^jgddlmZddlmZddlmZddlmZmZddl Z ddl mZ ddl mZddlmZddlmZdd lmZmZmZdd lmZdd lmZmZmZdd lmZm Z dd l!m"Z"erddl#Z$GddeZ%eGddZ&y)) annotations)deepcopy) dataclass) TYPE_CHECKINGAnyN)pyplot)ORIENTED_BOX_COORDINATES) Detections) box_iou_batchmask_iou_batchoriented_box_iou_batch)LEGACY_COLOR_PALETTE)AveragingMethodMetric MetricTarget)ObjectSizeCategoryget_detection_size_category)ensure_pandas_installedcBeZdZdZej ejf ddZddZ ddZ ddZ ddZ ddZ e ddZe dd Ze dd Zdd Zdd Z dd Z ddZy)Recalla Recall is a metric used to evaluate object detection models. It is the ratio of true positive detections to the total number of ground truth instances. We calculate it at different IoU thresholds. In simple terms, Recall is a measure of a model's completeness, calculated as: `Recall = TP / (TP + FN)` Here, `TP` is the number of true positives (correct detections), and `FN` is the number of false negatives (missed detections). Examples: ```pycon >>> import numpy as np >>> import supervision as sv >>> from supervision.metrics import Recall >>> predictions = sv.Detections( ... xyxy=np.array([[0, 0, 10, 10]]), ... class_id=np.array([0]), ... confidence=np.array([0.9]) ... ) >>> targets = sv.Detections( ... xyxy=np.array([[0, 0, 10, 10]]), ... class_id=np.array([0]) ... ) >>> recall_metric = Recall() >>> recall_result = recall_metric.update(predictions, targets).compute() >>> round(float(recall_result.recall_at_50), 2) 1.0 ``` ![example_plot]( https://media.roboflow.com/supervision-docs/metrics/recall_plot_example.png ){ align=center width="800" } c<||_||_g|_g|_y)a Initialize the Recall metric. Args: metric_target: The type of detection data to use. averaging_method: The averaging method used to compute the recall. Determines how the recall is aggregated across classes. N)_metric_targetaveraging_method_predictions_list _targets_list)self metric_targetrs e/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/supervision/metrics/recall.py__init__zRecall.__init__Es$, 035/1c g|_g|_y)zR Reset the metric to its initial state, clearing all stored data. N)rrrs rresetz Recall.resetXs"$r c4t|ts|g}t|ts|g}t|t|k7r$tdt|dt|d|jj ||j j ||S)a Add new predictions and targets to the metric, but do not compute the result. Args: predictions: The predicted detections. targets: The target detections. Returns: The updated metric instance. zThe number of predictions (z) and targets (z%) during the update must be the same.) isinstancelistlen ValueErrorrextendr)r predictionstargetss rupdatez Recall.update_s+t,&-K'4(iG { s7| +-c+.>-?@ \N*OQ  %%k2 !!'* r c,|j|j|j}|j|j|jtj \}}|j|||_|j|j|jtj\}}|j|||_|j|j|jtj\}}|j|||_ |S)z Calculate the recall metric based on the stored predictions and ground-truth data, at different IoU thresholds. Returns: The recall metric result. ) _computerr'_filter_predictions_and_targets_by_sizerSMALL small_objectsMEDIUMmedium_objectsLARGE large_objects)rresultsmall_predictions small_targetsmedium_predictionsmedium_targetslarge_predictions large_targetss rcomputezRecall.compute~st55t7I7IJ+/+W+W  " "D$6$68J8P8P, (= $}}-> N  8 8&&(:(: N r c tjddd}g}t||D]\}}|j|}|j|}t |dkDs8t |dk(r|j tj d|jfttj dtjtj dt|jf|jtjk(r t||} n_|jtj k(r t#||} n5|jtj$k(r t'||} n t)d|j+|j |jntj,g|j |jntj,g| |} |j | |j.|j|jf|st1|j|j2tj |j4dtj d|j4df|tj,gtddd St|D cgc]} tj6| d} } |j8| \} }}t1|j|j2| |||ddd Scc} w) Ng?gffffff? rdtype)rz-Unsupported metric target for IoU calculation) rr recall_scoresrecall_per_classiou_thresholdsmatched_classesr1r3r5)nplinspacezip_detections_contentr'appendzerossizeboolfloat32intclass_idrrBOXESr MASKSr ORIENTED_BOUNDING_BOXESr r(_match_detection_batcharray confidence RecallResultrshape concatenate_compute_recall_for_classes)rpredictions_list targets_listrDstatsr*r+prediction_contentstarget_contentsioumatchesitemsconcatenated_statsrBrCunique_classess rr.zRecall._computesS$3$'(8,$G.  K"&":":;"G "66w?O7|a{#q(LLHHa)<)<%=TJHHT<HHT5#,, **l.@.@@+O=PQ,, 0B0BB,_>QR,, 0T0TT4+-@)K#99&//;$,,XXb\"++7 ((XXb\& GLL#'22'00#,, O. `"11!%!6!6 hh~';';A'>?!#1n.B.B1.E*F!G- "3 7"#"  EHKP5bnnUA6PP ,D , ,.@ A 8 '--!22'-)*  Qs%K?c\tj| }||}||}tj|d\}}|j||||}|j |} |j t jk(rtj| d} n|j t jk(r#|jd} |j | } nT|j t jk(r7|jtj}tj| d|}  | |fS)NT) return_countsraxis)rhweights)rFargsortunique_compute_confusion_matrix_compute_recallrrMACROmeanMICROsumWEIGHTEDastyperNaverage) rraprediction_confidenceprediction_class_idstrue_class_idssorted_indicesrd class_countsconfusion_matrixrCrBconfusion_matrix_mergeds rrZz"Recall._compute_recall_for_classess%:$:;.)3NC')yyt'T$  99 )><   //0@A  O$9$9 9GG$41=M  " "o&;&; ;&6&:&:1&= # 001HIM  " "o&>&> >'..rzz:LJJ'7aVM.>>r c|jd|jd}}tj||ft}|dddf|k(}t |D] \}} tj || k\|z} | djds5tj | d} || dddf} tj| | g} | djddkDrh| | dddfjddd} | tj| dddfdd} | tj| dddfdd} d|| dddfjt|f<|}|S) Nrr@rgT) return_index) rXrFrKrM enumeratewherestackhstackrjrkrsrO)predictions_classestarget_classesr`rDnum_predictionsnum_iou_levelscorrect correct_classi iou_levelmatched_indicescombined_indices iou_valuesraresult_corrects rrTzRecall._match_detection_batchs~ % %a (   #(((O^H#I.H&llnO!#!#.!9"$((>":"$''.("CQ!#.!9"$''./"J"$((>":!/!9!=!=a!@#$~h'?#?"D"DQ"G"*^";*,((/B+ Y '# (+; r c|jddk(std|j|d}|d}||z}tj||tj||dk7}|}|S)a[ Broadcastable function, computing the recall from the confusion matrix. Args: confusion_matrix: shape (N, ..., 3), where the last dimension contains the true positives, false positives, and false negatives. Returns: shape (N, ...), containing the recall for each element. rrz/Confusion matrix must have shape (..., 3), got ).r).r~r)outr)rXr(rFdivide zeros_like)rzrr denominatorrecall result_recalls rrmzRecall._compute_recallks %%b)Q.A#))*, *&1*62$6    n-"  28 r c|jtjk(r|j}|S|jtjk(r*|j |j }|S|j S|jtjk(rf|jjt}|5t|dkDr'tj|tj}|S|j Std|j)z?Return boxes, masks or oriented bounding boxes from detections.rr@Invalid metric target: )rrrQxyxyrRmask_make_empty_contentrSdatagetr r'rFrUrNr()r detections result_boxes result_masksobb result_obbs rrIzRecall._detections_contents   ,"4"4 44>OOL    ,"4"4 4*6@oo ##++- -   ,"F"F F//%%&>?C3s8a<68hhs"**6U !!++- -243F3F2GHIIr c|jtjk(r'tjdtj }|S|jtj k(rtjdt}|S|jtjk(r'tjdtj }|Std|j)N)rr@)rrr)rrr~r) rrrQrFemptyrNrRrMrSr()r empty_boxes empty_masks empty_obbs rrzRecall._make_empty_contents   ,"4"4 43588F"**3UK    ,"4"4 413)41PK    ,"F"F F13)2::1VI 243F3F2GHIIr c~t|}|js|tjk(r|St ||j }||j k(}|j||_|j|j||_|j|j||_ |j|j||_ |j|j||_ |jG|jjD]*\}}tj|||j|<,|S)zBReturn a copy of detections with contents filtered by object size.)ris_emptyrANYrrvaluerrrPrV tracker_idrrbrFrU)rr size_categorynew_detectionssizes size_maskkeyrs r_filter_detections_by_sizez!Recall._filter_detections_by_sizes4"*-    M5G5K5K$K! !+ND:R 0R @PR R h"?&"? 7"?4 "? . "?   "?H2-%0   <6-6%:6.6, 6 ! 66p1 @J$J"$5G 46*6'6* 6 3 6r rceZdZUdZded<ded<eddZeddZded <ded <d ed <d ed<ded<ded<ded<ddZddZ ddZ y)rWu The results of the recall metric calculation. Defaults to `0` if no detections or targets were provided. Attributes: metric_target: the type of data used for the metric - boxes, masks or oriented bounding boxes. averaging_method: the averaging method used to compute the recall. Determines how the recall is aggregated across classes. recall_at_50: the recall at IoU threshold of `0.5`. recall_at_75: the recall at IoU threshold of `0.75`. recall_scores: the recall scores at each IoU threshold. Shape: `(num_iou_thresholds,)` recall_per_class: the recall scores per class and IoU threshold. Shape: `(num_target_classes, num_iou_thresholds)` iou_thresholds: the IoU thresholds used in the calculations. matched_classes: the class IDs of all matched classes. Corresponds to the rows of `recall_per_class`. small_objects: the Recall metric results for small objects (area < 32²). medium_objects: the Recall metric results for medium objects (32² ≤ area < 96²). large_objects: the Recall metric results for large objects (area ≥ 96²). rrrrc2t|jdS)NrfloatrBr"s r recall_at_50zRecallResult.recall_at_50T''*++r c2t|jdS)Nrr"s r recall_at_75zRecallResult.recall_at_75rr rrBrCrrDrrEzRecallResult | Noner1r3r5c|jjd|jd|jd|jdd|j dd|j d|jd}|jjd k(r|d z }t|j|jD]\}}|d |d |d z }d }|j3|t|jjd d |z}|d|z }|j3|t|jjd d |z}|d|z }|j 3|t|j jd d |z}|d|z }|S)a= Format as a pretty string. Example: ```pycon >>> import numpy as np >>> import supervision as sv >>> from supervision.metrics import Recall >>> predictions = sv.Detections( ... xyxy=np.array([[0, 0, 10, 10]]), ... class_id=np.array([0]), ... confidence=np.array([0.9]) ... ) >>> targets = sv.Detections( ... xyxy=np.array([[0, 0, 10, 10]]), ... class_id=np.array([0]) ... ) >>> recall_metric = Recall() >>> recall_result = recall_metric.update(predictions, targets).compute() >>> print(recall_result) # doctest: +ELLIPSIS RecallResult: Metric target: MetricTarget.BOXES Averaging method: AveragingMethod.WEIGHTED R @ 50: 1.0000 R @ 75: 1.0000 R @ thresh: [1. ... 1.] IoU thresh: [0.5 0.55 ... 0.95] Recall per class: 0: [1. ... 1.] ... Medium objects: RecallResult: Metric target: MetricTarget.BOXES Averaging method: AveragingMethod.WEIGHTED R @ 50: 0.0000 ... ``` z: Metric target: z Averaging method: z R @ 50: z.4fz R @ 75: z R @ thresh: z IoU thresh: z Recall per class: rz No results z z:  z Small objects: z Medium objects: z Large objects: ) __class__rrrrrrBrDrCrLrHrEr1strreplacer3r5)rout_strrPrecall_of_classindentindenteds r__str__zRecallResult.__str__sR~~&&'(!!%!3!3 45!!%!6!6 78,,S12,,S12--./../0"  #   % % * ' 'G),  $"7"7*  < %Ho H:R'8; ;G <     )D$6$6 7 ? ?6(m TTH +H:6 6G    *D$7$7 8 @ @F8} UUH ,XJ7 7G    )D$6$6 7 ? ?6(m TTH +H:6 6Gr ctddl}|j|jd}|j:|jj }|j D] \}}||d|<|j:|jj }|j D] \}}||d|<|j:|jj }|j D] \}}||d|<|j|dgS)zt Convert the result to a pandas DataFrame. Returns: The result as a DataFrame. rN)zR@50zR@75small_objects_medium_objects_large_objects_)index) rpandasrrr1 to_pandasrbr3r5 DataFrame)rpd pandas_datasmall_objects_dfrrmedium_objects_dflarge_objects_dfs rrzRecallResult.to_pandasUs+ !%%%%    )#11;;= .446 < U6; nSE23 <    * $ 3 3 = = ? /557 = U7< ocU34 =    )#11;;= .446 < U6; nSE23 <r||Ks33r cddg}|j|jg}tdgdz}|j>|j}|ddgz }||j|jgz }|tdgdzz }|j>|j}|d d gz }||j|jgz }|tdgdzz }|j >|j }|d d gz }||j|jgz }|td gdzz }dt jd<t jd\}}|jdd|jddd|jjd|jjd} |j| dtt!|} |j#| ||d} |j%| |j'|dd| D]O} | j)} |j+| j-| j/dz z| dz| ddd !Qd"t jd<t j0t j2y)#z Plot the recall results. ![example_plot]( https://media.roboflow.com/supervision-docs/metrics/recall_plot_example.png ){ align=center width="800" } z Recall@50z Recall@75rr~Nz Small: R@50z Small: R@75rz Medium: R@50z Medium: R@75z Large: R@50z Large: R@75r monospacez font.family)r?)figsizer}Valuebold) fontweightz Recall, by Object Size (target: z , averaging: )center)coloralign-right)rotationhag{Gz?z.2fbottom)rvaz sans-serif)rrrr1r3r5pltrcParamssubplotsset_ylim set_ylabelrrr set_titleranger'bar set_xticksset_xticklabels get_heighttextget_x get_width tight_layoutshow)rlabelsvaluescolorsr1r3r5_axtitle x_positionsbarsry_values rplotzRecallResult.plotss{+##T%6%67&q)*Q.    ) ..M }m4 4F }11=3M3MN NF +A./!3 3F    *!00N ~~6 6F ~22N4O4OP PF +A./!3 3F    ) ..M }m4 4F }11=3M3MN NF +A./!3 3F&1 ]# W-2 Aq g& 1,,223400667q :  Uv .CK( vvk6xvH k" 6B7; Cnn&G GG cmmo11$3-   '3 ]#   r N)rr)rr)rz pd.DataFramer) rrrr__annotations__propertyrrrrr rr rrWrWsx6 %% ,,,,+*--++**&&''&&DL4<>r rW)' __future__rcopyr dataclassesrtypingrrnumpyrF numpy.typingnpt matplotlibrrsupervision.configr supervision.detection.corer 'supervision.detection.utils.iou_and_nmsr r r supervision.draw.colorrsupervision.metrics.corerrr%supervision.metrics.utils.object_sizerrsupervision.metrics.utils.utilsrrrrrWrr rr2sq"!%$71 8JJD}6V}6@ RR Rr