मॉडल के फीचर मैप्स को सेव करें यदि True, डिफ़ॉल्ट रूप से गलत है।

False
augment bool

पूर्वानुमान के दौरान छवि को बढ़ाएँ, डिफ़ॉल्ट रूप से गलत हो जाता है.

False
embed list

वापसी के लिए फीचर वैक्टर/एम्बेडिंग की एक सूची।

None

देता:

प्रकार विवरण: __________
Tensor

मॉडल का अंतिम आउटपुट।

में स्रोत कोड ultralytics/nn/tasks.py
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

का रूप: BaseModel

YOLOv8 डिटेक्शन मॉडल।

में स्रोत कोड 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 320321 322 323 324 325 326 327 328329 330 331 332 333 334 335 336 337 338339340 341
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)

इनरिजिनियलाइज़ करें YOLOv8 दिए गए कॉन्फ़िगरेशन और मापदंडों के साथ डिटेक्शन मॉडल।

में स्रोत कोड ultralytics/nn/tasks.py
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
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()

DetectionModel के लिए हानि मानदंड प्रारंभ करें।

में स्रोत कोड ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the DetectionModel."""
    return v8DetectionLoss(self)



ultralytics.nn.tasks.OBBModel

का रूप: DetectionModel

YOLOv8 ओरिएंटेड बाउंडिंग बॉक्स (OBB) मॉडल।

में स्रोत कोड ultralytics/nn/tasks.py
344 345 346 347 348 349 350 351 352 353
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)

प्रारंभ YOLOv8 दिए गए कॉन्फ़िगरेशन और मापदंडों के साथ OBB मॉडल।

में स्रोत कोड 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()

मॉडल के लिए हानि मानदंड को प्रारंभ करें।

में स्रोत कोड ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the model."""
    return v8OBBLoss(self)



ultralytics.nn.tasks.SegmentationModel

का रूप: DetectionModel

YOLOv8 विभाजन मॉडल।

में स्रोत कोड 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)

प्रारंभ YOLOv8 दिए गए कॉन्फ़िगरेशन और मापदंडों के साथ विभाजन मॉडल।

में स्रोत कोड 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()

SegmentationModel के लिए हानि मानदंड प्रारंभ करें।

में स्रोत कोड ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the SegmentationModel."""
    return v8SegmentationLoss(self)



ultralytics.nn.tasks.PoseModel

का रूप: DetectionModel

YOLOv8 पोज़ मॉडल।

में स्रोत कोड 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)

प्रारंभ YOLOv8 पोज़ मॉडल।

में स्रोत कोड 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()

PoseModel के लिए नुकसान मानदंड को प्रारंभ करें।

में स्रोत कोड ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the PoseModel."""
    return v8PoseLoss(self)



ultralytics.nn.tasks.ClassificationModel

का रूप: BaseModel

YOLOv8 वर्गीकरण मॉडल।

में स्रोत कोड 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 412 413 414 415 416417 418 419 420 421 422 423 424 425 426 427 428429 430 431432
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)

वाईएएमएल के साथ इनिट वर्गीकरण, चैनल, कक्षाओं की संख्या, वर्बोज़ ध्वज।

में स्रोत कोड 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()

ClassificationModel के लिए हानि मानदंड प्रारंभ करें।

में स्रोत कोड ultralytics/nn/tasks.py
def init_criterion(self):
    """Initialize the loss criterion for the ClassificationModel."""
    return v8ClassificationLoss()

reshape_outputs(model, nc) staticmethod

यदि आवश्यक हो तो वर्ग गणना 'एन' के लिए एक TorchVision वर्गीकरण मॉडल अद्यतन करें.

में स्रोत कोड ultralytics/nn/tasks.py
409 410 411 412 413 414 415 416 417 418 419420 421 422 423 424 425 426 427 428
@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

का रूप: DetectionModel

RTDETR (रीयल-टाइम डिटेक्शन और ट्रांसफॉर्मर का उपयोग करके ट्रैकिंग) डिटेक्शन मॉडल क्लास।

यह वर्ग RTDETR आर्किटेक्चर के निर्माण, हानि कार्यों को परिभाषित करने और दोनों को सुविधाजनक बनाने के लिए जिम्मेदार है प्रशिक्षण और अनुमान प्रक्रियाएं। RTDETR एक ऑब्जेक्ट डिटेक्शन और ट्रैकिंग मॉडल है जो डिटेक्शनमॉडल बेस क्लास।

विशेषताएँ:

नाम प्रकार विवरण: __________
cfg str

कॉन्फ़िगरेशन फ़ाइल पथ या प्रीसेट स्ट्रिंग। डिफ़ॉल्ट 'rtdetr-l.yaml' है।

ch int

इनपुट चैनलों की संख्या। डिफ़ॉल्ट 3 (RGB) है।

nc int

ऑब्जेक्ट डिटेक्शन के लिए कक्षाओं की संख्या। डिफ़ॉल्ट कोई नहीं है।

verbose bool

निर्दिष्ट करता है कि आरंभीकरण के दौरान सारांश आँकड़े दिखाए जाते हैं या नहीं. डिफ़ॉल्ट True है.

विधियाँ:

नाम विवरण: __________
init_criterion

हानि गणना के लिए उपयोग किए जाने वाले मानदंड को प्रारंभ करता है।

loss

प्रशिक्षण के दौरान नुकसान की गणना और वापसी करता है।

predict

नेटवर्क के माध्यम से एक फॉरवर्ड पास करता है और आउटपुट देता है।

में स्रोत कोड ultralytics/nn/tasks.py
435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488489 490491 492 493 494 495 496497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518519 520 521 522 523 524525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 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)

RTDETRDetectionModel प्रारंभ करें।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
cfg str

कॉन्फ़िगरेशन फ़ाइल नाम या पथ।

'rtdetr-l.yaml'
ch int

इनपुट चैनलों की संख्या।

3
nc int

कक्षाओं की संख्या। कोई नहीं करने के लिए डिफ़ॉल्ट।

None
verbose bool

आरंभीकरण के दौरान अतिरिक्त जानकारी प्रिंट करें। सही करने के लिए डिफ़ॉल्ट।

True
में स्रोत कोड ultralytics/nn/tasks.py
455 456 457 458 459 460 461 462 463 464 465
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()

RTDETRDetectionModel के लिए हानि मानदंड प्रारंभ करें।

में स्रोत कोड 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)

दिए गए डेटा बैच के लिए नुकसान की गणना करें।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
batch dict

शब्दकोश जिसमें छवि और लेबल डेटा शामिल हैं।

आवश्यक
preds Tensor

प्रीकंप्यूटेड मॉडल भविष्यवाणियां। कोई नहीं करने के लिए डिफ़ॉल्ट।

None

देता:

प्रकार विवरण: __________
tuple

एक टपल जिसमें कुल नुकसान और मुख्य तीन नुकसान होते हैं tensor.

में स्रोत कोड ultralytics/nn/tasks.py
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497498 499500 501 502 503 504505 506 507 508 509 510 511 512 513 514 515516
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)

मॉडल के माध्यम से एक फॉरवर्ड पास करें।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
x Tensor

इनपुट tensor.

आवश्यक
profile bool

यदि सही है, तो प्रत्येक परत के लिए गणना समय को प्रोफाइल करें। डिफ़ॉल्ट रूप से गलत है.

False
visualize bool

यदि सही है, तो विज़ुअलाइज़ेशन के लिए सुविधा मानचित्र सहेजें। डिफ़ॉल्ट रूप से गलत है.

False
batch dict

मूल्यांकन के लिए जमीनी सच्चाई डेटा। कोई नहीं करने के लिए डिफ़ॉल्ट।

None
augment bool

यदि सही है, तो अनुमान के दौरान डेटा वृद्धि करें। डिफ़ॉल्ट रूप से गलत है.

False
embed list

वापसी के लिए फीचर वैक्टर/एम्बेडिंग की एक सूची।

None

देता:

प्रकार विवरण: __________
Tensor

मॉडल का आउटपुट tensor.

में स्रोत कोड ultralytics/nn/tasks.py
518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540541 542 543 544 545 546 547 548549
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

का रूप: ModuleList

मॉडलों का पहनावा।

में स्रोत कोड 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__()

मॉडल के एक पहनावा को प्रारंभ करें।

में स्रोत कोड ultralytics/nn/tasks.py
def __init__(self):
    """Initialize an ensemble of models."""
    super().__init__()

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

फ़ंक्शन उत्पन्न करता है YOLO नेटवर्क की अंतिम परत।

में स्रोत कोड ultralytics/nn/tasks.py
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)

में मॉड्यूल को अस्थायी रूप से जोड़ने या संशोधित करने के लिए संदर्भ प्रबंधक Pythonमॉड्यूल कैश (sys.modules).

इस फ़ंक्शन का उपयोग रनटाइम के दौरान मॉड्यूल पथ को बदलने के लिए किया जा सकता है। कोड को रिफैक्टरिंग करते समय यह उपयोगी है, जहां आपने एक मॉड्यूल को एक स्थान से दूसरे स्थान पर ले जाया है, लेकिन आप अभी भी पुराने आयात का समर्थन करना चाहते हैं पश्चगामी संगतता के लिए पथ।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
modules dict

एक शब्दकोश नए मॉड्यूल पथ के लिए पुराने मॉड्यूल पथ मानचित्रण.

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

परिवर्तन केवल संदर्भ प्रबंधक के अंदर प्रभावी होते हैं और संदर्भ प्रबंधक के बाहर निकलने के बाद पूर्ववत हो जाते हैं। ध्यान रखें कि सीधे हेरफेर sys.modules अप्रत्याशित परिणाम हो सकते हैं, विशेष रूप से बड़े में अनुप्रयोग या पुस्तकालय. सावधानी के साथ इस फ़ंक्शन का उपयोग करें।

में स्रोत कोड ultralytics/nn/tasks.py
642  643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658659 660 661 662 663 664 665 666 667 668 669 670671 672 673 674 675 676 677 678 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)

यह फ़ंक्शन एक लोड करने का प्रयास करता है PyTorch के साथ मॉडल torch.load() फ़ंक्शन का उपयोग करें। यदि कोई ModuleNotFoundError उठाया जाता है, यह त्रुटि को पकड़ता है, एक चेतावनी संदेश लॉग करता है, और लापता मॉड्यूल को स्थापित करने का प्रयास करता है check_requirements() फ़ंक्शन का उपयोग करें। स्थापना के बाद, फ़ंक्शन फिर से मॉडल का उपयोग करके लोड करने का प्रयास करता है torch.load() का उपयोग करें।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
weight str

का फ़ाइल पथ PyTorch को गढ़ना।

आवश्यक

देता:

प्रकार विवरण: __________
dict

भरी हुई PyTorch को गढ़ना।

में स्रोत कोड ultralytics/nn/tasks.py
684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708709 710 711712713 714 715716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736737 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)

मॉडल वजन का एक पहनावा लोड करता है = [ए, बी, सी] या एक एकल मॉडल वजन = [ए] या वजन = ए।

में स्रोत कोड ultralytics/nn/tasks.py
741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769770 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)

एकल मॉडल भार लोड करता है।

में स्रोत कोड ultralytics/nn/tasks.py
780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799800801 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)

पार्स ए YOLO model.yaml शब्दकोश को एक PyTorch को गढ़ना।

में स्रोत कोड ultralytics/nn/tasks.py
806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907908 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)

एक लोड करें YOLOv8 एक YAML फ़ाइल से मॉडल।

में स्रोत कोड 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)

एक के लिए एक रास्ता लेता है YOLO इनपुट के रूप में मॉडल की YAML फ़ाइल और मॉडल के पैमाने के आकार चरित्र को निकालती है। समारोह YAML फ़ाइल नाम में मॉडल स्केल के पैटर्न को खोजने के लिए नियमित अभिव्यक्ति मिलान का उपयोग करता है, जिसे द्वारा दर्शाया जाता है एन, एस, एम, एल, या एक्स। फ़ंक्शन स्ट्रिंग के रूप में मॉडल स्केल के आकार चरित्र को लौटाता है।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
model_path str | Path

के लिए पथ YOLO मॉडल की YAML फ़ाइल।

आवश्यक

देता:

प्रकार विवरण: __________
str

मॉडल के पैमाने का आकार वर्ण, जो n, s, m, l, या x हो सकता है।

में स्रोत कोड ultralytics/nn/tasks.py
930 931 932 933 934 935 936 937 938 939 940 941 942 943 944945946
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)

एक के कार्य का अनुमान लगाएं PyTorch इसकी वास्तुकला या विन्यास से मॉडल।

पैरामीटर:

नाम प्रकार विवरण: __________ चूक
model Module | dict

PyTorch YAML प्रारूप में मॉडल या मॉडल कॉन्फ़िगरेशन।

आवश्यक

देता:

प्रकार विवरण: __________
str

मॉडल का कार्य ('पता लगाएं', 'खंड', 'वर्गीकृत', 'मुद्रा')।

उठाती:

प्रकार विवरण: __________
SyntaxError

यदि मॉडल का कार्य निर्धारित नहीं किया जा सका।

में स्रोत कोड 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





2023-11-12 बनाया गया, अपडेट किया गया 2024-01-05
लेखक: ग्लेन-जोचर (5), लाफिंग-क्यू (1)