FPhdZddlZddlZddlmZddlmZddlZ ddl Z ddl m Z m Z mZmZe j gddz Zd%dZd&d Zd'd Zd&d Zd&d Zd(d ZGddZd)dZeedddfdZeedddddfdZdZddedddfdZGdde ZGdde ZGdd e Z Gd!d"e Z!Gd#d$e Z"y)*zModel validation metrics.N)Path)LOGGER SimpleClass TryExcept plt_settings)gp= ף??rffffff?r HzG?r ףp= ?r ףp= ?r Q?r ףp= ?r{Gz?rg$@Fc|j\}}}}|j\}} } } tj|dddf| tj|dddf|z j dtj|dddf| tj|dddf| z j dz} | |z | | z z} |r||z ||z z}| |dddfz| z } | | |zz S)a> Calculate the intersection over box2 area given box1 and box2. Boxes are in x1y1x2y2 format. Args: box1 (np.array): A numpy array of shape (n, 4) representing n bounding boxes. box2 (np.array): A numpy array of shape (m, 4) representing m bounding boxes. iou (bool): Calculate the standard iou if True else return inter_area/box2_area. eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. Returns: (np.array): A numpy array of shape (n, m) representing the intersection over box2 area. Nr)Tnpminimummaximumclip)box1box2iouepsb1_x1b1_y1b1_x2b1_y2b2_x1b2_y1b2_x2b2_y2 inter_areaarea box1_areas dC:\Users\daisl\Desktop\realtime-object-detection\venv\Lib\site-packages\ultralytics/utils/metrics.pybbox_ioar&s"&E5%!%E5%**U1d7^U3bjjq$wQV6WW]]^_`**U1d7^U3bjjq$wQV6WW]]^_`aJ EMeem ,D U]uu}5 i4((:5  $$c|jdjdd|jdjddc\}}\}}tj||tj||z j dj d}|||z j d||z j dz|z |zz S)a_ Calculate intersection-over-union (IoU) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Based on https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py Args: box1 (torch.Tensor): A tensor of shape (N, 4) representing N bounding boxes. box2 (torch.Tensor): A tensor of shape (M, 4) representing M bounding boxes. eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. Returns: (torch.Tensor): An NxM tensor containing the pairwise IoU values for every element in box1 and box2. r) unsqueezechunktorchminmaxclamp_prod)rrra1a2b1b2inters r%box_iour71s *00A6q8I8O8OPQST8UHRhr2 YYr2 2r!2 2 : :1 = B B1 EE R"WNN1%bq(99EACG HHr'c|ru|jdd|jddc\}}} } \} } } }| dz | dz | dz |dz f\}}}}||z ||z||z ||zf\}}}}| |z | |z| |z | |zf\}}}}nH|jdd\}}}}|jdd\}}}}||z ||z |z} } ||z ||z |z}} |j||j|z jd|j||j|z jdz}| | z| |zz|z |z}||z }|s|s|r%|j||j|z }|j||j|z }|s|r|dz|dzz|z} ||z|z |z dz||z|z |z dzzdz }!|rdtj dzz t j| |z t j| | z z jdz}"t j5|"|"|z d|zzz }#ddd||!| z |"#zzz S||!| z z S||z|z}$||$|z |$z z S|S#1swY4xYw)a Calculate Intersection over Union (IoU) of box1(1, 4) to box2(n, 4). Args: box1 (torch.Tensor): A tensor representing a single bounding box with shape (1, 4). box2 (torch.Tensor): A tensor representing n bounding boxes with shape (n, 4). xywh (bool, optional): If True, input boxes are in (x, y, w, h) format. If False, input boxes are in (x1, y1, x2, y2) format. Defaults to True. GIoU (bool, optional): If True, calculate Generalized IoU. Defaults to False. DIoU (bool, optional): If True, calculate Distance IoU. Defaults to False. CIoU (bool, optional): If True, calculate Complete IoU. Defaults to False. eps (float, optional): A small value to avoid division by zero. Defaults to 1e-7. Returns: (torch.Tensor): IoU, GIoU, DIoU, or CIoU values depending on the specified flags. r*rr)N) r,rrr0mathpir-atanpowno_grad)%rrxywhGIoUDIoUCIoUrx1y1w1h1x2y2w2h2w1_h1_w2_h2_rrrrrr rr!r6unionrcwchc2rho2valphac_areas% r%bbox_iourXHs& -1ZZ2-> 1b@Q*RR*2r2r!VR!VR!VR!V;S#s%'#XrCxc28%K"ueU%'#XrCxc28%K"ueU%)ZZ2%6"ueU%)ZZ2%6"ueU  3B  3B]]5 !EMM%$8 8 @ @ C ]]5 !EMM%$8 8 @ @ C DE Gb2g  % +E %-C tt ]]5 !EMM%$8 8 ]]5 !EMM%$8 8 4q27"S(BU]U*U2q8EEMEA IIqbMHQW- - 2 22 6(,,r:J1d7:SVY:Y ZZr'cdd|zz d|zfS)a Computes smoothed positive and negative Binary Cross-Entropy targets. This function calculates positive and negative label smoothing BCE targets based on a given epsilon value. For implementation details, refer to https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441. Args: eps (float, optional): The epsilon value for label smoothing. Defaults to 0.1. Returns: (tuple): A tuple containing the positive and negative label smoothing BCE targets. ?g?)rs r% smooth_BCEros s?C#I %%r'cheZdZdZd dZdZdZdZdZe de d d Z d Z y) ConfusionMatrixa A class for calculating and updating a confusion matrix for object detection and classification tasks. Attributes: task (str): The type of task, either 'detect' or 'classify'. matrix (np.array): The confusion matrix, with dimensions depending on the task. nc (int): The number of classes. conf (float): The confidence threshold for detections. iou_thres (float): The Intersection over Union threshold. c||_|jdk(rtj|dz|dzfntj||f|_||_|dvrdn||_||_y)z)Initialize attributes for the YOLO model.detectr))NgMbP?rN)taskrzerosmatrixncconf iou_thres)selfrwrxryrts r%__init__zConfusionMatrix.__init__sa 48II4IbhhQQ/0rxxY[]_X`Oa  M1Dt "r'c2tj|dddftj|}}t|jj |jj D]\}}|j ||xxdz cc<!y)z Update confusion matrix for classification task. Args: preds (Array[N, min(nc,5)]): Predicted class labels. targets (Array[N, 1]): Ground truth class labels. Nrr))r-catzipcpunumpyrv)rzpredstargetspts r%process_cls_predsz!ConfusionMatrix.process_cls_predsst5)!Q$/71Cw ))+W[[]-@-@-BCDAq KKN1  " Dr'c|;|j}|D]%}|j|j|fxxdz cc<'y||dddf|jkD}|dddfj}|dddfj}t |ddddf|ddddf}t j ||jkD}|djdrt jt j|d||d|dfdddffdjj}|djddkDr||dddfjddd}|tj|dddfd d}||dddfjddd}|tj|dddfd d}ntj d }|jddkD} |j#j%t\} } } t'|D]]\} }| | k(}| r.t)|dk(r |j|| ||fxxdz cc<;|j|j|fxxdz cc<_| rFt'|D]7\} }t+| | k(r|j||jfxxdz cc<9yy) a Update confusion matrix for object detection task. Args: detections (Array[N, 6]): Detected bounding boxes and their associated information. Each row should contain (x1, y1, x2, y2, conf, class). labels (Array[M, 5]): Ground truth bounding boxes and their associated class labels. Each row should contain (class, x1, y1, x2, y2). Nr)r9rr*r:T) return_index)r)intrvrwrxr7r-whereryshaper}stackrrargsortruniqueru transposeastype enumerater[any)rz detectionslabels gt_classesgcdetection_classesrxmatchesnm0m1_ijdcs r% process_batchzConfusionMatrix.process_batchs  J  DGGRK(A-(!  1a4 0499 <= AqD\%%' &q!t,002fQUmZ2A2%67 KKdnn, - Q4::a=iiQ!2C!ad OAtG4L MqQUUW]]_Gtzz!}q !'!Q$-"7"7"9$B$"?@!"))GAqDM"Ma"PQ!'!Q$-"7"7"9$B$"?@!"))GAqDM"Ma"PQhhv&G MM! q %%'..s3 Bz*EAraASVq[ -be4b89Q>9 DGGRK(A-( + "#45227|KKDGG ,1,6 r'c|jS)zReturns the confusion matrix.)rvrzs r%rvzConfusionMatrix.matrixs {{r'c|jj}|jjd|z }|jdk(r |dd|ddfS||fS)z+Returns true positives and false positives.r)rsNr:)rvdiagonalr[rt)rztpfps r%tp_fpzConfusionMatrix.tp_fp sV [[ ! ! # [[__Q " $%)YY(%:3BCR!HRHr'u+WARNING ⚠️ ConfusionMatrix plot failureNc ddl}|j|r.|jjdjdddzndz }tj ||dk<t jdddd \}}|jt|} } |j| d krd nd d| cxkxrdkncxr| | k(} | rt|dgznd} tj5tjd|j||| dkddid|rdnddd| |  j!dddddd|zz} |j#d|j%d|j'| t)|| j+j-dd d!z }|j/|d"#t j0||r ||yy#1swYxYw)$a Plot the confusion matrix using seaborn and save it to a file. Args: normalize (bool): Whether to normalize the confusion matrix. save_dir (str): Directory where the plot will be saved. names (tuple): Names of classes, used as labels on the plot. on_plot (func): An optional callback to pass plots path and data when they are rendered. rNr)r:g& .>g{Gzt?) Tfigsize tight_layout2rmg?) font_scalec backgroundautoignoresizeBlues.2fz.0f) axannot annot_kwscmapfmtsquarevmin xticklabels yticklabels)r)r)r)zConfusion Matrixz NormalizedTrue Predicted rz.pngdpi)seabornrvr[reshapernanpltsubplotsrwlensetlistwarningscatch_warnings simplefilterheatmap set_facecolor set_xlabel set_ylabel set_titlerlowerreplacesavefigclose)rz normalizesave_dirnameson_plotsnarrayfigrrwnnr ticklabelstitle plot_fnames r%plotzConfusionMatrix.plots  Y  2 : :1b AD H\]^!vveem,,q!W4HR#e*B b#c2b+2+-B"H7=d5k\N26  $ $ &  ! !( + JJu"W!1"&#$-55"#-#-  /0=}Y/G'#]Y%>> f k" U(^)>)>sC)H(I&NN  JC ( #  J  )' &s $A GGc t|jdzD]A}tjdj t t |j|Cy)z*Print the confusion matrix to the console.r)rN)rangerwrinfojoinmapstrrvrzrs r%printzConfusionMatrix.print?s=tww{#A KKS$++a.!9: ;$r')rg?rs)TrnN) __name__ __module__ __qualname____doc__r{rrrvrrrrrrnr'r%rqrqsL # #,2\I<=^) >) V.JG K$ B!62GGB av=WZ\]^`a]aZbZgZgZi=iGjMM(MM+KK1KK1IIYLI9LL)*KKcK"IIcNr'z mc_curve.png ConfidenceMetricc tjdddd\}}dt|cxkrdkr0nn-t|D]\} } |j || d||  n|j ||j dd t |jdd } |j || d d d | jdd|| jd|j||j||jdd|jdd|jdd|j|d|j!|dtj"||r ||yy)z Plots a metric-confidence curve.r)rTrrrr r r皙?rrz all classes rz at r rrrrz-Confidence CurverrN)rrrrrrrrr/argmaxrrrrrrrr) rrrrxlabelylabelrrrrrs r% plot_mc_curver(fsIll1adCGC3u:bMDAq GGBQq G <" BDDAV4rwwqz4 AGGBQfl15573-tTVWXW_W_WaTbcfSg4hGiMM&MM&KK1KK1IIYLI9LLF8,-.KKcK"IIcNr'c(tjdg|dgf}tjdg|dgf}tjtjj tj|}d}|dk(rCtj ddd}tj tj||||}nKtj|dd|ddk7d}tj||dz||z ||dzz}|||fS) ay Compute the average precision (AP) given the recall and precision curves. Args: recall (list): The recall curve. precision (list): The precision curve. Returns: (float): Average precision. (np.ndarray): Precision envelope curve. (np.ndarray): Modified recall curve with sentinel values added at the beginning and end. rrminterprr)eNr:) rrflipr accumulatelinspacetrapzr*rr[)recall precisionmrecmpremethodrrrs r% compute_apr5s >>C5&3%0 1D >>C5)cU3 4D 772::((7 8DF  KK1c " XXbii4. 2 HHT!"Xcr* +A . VVT!a%[47*d1q5k9 : tT>r'gؗҜ*A Mfeeg !8sax 2a5y  #ell1oc "iiT!WHfQTlC 39% iiT!WHi1oAF rxx{#A$.vad|Yq!t_$M !Br1uItTQ""299Qd#;<$)+2((;'K7{W$'(9C(?@H ;;= @=41aA,?Q=E @ 5! "E ab(x|5L*Le]dea8 .E#EuUYcjka(x{-C"CUS^hopa(x{-C"CUS[elmx}}Q%,,.Aq!t}gadmXad^"qA b& B C.2  $ $ &B r1aR!6!6s!;WgxYZ\g gg As ' L>4L>ceZdZdZddZedZedZedZedZ edZ ed Z ed Z d Z d Zed ZdZdZedZedZy)r"a Class for computing evaluation metrics for YOLOv8 model. Attributes: p (list): Precision for each class. Shape: (nc,). r (list): Recall for each class. Shape: (nc,). f1 (list): F1 score for each class. Shape: (nc,). all_ap (list): AP scores for all classes and all IoU thresholds. Shape: (nc, 10). ap_class_index (list): Index of class for each AP score. Shape: (nc,). nc (int): Number of classes. Methods: ap50(): AP at IoU threshold of 0.5 for all classes. Returns: List of AP scores. Shape: (nc,) or []. ap(): AP at IoU thresholds from 0.5 to 0.95 for all classes. Returns: List of AP scores. Shape: (nc,) or []. mp(): Mean precision of all classes. Returns: Float. mr(): Mean recall of all classes. Returns: Float. map50(): Mean AP at IoU threshold of 0.5 for all classes. Returns: Float. map75(): Mean AP at IoU threshold of 0.75 for all classes. Returns: Float. map(): Mean AP at IoU thresholds from 0.5 to 0.95 for all classes. Returns: Float. mean_results(): Mean of results, returns mp, mr, map50, map. class_result(i): Class-aware result, returns p[i], r[i], ap50[i], ap[i]. maps(): mAP of each class. Returns: Array of mAP scores, shape: (nc,). fitness(): Model fitness as a weighted combination of metrics. Returns: Float. update(results): Update metric attributes with new evaluation results. NcXg|_g|_g|_g|_g|_d|_y)zTInitializes a Metric instance for computing evaluation metrics for the YOLOv8 model.rN)rrOrPall_apap_class_indexrwrs r%r{zMetric.__init__s-  r'cVt|jr|jdddfSgS)z Returns the Average Precision (AP) at an IoU threshold of 0.5 for all classes. Returns: (np.ndarray, list): Array of shape (nc,) with AP50 values per class, or an empty list if not available. Nr)rrTrs r%ap50z Metric.ap50&s'%( $4t{{1a4 <"B>r'cdt|jr|jjSdS)z Returns the Mean Precision of all classes. Returns: (float): The mean precision of all classes. r)rrrrs r%mpz Metric.mp:#!$DFF tvv{{}44r'cdt|jr|jjSdS)z Returns the Mean Recall of all classes. Returns: (float): The mean recall of all classes. r)rrOrrs r%mrz Metric.mrDr\r'crt|jr!|jdddfjSdS)z Returns the mean Average Precision (mAP) at an IoU threshold of 0.5. Returns: (float): The mAP50 at an IoU threshold of 0.5. NrrrYrs r%map50z Metric.map50N0,/t{{+;t{{1a4 %%'DDr'crt|jr!|jdddfjSdS)z Returns the mean Average Precision (mAP) at an IoU threshold of 0.75. Returns: (float): The mAP50 at an IoU threshold of 0.75. NrrrYrs r%map75z Metric.map75Xrar'cdt|jr|jjSdS)z Returns the mean Average Precision (mAP) over IoU thresholds of 0.5 - 0.95 in steps of 0.05. Returns: (float): The mAP over IoU thresholds of 0.5 - 0.95 in steps of 0.05. rrYrs r%rz Metric.mapbs'&)%5t{{!>3>r'c^|j|j|j|jgS)z+Mean of results, return mp, mr, map50, map.)r[r^r`rrs r% mean_resultszMetric.mean_resultsls!$**dhh77r'cv|j||j||j||j|fS)z6Class-aware result, return p[i], r[i], ap50[i], ap[i].)rrOrWrrs r% class_resultzMetric.class_resultps1vvay$&&)TYYq\4771:==r'ctj|j|jz}t |j D]\}}|j |||<|S)zMAP of each class.)rrurwrrrUr)rzmapsrrHs r%rjz Metric.mapstsNxx 488+d112DAqggajDG3 r'crgd}tj|j|zjS)z3Model fitness as a weighted combination of metrics.)rrr:g?)rrrfr[)rzws r%fitnesszMetric.fitness|s- **,-16688r'c |\ |_|_|_|_|_|_|_|_|_|_ y)a Updates the evaluation metrics of the model with a new set of results. Args: results (tuple): A tuple containing the following evaluation metrics: - p (list): Precision for each class. Shape: (nc,). - r (list): Recall for each class. Shape: (nc,). - f1 (list): F1 score for each class. Shape: (nc,). - all_ap (list): AP scores for all classes and all IoU thresholds. Shape: (nc, 10). - ap_class_index (list): Index of class for each AP score. Shape: (nc,). Side Effects: Updates the class attributes `self.p`, `self.r`, `self.f1`, `self.all_ap`, and `self.ap_class_index` based on the values provided in the `results` tuple. N) rrOrPrTrUrErFrMrrD)rzresultss r%updatez Metric.updates="% $+t/BDLRVR^`d`mosov r'cgS?Returns a list of curves for accessing specific metrics curves.rnrs r%curvesz Metric.curves  r'c|j|jddg|j|jddg|j|jddg|j|jddggS)rsrrr!r9)rrDrMrErFrs r%curves_resultszMetric.curves_resultssd$**HkBTWWdmm]ikoDp$,, kBTWWdll\hjrDsu ur'returnN)rrrrr{propertyrWrr[r^r`rcrrfrhrjrmrprtrwrnr'r%r"r"s4==??5555EEEE??8>9 %&uur'ceZdZdZeddddfddZdZedZd Z d Z ed Z ed Z ed Z edZedZedZy) DetMetricsa9 This class is a utility class for computing detection metrics such as precision, recall, and mean average precision (mAP) of an object detection model. Args: save_dir (Path): A path to the directory where the output plots will be saved. Defaults to current directory. plot (bool): A flag that indicates whether to plot precision-recall curves for each class. Defaults to False. on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None. names (tuple of str): A tuple of strings that represents the names of the classes. Defaults to an empty tuple. Attributes: save_dir (Path): A path to the directory where the output plots will be saved. plot (bool): A flag that indicates whether to plot the precision-recall curves for each class. on_plot (func): An optional callback to pass plots path and data when they are rendered. names (tuple of str): A tuple of strings that represents the names of the classes. box (Metric): An instance of the Metric class for storing the results of the detection metrics. speed (dict): A dictionary for storing the execution time of different parts of the detection process. Methods: process(tp, conf, pred_cls, target_cls): Updates the metric results with the latest batch of predictions. keys: Returns a list of keys for accessing the computed detection metrics. mean_results: Returns a list of mean values for the computed detection metrics. class_result(i): Returns a list of values for the computed detection metrics for a specific class. maps: Returns a dictionary of mean average precision (mAP) values for different IoU thresholds. fitness: Computes the fitness score based on the computed detection metrics. ap_class_index: Returns a list of class indices sorted by their average precision (AP) values. results_dict: Returns a dictionary that maps detection metric keys to their computed values. curves: TODO curves_results: TODO .FNrnc||_||_||_||_t |_ddddd|_d|_y)zfInitialize a DetMetrics instance with a save directory, plot flag, callback function, and class names.r preprocess inferenceloss postprocessrsN)rrrrr"boxspeedrtrzrrrrs r%r{zDetMetrics.__init__s?     8$'c3WZ[  r'c t|||||j|j|j|jdd}t |j|j _|j j|y)zBProcess predicted results for object detection and update metrics.)rrrrr*N) rQrrrrrrrwrp)rzrrxr?r@ros r%processzDetMetrics.processsdr#')$(II(, %)ZZ'+||567R9$**o   r'c gdS)z6Returns a list of keys for accessing specific metrics.)metrics/precision(B)metrics/recall(B)metrics/mAP50(B)metrics/mAP50-95(B)rnrs r%keyszDetMetrics.keyss hgr'c6|jjS)zSCalculate mean of detected objects & return precision, recall, mAP50, and mAP50-95.)rrfrs r%rfzDetMetrics.mean_resultssxx$$&&r'c8|jj|S)zaReturn the result of evaluating the performance of an object detection model on a specific class.)rrhrs r%rhzDetMetrics.class_resultsxx$$Q''r'c.|jjS)z6Returns mean Average Precision (mAP) scores per class.)rrjrs r%rjzDetMetrics.mapssxx}}r'c6|jjS)z"Returns the fitness of box object.)rrmrs r%rmzDetMetrics.fitnesssxx!!r'c.|jjS)z.Returns the average precision index per class.rrUrs r%rUzDetMetrics.ap_class_indexxx&&&r'ctt|jdgz|j|jgzS)BReturns dictionary of computed performance metrics and statistics.rmr>r~rrfrmrs r% results_dictzDetMetrics.results_dict5C YK/1B1B1D ~1UVWWr'c gdS)rs)Precision-Recall(B)F1-Confidence(B)Precision-Confidence(B)Recall-Confidence(B)rnrs r%rtzDetMetrics.curvess nmr'c.|jjSr)rrwrs r%rwzDetMetrics.curves_resultsrr'rxrrrrrr{rrzrrfrhrjrmrUrrtrwrnr'r%r|r|s>!%S t2 !hh'(""''XXnn''r'r|ceZdZdZeddddfddZdZedZd Z d Z ed Z ed Z ed Z edZedZedZy)SegmentMetricsa3 Calculates and aggregates detection and segmentation metrics over a given set of classes. Args: save_dir (Path): Path to the directory where the output plots should be saved. Default is the current directory. plot (bool): Whether to save the detection and segmentation plots. Default is False. on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None. names (list): List of class names. Default is an empty list. Attributes: save_dir (Path): Path to the directory where the output plots should be saved. plot (bool): Whether to save the detection and segmentation plots. on_plot (func): An optional callback to pass plots path and data when they are rendered. names (list): List of class names. box (Metric): An instance of the Metric class to calculate box detection metrics. seg (Metric): An instance of the Metric class to calculate mask segmentation metrics. speed (dict): Dictionary to store the time taken in different phases of inference. Methods: process(tp_m, tp_b, conf, pred_cls, target_cls): Processes metrics over the given set of predictions. mean_results(): Returns the mean of the detection and segmentation metrics over all the classes. class_result(i): Returns the detection and segmentation metrics of class `i`. maps: Returns the mean Average Precision (mAP) scores for IoU thresholds ranging from 0.50 to 0.95. fitness: Returns the fitness scores, which are a single weighted combination of metrics. ap_class_index: Returns the list of indices of classes used to compute Average Precision (AP). results_dict: Returns the dictionary containing all the detection and segmentation metrics and fitness score. r}FNrnc||_||_||_||_t |_t |_ddddd|_d|_y)zjInitialize a SegmentMetrics instance with a save directory, plot flag, callback function, and class names.rrsegmentN) rrrrr"rsegrrtrs r%r{zSegmentMetrics.__init__ sH     88$'c3WZ[  r'c t|||||j|j|j|jd dd}t |j|j _|j j|t|||||j|j|j|jd dd}t |j|j_|jj|y)a Processes the detection and segmentation metrics over the given set of predictions. Args: tp_b (list): List of True Positive boxes. tp_m (list): List of True Positive masks. conf (list): List of confidence scores. pred_cls (list): List of predicted classes. target_cls (list): List of target classes. MaskrrrrrAr*NBox) rQrrrrrrrwrpr)rztp_btp_mrxr?r@ results_mask results_boxs r%rzSegmentMetrics.process+s$D$($,$.)-,0LL-1]]*.**+134527 $**o   %"4#'#+#-(, +/<<,0MM)-*/1235 $**o   $r'c gdS)z-Returns a list of keys for accessing metrics.)rrrrzmetrics/precision(M)zmetrics/recall(M)zmetrics/mAP50(M)zmetrics/mAP50-95(M)rnrs r%rzSegmentMetrics.keysNd dr'cl|jj|jjzS)zBReturn the mean metrics for bounding box and segmentation results.)rrfrrs r%rfzSegmentMetrics.mean_resultsUs'xx$$&)>)>)@@@r'cp|jj||jj|zS)z;Returns classification results for a specified class index.)rrhrrs r%rhzSegmentMetrics.class_resultYs+xx$$Q'$((*?*?*BBBr'c\|jj|jjzS)zIReturns mAP scores for object detection and semantic segmentation models.)rrjrrs r%rjzSegmentMetrics.maps]sxx}}txx}},,r'cl|jj|jjzS)zDGet the fitness score for both segmentation and bounding box models.)rrmrrs r%rmzSegmentMetrics.fitnessbs)xx!DHH$4$4$666r'c.|jjS)z-Boxes and masks have the same ap_class_index.rrs r%rUzSegmentMetrics.ap_class_indexgrr'ctt|jdgz|j|jgzS)z9Returns results of object detection model for evaluation.rmrrs r%rzSegmentMetrics.results_dictlrr'c gdS)rs)rrrrzPrecision-Recall(M)zF1-Confidence(M)zPrecision-Confidence(M)zRecall-Confidence(M)rnrs r%rtzSegmentMetrics.curvesqj jr'c\|jj|jjzSr)rrwrrs r%rwzSegmentMetrics.curves_resultsxs#xx&&)@)@@@r'rxrrnr'r%rrs8!%S t2 !%Fdd AC--77''XXjj AAr'rceZdZdZeddddfdfd ZdZedZd Z d Z ed Z ed Z ed Z edZxZS) PoseMetricsa, Calculates and aggregates detection and pose metrics over a given set of classes. Args: save_dir (Path): Path to the directory where the output plots should be saved. Default is the current directory. plot (bool): Whether to save the detection and segmentation plots. Default is False. on_plot (func): An optional callback to pass plots path and data when they are rendered. Defaults to None. names (list): List of class names. Default is an empty list. Attributes: save_dir (Path): Path to the directory where the output plots should be saved. plot (bool): Whether to save the detection and segmentation plots. on_plot (func): An optional callback to pass plots path and data when they are rendered. names (list): List of class names. box (Metric): An instance of the Metric class to calculate box detection metrics. pose (Metric): An instance of the Metric class to calculate mask segmentation metrics. speed (dict): Dictionary to store the time taken in different phases of inference. Methods: process(tp_m, tp_b, conf, pred_cls, target_cls): Processes metrics over the given set of predictions. mean_results(): Returns the mean of the detection and segmentation metrics over all the classes. class_result(i): Returns the detection and segmentation metrics of class `i`. maps: Returns the mean Average Precision (mAP) scores for IoU thresholds ranging from 0.50 to 0.95. fitness: Returns the fitness scores, which are a single weighted combination of metrics. ap_class_index: Returns the list of indices of classes used to compute Average Precision (AP). results_dict: Returns the dictionary containing all the detection and segmentation metrics and fitness score. r}FNrnct||||||_||_||_||_t |_t |_ddddd|_ d|_ y)zXInitialize the PoseMetrics class with directory path, class names, and plotting options.rrposeN) superr{rrrrr"rrrrt)rzrrrr __class__s r%r{zPoseMetrics.__init__sZ 4/     8H $'c3WZ[  r'c t|||||j|j|j|jd dd}t |j|j _|j j|t|||||j|j|j|jd dd}t |j|j_|jj|y)a Processes the detection and pose metrics over the given set of predictions. Args: tp_b (list): List of True Positive boxes. tp_p (list): List of True Positive keypoints. conf (list): List of confidence scores. pred_cls (list): List of predicted classes. target_cls (list): List of target classes. Poserr*Nr) rQrrrrrrrwrpr)rzrtp_prxr?r@ results_posers r%rzPoseMetrics.processs$D$($,$.)-,0LL-1]]*.**+134527 4::  &"4#'#+#-(, +/<<,0MM)-*/1235 $**o   $r'c gdS)z'Returns list of evaluation metric keys.)rrrrzmetrics/precision(P)zmetrics/recall(P)zmetrics/mAP50(P)zmetrics/mAP50-95(P)rnrs r%rzPoseMetrics.keysrr'cl|jj|jjzS)z(Return the mean results of box and pose.)rrfrrs r%rfzPoseMetrics.mean_resultss'xx$$&)?)?)AAAr'cp|jj||jj|zS)z?Return the class-wise detection results for a specific class i.)rrhrrs r%rhzPoseMetrics.class_results+xx$$Q'$))*@*@*CCCr'c\|jj|jjzS)zTReturns the mean average precision (mAP) per class for both box and pose detections.)rrjrrs r%rjzPoseMetrics.mapssxx}}tyy~~--r'cl|jj|jjzS)zPComputes classification metrics and speed using the `targets` and `pred` inputs.)rrmrrs r%rmzPoseMetrics.fitnesss)yy  "TXX%5%5%777r'c gdS)rs)rrrrzPrecision-Recall(P)zF1-Confidence(P)zPrecision-Confidence(P)zRecall-Confidence(P)rnrs r%rtzPoseMetrics.curvesrr'c\|jj|jjzSr)rrwrrs r%rwzPoseMetrics.curves_resultss#xx&&)A)AAAr'rx)rrrrrr{rrzrrfrhrjrmrtrw __classcell__)rs@r%rr~s8!%S t2 !%Fdd BD..88jj BBr'rcneZdZdZd dZdZedZedZedZ edZ ed Z y) ClassifyMetricsa Class for computing classification metrics including top-1 and top-5 accuracy. Attributes: top1 (float): The top-1 accuracy. top5 (float): The top-5 accuracy. speed (Dict[str, float]): A dictionary containing the time taken for each step in the pipeline. Properties: fitness (float): The fitness of the model, which is equal to top-5 accuracy. results_dict (Dict[str, Union[float, str]]): A dictionary containing the classification metrics and fitness. keys (List[str]): A list of keys for the results_dict. Methods: process(targets, pred): Processes the targets and predictions to compute classification metrics. NcFd|_d|_ddddd|_d|_y)z&Initialize a ClassifyMetrics instance.rrrclassifyN)top1top5rrtrs r%r{zClassifyMetrics.__init__s(  $'c3WZ[  r'cVtj|tj|}}|dddf|k(j}tj|dddf|j dj fd}|j dj\|_|_ y)z%Target classes and predicted classes.Nrr))dim) r-r}floatrr/valuesrtolistrr)rzrpredcorrectaccs r%rzClassifyMetrics.process s $7);g1d7#t+224kk71a4='++a.*?*?@aH"xx{113 49r'c:|j|jzdz S)zr~rrrrmrs r%rzClassifyMetrics.results_dicts4C YK/$))TYY 1UVWWr'c ddgS)z5Returns a list of keys for the results_dict property.zmetrics/accuracy_top1zmetrics/accuracy_top5rnrs r%rzClassifyMetrics.keyss()@AAr'cgSrrrnrs r%rtzClassifyMetrics.curvesrur'cgSrrrnrs r%rwzClassifyMetrics.curves_results$rur'rx) rrrrr{rrzrmrrrtrwrnr'r%rrsy"4++XXBBr'r)FHz>)r)TFFFr)r:)r$)#rr;rpathlibrmatplotlib.pyplotpyplotrrrr-ultralytics.utilsrrrrr OKS_SIGMAr&r7rXr_rkrorqrr r(r5rQr"r|rrrrnr'r%rs'  JJ BHHl mpt t %@I.5p(&[, & I<I