o W h@s8ddlmZddlmZddlmZGdddeZdS)) BasePredictor)Results)opsc@s0eZdZdZddZddZddZdd Zd S) DetectionPredictora A 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. Examples: >>> from ultralytics.utils import ASSETS >>> from ultralytics.models.yolo.detect import DetectionPredictor >>> args = dict(model="yolo11n.pt", source=ASSETS) >>> predictor = DetectionPredictor(overrides=args) >>> predictor.predict_cli() c Kst|dd}tj||jj|jj|jj|jj|jj|jj dkr dnt |j j t|j dd|jj dk|d }t |ts>t|}|rM||j|d}|d}|j|||fi|}|rgt||D]\}} | |_q_|S) ay Post-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="yolov8n.pt")) >>> results = predictor.predict("path/to/image.jpg") >>> processed_results = predictor.postprocess(preds, img, orig_imgs) save_featsFdetectrend2endobb)max_detncrrotated return_idxs)getattrrnon_max_suppressionargsconfiouclasses agnostic_nmsr tasklenmodelnames isinstancelistconvert_torch2numpy_batch get_obj_feats_featsconstruct_resultszipfeats) selfpredsimg orig_imgskwargsr obj_featsresultsrfr+Z/var/www/vscode/kcb/lib/python3.10/site-packages/ultralytics/models/yolo/detect/predict.py postprocess!s.    zDetectionPredictor.postprocesscsVddlm}ddl}|dd|D|jfdd|Ddd}d dt||DS) z.Extract object features from the feature maps.r)gcdNcSsg|]}|jdqS)r)shape.0xr+r+r, Ysz4DetectionPredictor.get_obj_feats..c s@g|]}|dddd|jdd|jdjddqS)rrdim)permutereshaper/meanr0sr+r,r3[s@rr7cSsg|]\}}||qSr+r+)r1r!idxr+r+r,r3]s)mathr.torchcatr )r" feat_mapsidxsr.r@r'r+r<r,rSs z DetectionPredictor.get_obj_featscs"fddt||jdDS)a Construct 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. cs"g|] \}}}|||qSr+)construct_result)r1predorig_imgimg_pathr$r"r+r,r3ksz8DetectionPredictor.construct_results..r)r batch)r"r#r$r%r+rHr,r_s z$DetectionPredictor.construct_resultscCs^t|jdd|ddddf|j|ddddf<t|||jj|ddddfdS)a. Construct a single Results object from one image prediction. Args: pred (torch.Tensor): Predicted boxes and scores with shape (N, 6) where N is the number of detections. img (torch.Tensor): Preprocessed image tensor used for inference. orig_img (np.ndarray): Original image before preprocessing. img_path (str): Path to the original image file. Returns: (Results): Results object containing the original image, image path, class names, and scaled bounding boxes. r4N)pathrboxes)r scale_boxesr/rrr)r"rEr$rFrGr+r+r,rDps: $z#DetectionPredictor.construct_resultN)__name__ __module__ __qualname____doc__r-rrrDr+r+r+r,rs 2 rN)ultralytics.engine.predictorrultralytics.engine.resultsrultralytics.utilsrrr+r+r+r,s