a yf @sLddlZddlmZddlmZddlmZddlmZGdddeZ dS)N) LetterBox) BasePredictor)Results)opsc@s eZdZdZddZddZdS)RTDETRPredictora5 RT-DETR (Real-Time Detection Transformer) Predictor extending the BasePredictor class for making predictions using Baidu's RT-DETR model. This class leverages the power of Vision Transformers to provide real-time object detection while maintaining high accuracy. It supports key features like efficient hybrid encoding and IoU-aware query selection. Example: ```python from ultralytics.utils import ASSETS from ultralytics.models.rtdetr import RTDETRPredictor args = dict(model="rtdetr-l.pt", source=ASSETS) predictor = RTDETRPredictor(overrides=args) predictor.predict_cli() ``` Attributes: imgsz (int): Image size for inference (must be square and scale-filled). args (dict): Argument overrides for the predictor. c CsPt|ttfs|dg}|djd}|djd|dfdd\}}t|tsVt|}g}t||||jdD]\}} } } t |}| j ddd\} } | d|j j k}|j jdur| tj|j j| jdkd |@}tj|| | gdd|}| jdd \}}|d dd gf|9<|d d d gf|9<|t| | |jj|d qn|S)aZ Postprocess the raw predictions from the model to generate bounding boxes and confidence scores. The method filters detections based on confidence and class if specified in `self.args`. Args: preds (list): List of [predictions, extra] from the model. img (torch.Tensor): Processed input images. orig_imgs (list or torch.Tensor): Original, unprocessed images. Returns: (list[Results]): A list of Results objects containing the post-processed bounding boxes, confidence scores, and class labels. Nr)dimT)Zkeepdim)device.)pathnamesZboxes) isinstancelisttupleshapesplitrZconvert_torch2numpy_batchzipbatchZ xywh2xyxymaxZsqueezeargsconfclassestorchZtensorr anycatappendrmodelr)selfpredsZimgZ orig_imgsndZbboxesZscoresresultsZbboxZscoreZorig_imgZimg_pathZ max_scoreclsidxpredZohowr(]/var/www/html/django/DPS/env/lib/python3.9/site-packages/ultralytics/models/rtdetr/predict.py postprocess"s&     "zRTDETRPredictor.postprocesscs"t|jdddfdd|DS)a Pre-transforms the input images before feeding them into the model for inference. The input images are letterboxed to ensure a square aspect ratio and scale-filled. The size must be square(640) and scaleFilled. Args: im (list[np.ndarray] |torch.Tensor): Input images of shape (N,3,h,w) for tensor, [(h,w,3) x N] for list. Returns: (list): List of pre-transformed images ready for model inference. FT)autoZ scaleFillcsg|]}|dqS))imager().0xZ letterboxr(r) Tz1RTDETRPredictor.pre_transform..)rZimgsz)r Zimr(r/r) pre_transformHs zRTDETRPredictor.pre_transformN)__name__ __module__ __qualname____doc__r*r2r(r(r(r)r s&r) rZultralytics.data.augmentrZultralytics.engine.predictorrZultralytics.engine.resultsrZultralytics.utilsrrr(r(r(r)s