─░├žeri─če ge├ž

Referans i├žin ultralytics/models/rtdetr/model.py

Not

Bu dosya https://github.com/ultralytics/ultralytics/blob/main/ ultralytics/models/rtdetr/model .py adresinde mevcuttur. Bir sorun tespit ederseniz l├╝tfen bir ├çekme ─░ste─či ­čŤá´ŞĆ ile katk─▒da bulunarak d├╝zeltilmesine yard─▒mc─▒ olun. Te┼čekk├╝rler ­čÖĆ!



ultralytics.models.rtdetr.model.RTDETR

├ťsler: Model

Baidu'nun RT-DETR modeli i├žin aray├╝z. Bu Vision Transformer tabanl─▒ nesne alg─▒lay─▒c─▒, ger├žek zamanl─▒ performans sa─člar y├╝ksek do─črulukla. Verimli hibrit kodlamay─▒, IoU fark─▒ndal─▒ sorgu se├žimini ve uyarlanabilir ├ž─▒kar─▒m h─▒z─▒n─▒ destekler.

Nitelikler:

─░sim Tip A├ž─▒klama
model str

├ľnceden e─čitilmi┼č modelin yolu. Varsay─▒lan de─čer 'rtdetr-l.pt'.

Kaynak kodu ultralytics/models/rtdetr/model.py
class RTDETR(Model):
    """
    Interface for Baidu's RT-DETR model. This Vision Transformer-based object detector provides real-time performance
    with high accuracy. It supports efficient hybrid encoding, IoU-aware query selection, and adaptable inference speed.

    Attributes:
        model (str): Path to the pre-trained model. Defaults to 'rtdetr-l.pt'.
    """

    def __init__(self, model="rtdetr-l.pt") -> None:
        """
        Initializes the RT-DETR model with the given pre-trained model file. Supports .pt and .yaml formats.

        Args:
            model (str): Path to the pre-trained model. Defaults to 'rtdetr-l.pt'.

        Raises:
            NotImplementedError: If the model file extension is not 'pt', 'yaml', or 'yml'.
        """
        super().__init__(model=model, task="detect")

    @property
    def task_map(self) -> dict:
        """
        Returns a task map for RT-DETR, associating tasks with corresponding Ultralytics classes.

        Returns:
            dict: A dictionary mapping task names to Ultralytics task classes for the RT-DETR model.
        """
        return {
            "detect": {
                "predictor": RTDETRPredictor,
                "validator": RTDETRValidator,
                "trainer": RTDETRTrainer,
                "model": RTDETRDetectionModel,
            }
        }

task_map: dict property

G├Ârevleri kar┼č─▒l─▒k gelen Ultralytics s─▒n─▒flar─▒yla ili┼čkilendirerek RT-DETR i├žin bir g├Ârev haritas─▒ d├Ând├╝r├╝r.

─░ade:

─░sim Tip A├ž─▒klama
dict dict

RT-DETR modeli i├žin g├Ârev adlar─▒n─▒ Ultralytics g├Ârev s─▒n─▒flar─▒yla e┼čleyen bir s├Âzl├╝k.

__init__(model='rtdetr-l.pt')

RT-DETR modelini verilen ├Ânceden e─čitilmi┼č model dosyas─▒ ile ba┼člat─▒r. .pt ve .yaml bi├žimlerini destekler.

Parametreler:

─░sim Tip A├ž─▒klama Varsay─▒lan
model str

├ľnceden e─čitilmi┼č modelin yolu. Varsay─▒lan de─čer 'rtdetr-l.pt'.

'rtdetr-l.pt'

Zamlar:

Tip A├ž─▒klama
NotImplementedError

Model dosyas─▒ uzant─▒s─▒ 'pt', 'yaml' veya 'yml' de─čilse.

Kaynak kodu ultralytics/models/rtdetr/model.py
def __init__(self, model="rtdetr-l.pt") -> None:
    """
    Initializes the RT-DETR model with the given pre-trained model file. Supports .pt and .yaml formats.

    Args:
        model (str): Path to the pre-trained model. Defaults to 'rtdetr-l.pt'.

    Raises:
        NotImplementedError: If the model file extension is not 'pt', 'yaml', or 'yml'.
    """
    super().__init__(model=model, task="detect")





Created 2023-11-12, Updated 2024-06-02
Authors: glenn-jocher (5), Burhan-Q (1)