h\PddlZddlmZddlmZmZmZmZmZm Z ddl Z ddl Z ddl mZmZmZddlmZddlmZmZddlmZddlmZmZmZdd lmZGd d eZy) N)Path)AnyDictListOptionalTupleUnion)build_dataloaderbuild_yolo_dataset converter) BaseValidator)LOGGERops)check_requirements)ConfusionMatrix DetMetricsbox_iou) plot_imagesc(eZdZdZd-d.fd ZdeeefdeeeffdZde jjddfdZ defd Z d e jdeeee jffd Zd edeeefdeeeffd Zdeee jfdeee jffdZd eeee jfdeeefddfdZd.dZdeeeffdZd.dZd eee jfdeeefdeeej2ffdZd/dededeede j8j:j<fdZdedede j8j:j@fdZ!deeefdeddfdZ" d0deeefd eeee jfdedeeddf dZ#deee jfd e$d!e%eefd"e&ddf d#Z'deee jfd$eeefddfd%Z(d&eeefdeeeffd'Z) d1d&eeefd(ed)ed*e*eeefd+e*eeefdeeeff d,Z+xZ,S)2DetectionValidatora~ A class extending the BaseValidator class for validation based on a detection model. This class implements validation functionality specific to object detection tasks, including metrics calculation, prediction processing, and visualization of results. Attributes: is_coco (bool): Whether the dataset is COCO. is_lvis (bool): Whether the dataset is LVIS. class_map (List[int]): Mapping from model class indices to dataset class indices. metrics (DetMetrics): Object detection metrics calculator. iouv (torch.Tensor): IoU thresholds for mAP calculation. niou (int): Number of IoU thresholds. lb (List[Any]): List for storing ground truth labels for hybrid saving. jdict (List[Dict[str, Any]]): List for storing JSON detection results. stats (Dict[str, List[torch.Tensor]]): Dictionary for storing statistics during validation. Examples: >>> from ultralytics.models.yolo.detect import DetectionValidator >>> args = dict(model="yolo11n.pt", data="coco8.yaml") >>> validator = DetectionValidator(args=args) >>> validator() Nreturnc t|||||d|_d|_d|_d|j _tjddd|_ |jj|_ t|_ y)a Initialize detection validator with necessary variables and settings. Args: dataloader (torch.utils.data.DataLoader, optional): Dataloader to use for validation. save_dir (Path, optional): Directory to save results. args (Dict[str, Any], optional): Arguments for the validator. _callbacks (List[Any], optional): List of callback functions. FNdetectg?gffffff? )super__init__is_cocois_lvis class_mapargstasktorchlinspaceiouvnumelniourmetrics)self dataloadersave_dirr _callbacks __class__s `/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/ultralytics/models/yolo/detect/val.pyrzDetectionValidator.__init__+sg XtZ@  ! NN3b1 IIOO% !| batchc |dj|jd|d<|jjr|djn|dj dz |d<dD]#}||j|j||<%|S)z Preprocess batch of images for YOLO validation. Args: batch (Dict[str, Any]): Batch containing images and annotations. Returns: (Dict[str, Any]): Preprocessed batch. imgT) non_blocking>clsbboxes batch_idx)todevicer halffloat)r(r/ks r- preprocesszDetectionValidator.preprocess>sU|t{{Fe /3yy~~e ))+5>#aΛ4QU1a[4"1a[    5sD<rc|jdz }|jddz |jrdnd|jjdz }|j |||S)a Evaluate YOLO output in JSON format and return performance statistics. Args: stats (Dict[str, Any]): Current statistics dictionary. Returns: (Dict[str, Any]): Updated statistics dictionary with COCO/LVIS evaluation results. zpredictions.jsonr annotationszinstances_val2017.jsonlvis_v1_z.json)r*rFrr rH coco_evaluate)r(r pred_json anno_jsons r- eval_jsonzDetectionValidator.eval_jsonshMM$66 IIf  +/<<'x GXX]=^ `  !!%I>>r.rr iou_typessuffixc  |jjr7|js |jrt |j rt jd|d|d ||fD]}|jrJ|dt|tr|gn|}t|tr|gn|}tdddl m }m}||} | j|} t!|D]M\} } || | | |jt j} |j"j$j&Dcgc] }t)t+|j,"c}| j._| j3| j5| j7| j8d |d || dd <| j8d |d || dd <|js| j8d|d|| dd <| j8d|d|| dd <| j8d|d|| dd <P|jr|d|d<|S|Scc}w#t:$r#}t j<d|Yd}~|Sd}~wwxYw)az Evaluate COCO/LVIS metrics using faster-coco-eval library. Performs evaluation using the faster-coco-eval library to compute mAP metrics for object detection. Updates the provided stats dictionary with computed metrics including mAP50, mAP50-95, and LVIS-specific metrics if applicable. Args: stats (Dict[str, Any]): Dictionary to store computed metrics and statistics. pred_json (str | Path]): Path to JSON file containing predictions in COCO format. anno_json (str | Path]): Path to JSON file containing ground truth annotations in COCO format. iou_types (str | List[str]]): IoU type(s) for evaluation. Can be single string or list of strings. Common values include "bbox", "segm", "keypoints". Defaults to "bbox". suffix (str | List[str]]): Suffix to append to metric names in stats dictionary. Should correspond to iou_types if multiple types provided. Defaults to "Box". Returns: (Dict[str, Any]): Updated stats dictionary containing the computed COCO/LVIS evaluation metrics. z' Evaluating faster-coco-eval mAP using z and z...z file not foundzfaster-coco-eval>=1.6.7r)COCOCOCOeval_faster)iouType lvis_styleprint_functionAP_50zmetrics/mAP50()AP_allzmetrics/mAP50-95(APrz metrics/APr(APcz metrics/APc(APfz metrics/APf(zmetrics/mAP50-95(B)fitnessz faster-coco-eval unable to run: N)r rRrrrQrXrris_filerIrJrfaster_coco_evalrrloadResrr)rim_filesrrrparamsimgIdsevaluate accumulate summarize stats_as_dict Exceptionr)r(rrrrrrwrrannorriou_typerSes r-rz DetectionValidator.coco_evaluatesw6 99  DLLDLLc$**o KKB9+US\R]]`a b G"I->A99;=1#_(==;>+5i+EYK9 %/%<&&"#<=BI||I.#,Y#7YKAx)dH^d^i^iCEIOOD[D[DdDd(eqT!W\\):(eCJJ%LLNNN$MMO?B>O>OPW>XEN6!9Q<.:;ADARARS[A\E-fQil^1=>||@C@Q@QRW@X VAYq\N!<=@C@Q@QRW@X VAYq\N!<=@C@Q@QRW@X VAYq\N!<=!Y$<<',-B'CE)$ u %)f  G!A!EFF  Gs9$I"y%((//ydy0l#lkk$tCU *Dc5<<.?)@$A*$sTWx.*]a*X. )4S> )(]Dell):$;]DcN]W[\_acakak\kWl] hc h hXc] h^c^i^i^n^n^v^v h `3 `C `EKKDTDTD_D_ ` d38n # $ "nr #s(^ ,0c5<<6G1H,I OR ]efi]j  :.$sELL'8"9.d.SXY\^aYaSb.jn.sw.&$sELL'8"94S>VZ:?tCH~?$sCx.?.,2(- =CH~== = d3i( = c49n% = c3h=r.r)rLpathlibrtypingrrrrrr rrr"ultralytics.datar r r ultralytics.engine.validatorr ultralytics.utilsrrultralytics.utils.checksrultralytics.utils.metricsrrrultralytics.utils.plottingrrrcr.r-r2s? :: LL6)7JJ2GGr.