/j JddlmZddlmZddlmZmZGddeZdS)) BasePredictor)Results)nmsopsc:eZdZdZdZedZdZdZdS)DetectionPredictora5A class extending the BasePredictor class for prediction based on a detection model. This predictor specializes in object detection tasks, processing model outputs into meaningful detection results with bounding boxes and class predictions. Attributes: args (namespace): Configuration arguments for the predictor. model (nn.Module): The detection model used for inference. batch (list): Batch of images and metadata for processing. Methods: postprocess: Process raw model predictions into detection results. construct_results: Build Results objects from processed predictions. construct_result: Create a single Result object from a prediction. get_obj_feats: Extract object features from the feature maps. Examples: >>> from ultralytics.utils import ASSETS >>> from ultralytics.models.yolo.detect import DetectionPredictor >>> args = dict(model="yolo26n.pt", source=ASSETS) >>> predictor = DetectionPredictor(overrides=args) >>> predictor.predict_cli() c ~t|dddu}tj||jj|jj|jj|jj|jj|jj dkrdnt|j j t|j dd|jj dk| }t|tstj|d ddd f}|r)||j|d }|d}|j|||fi|}|rt)||D] \}} | |_ |S) apPost-process predictions and return a list of Results objects. This method applies non-maximum suppression to raw model predictions and prepares them for visualization and further analysis. Args: preds (torch.Tensor): Raw predictions from the model. img (torch.Tensor): Processed input image tensor in model input format. orig_imgs (torch.Tensor | list): Original input images before preprocessing. **kwargs (Any): Additional keyword arguments. Returns: (list): List of Results objects containing the post-processed predictions. Examples: >>> predictor = DetectionPredictor(overrides=dict(model="yolo26n.pt")) >>> results = predictor.predict("path/to/image.jpg") >>> processed_results = predictor.postprocess(preds, img, orig_imgs) _featsNdetectrend2endFobb)max_detncr rotated return_idxs.)getattrrnon_max_suppressionargsconfiouclasses agnostic_nmsrtasklenmodelnames isinstancelistrconvert_torch2numpy_batch get_obj_featsr construct_resultszipfeats) selfpredsimg orig_imgskwargs save_feats obj_featsresultsrfs k/home/longshao/multi-rider-rag/.venv/lib/python3.11/site-packages/ultralytics/models/yolo/detect/predict.py postprocesszDetectionPredictor.postprocess!sM(T8T22$> '  IN IM I  I "I%INh..qqC 8H4I4IDJ 599INe+"    )T** L5i@@dddKI  **4;aAAI!HE($(YII&II  GY//  1cddl}td|D|fd|Dd}dt||DS)z.Extract object features from the feature maps.rNc30K|]}|jdVdS)rNshape).0xs r0 z3DetectionPredictor.get_obj_feats..Ws(..q ......r2c g|]]}|dddd|jdd|jdzd^S)rrrdim)permutereshaper6mean)r7r8ss r0 z4DetectionPredictor.get_obj_feats..Ysb o o o`aQYYq!Q " " * *171:r1agajAo N N S SXZ S [ [ o o or2rr=cBg|]\}}|jdr||ngS)rr5)r7r%idxs r0rCz4DetectionPredictor.get_obj_feats..[s/ZZZzuccil2c ZZZr2)torchmincatr$) feat_mapsidxsrFr,rBs @r0r"z DetectionPredictor.get_obj_featsRs  ..I... . .II o o o oen o o ouv  [ZSTXEYEYZZZZr2cXfdt||jdDS)aConstruct a list of Results objects from model predictions. Args: preds (list[torch.Tensor]): List of predicted bounding boxes and scores for each image. img (torch.Tensor): Batch of preprocessed images used for inference. orig_imgs (list[np.ndarray]): List of original images before preprocessing. Returns: (list[Results]): List of Results objects containing detection information for each image. cHg|]\}}}|||S)construct_result)r7predorig_imgimg_pathr(r&s r0rCz8DetectionPredictor.construct_results..hsC   (h  ! !$Xx @ @   r2r)r$batch)r&r'r(r)s` ` r0r#z$DetectionPredictor.construct_results]sF     ,/y$*Q-,P,P    r2c tj|jdd|ddddf|j|ddddf<t|||jj|ddddfS)a%Construct a single Results object from one image prediction. Args: pred (torch.Tensor): Predicted boxes and scores with shape (N, 6) where N is the number of detections. img (torch.Tensor): Preprocessed image tensor used for inference. orig_img (np.ndarray): Original image before preprocessing. img_path (str): Path to the original image file. Returns: (Results): Results object containing the original image, image path, class names, and scaled bounding boxes. r;N)pathrboxes)r scale_boxesr6rrr)r&rOr(rPrQs r0rNz#DetectionPredictor.construct_resultmsvocimT!!!RaR%[(.QQQQQU xhdj6FdSTSTSTVXWXVXSXkZZZZr2N) __name__ __module__ __qualname____doc__r1 staticmethodr"r#rNrMr2r0rrso0///b[[\[   [ [ [ [ [r2rN)ultralytics.engine.predictorrultralytics.engine.resultsrultralytics.utilsrrrrMr2r0ras766666......&&&&&&&&r[r[r[r[r[r[r[r[r[r[r2