^jrddlmZddlmZddlmZddlmZmZddl Z ddl mZ ddl mZddlmZddlmZdd lmZmZmZdd lmZdd lmZmZmZdd lmZm Z dd l!m"Z"erddl#Z$GddeZ%eGddZ&y)) annotations)deepcopy) dataclass) TYPE_CHECKINGAnyN)pyplot)ORIENTED_BOX_COORDINATES) Detections) box_iou_batchmask_iou_batchoriented_box_iou_batch)LEGACY_COLOR_PALETTE)AveragingMethodMetric MetricTarget)ObjectSizeCategoryget_detection_size_category)ensure_pandas_installedcBeZdZdZej ejf ddZddZ ddZ ddZ ddZ ddZ e ddZe dd Ze dd Zdd Zdd Z dd Z ddZy) Precisiona/ Precision is a metric used to evaluate object detection models. It is the ratio of true positive detections to the total number of predicted detections. We calculate it at different IoU thresholds. In simple terms, Precision is a measure of a model's accuracy, calculated as: `Precision = TP / (TP + FP)` Here, `TP` is the number of true positives (correct detections), and `FP` is the number of false positive detections (detected, but incorrectly). Examples: ```pycon >>> import numpy as np >>> import supervision as sv >>> from supervision.metrics import Precision >>> predictions = sv.Detections( ... xyxy=np.array([[0, 0, 10, 10]]), ... class_id=np.array([0]), ... confidence=np.array([0.9]) ... ) >>> targets = sv.Detections( ... xyxy=np.array([[0, 0, 10, 10]]), ... class_id=np.array([0]) ... ) >>> precision_metric = Precision() >>> precision_result = precision_metric.update(predictions, targets).compute() >>> round(float(precision_result.precision_at_50), 2) 1.0 ``` ![example_plot]( https://media.roboflow.com/supervision-docs/metrics/precision_plot_example.png ){ align=center width="800" } c<||_||_g|_g|_y)a Initialize the Precision metric. Args: metric_target: The type of detection data to use. averaging_method: The averaging method used to compute the precision. Determines how the precision is aggregated across classes. N)_metric_targetaveraging_method_predictions_list _targets_list)self metric_targetrs h/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/supervision/metrics/precision.py__init__zPrecision.__init__Es$, 035/1c g|_g|_y)zR Reset the metric to its initial state, clearing all stored data. N)rrrs rresetzPrecision.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 rupdatezPrecision.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 precision metric based on the stored predictions and ground-truth data, at different IoU thresholds. Returns: The precision metric result. ) _computerr'_filter_predictions_and_targets_by_sizerSMALL small_objectsMEDIUMmedium_objectsLARGE large_objects)rresultsmall_predictions small_targetsmedium_predictionsmedium_targetslarge_predictions large_targetss rcomputezPrecision.compute~st55t7I7IJ+/+W+W  " "D$6$68J8P8P, (= $}}-> N  8 8&&(:(: N r c ~tjddd}g}t||D]\}}|j|}|j|}t |dk(rt |dkDr|j |j ^|jtjt ||jftj|j |j tjdtjft |dkDst |dk(r|jtjd|jfttjdtjtjdt|j f|jt j"k(r t%||} n_|jt j&k(r t)||} n5|jt j*k(r t-||} n t/d|j1|j |j ntj2g|j |j ntj2g| |} |j| |j |j |j f|st5|j|j6tj|j8dtjd|j8df|tj2gtddd St|D cgc]} tj:| d} } |j<| \} }}t5|j|j6| |||ddd Scc} w) aBuild per-image stats tuples and delegate to class-level computation. Each stats tuple is ``(matches, confidence, class_ids, true_class_ids)``: - Both empty: skip (no information). - Targets empty, predictions present: all predictions are FPs; true_class_ids is ``zeros((0,))``. - Targets present: IoU matching produces ``matches`` array. g?gffffff? rNdtype)rz-Unsupported metric target for IoU calculation) rrprecision_scoresprecision_per_classiou_thresholdsmatched_classesr1r3r5)nplinspacezip_detections_contentr'class_id confidenceappendzerossizebool_int32boolfloat32intrrBOXESr MASKSr ORIENTED_BOUNDING_BOXESr r(_match_detection_batcharrayPrecisionResultrshape concatenate_compute_precision_for_classes)rpredictions_list targets_listrDstatsr*r+prediction_contentstarget_contentsioumatchesitemsconcatenated_statsrBrCunique_classess rr.zPrecision._computesQS$3$'(8,$G=  K"&":":;"G "66w?O7|q S%5%9''/;3I3I3Q  -~/B/BC288$..#,,RXX6  W!{#q(LLHHa)<)<%=TJHHT<HHT5#,, **l.@.@@+O=PQ,, 0B0BB,_>QR,, 0T0TT4+-@)K#99&//;$,,XXb\"++7 ((XXb\& GLL#'22'00#,, m= ~""11!%!6!6!#.*>*>q*A!B$&HHa1E1Ea1H-I$J- "3 7"#"  EHKP5bnnUA6PP /D / /1C D >-~--!22- 3)*  Qs N:ctj| }||}||}tjtj||f}tj|d\}}tj|j dt } || tj||<|j|||| } |j| } |jtjk(rtj| d} n|jtjk(r#| jd} |j| } n|jtj k(rm| j#tj$} | jdk(r#tj| j d} ntj&| d| }  | |fS)zCompute precision scores from concatenated stats across all images. ``unique_classes`` is the union of GT and predicted classes so that predictions of classes absent from GT still count as false positives. T) return_countsrr@axis)rjweights)rFargsortuniquer[rMrZrS searchsorted_compute_confusion_matrix_compute_precisionrrMACROmeanMICROsumWEIGHTEDastyperRaverage)rrcprediction_confidenceprediction_class_idstrue_class_idssorted_indicesrf true_classes true_counts class_countsconfusion_matrixrCrBconfusion_matrix_mergeds rr\z(Precision._compute_precision_for_classess %:$:;.)3NC NNN,@A B %'IInD$Q! kxx 4 4Q 7sC FQ R__^\BC 99 )><  #556FG  O$9$9 9!ww':C   " "o&;&; ;&6&:&:1&= ##667NO   " "o&>&> >'..rzz:L!Q&$&88,?,E,Ea,H#I #%::'a$  !4nDDr 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@rkriT) return_index) rZrFrMrQ enumeratewherestackhstackrmrnrwrS)predictions_classestarget_classesrbrDnum_predictionsnum_iou_levelscorrect correct_classi iou_levelmatched_indicescombined_indices iou_valuesrcresult_corrects rrWz Precision._match_detection_batch?s~ % %a (   #(((O^H#I.H&llnO!#!#.!9"$((>":"$''.("CQ!#.!9"$''./"J"$((>":!/!9!=!=a!@#$~h'?#?"D"DQ"G"*^";*,((/B+ Y '# (2B r c|jddk(std|j|d}|d}||z}tj||tj||dk7}|}|S)aa Broadcastable function, computing the precision 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 precision for each element. rrz/Confusion matrix must have shape (..., 3), got ).r).rkr)outr)rZr(rFdivide zeros_like)rrr denominator precisionresult_precisions rrqzPrecision._compute_precisions %%b)Q.A#))*, *&1*62$6 II   n-"  5>r c|jtjk(r|j}|S|jtjk(r*|j |j }|S|j S|jtjk(rf|jjt}|5t|dkDr'tj|tj}|S|j Std|j)z?Return boxes, masks or oriented bounding boxes from detections.rr@Invalid metric target: )rrrTxyxyrUmask_make_empty_contentrVdatagetr r'rFrXrRr()r detections result_boxes result_masksobb result_obbs rrIzPrecision._detections_contents   ,"4"4 44>OOL    ,"4"4 4*6@oo ##++- -   ,"F"F F//%%&>?C3s8a<68hhs"**6U !!++- -243F3F2GHIIr c|jtjk(r'tjdtj }|S|jtj k(rtjdt}|S|jtjk(r'tjdtj }|Std|j)N)rr@)rrr)rrrr) rrrTrFemptyrRrUrQrVr()r empty_boxes empty_masks empty_obbs rrzPrecision._make_empty_contents   ,"4"4 43588F"**3UK    ,"4"4 413)41PK    ,"F"F F13)2::1VI 243F3F2GHIIr c~t|}|js|tjk(r|St ||j }||j k(}|j||_|j|j||_|j|j||_ |j|j||_ |j|j||_ |jG|jjD]*\}}tj|||j|<,|S)zBReturn a copy of detections with contents filtered by object size.)ris_emptyrANYrrvaluerrrJrK tracker_idrrdrFrX)rr size_categorynew_detectionssizes size_maskkeyrs r_filter_detections_by_sizez$Precision._filter_detections_by_sizes4"*-    M5G5K5K$K! !+ND:i 0i @Pi i V7E&7E 77E4 7E . 7E   7Er2-%0   <6-6%:6.6, 6 ! 66p 1   @J$ J$5G 46*6'6* 6 3 6r rceZdZUdZded<ded<eddZeddZded <ded <d ed <d ed<ded<ded<ded<ddZddZ ddZ y)rYu The results of the precision 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 precision. Determines how the precision is aggregated across classes. precision_at_50: the precision at IoU threshold of `0.5`. precision_at_75: the precision at IoU threshold of `0.75`. precision_scores: the precision scores at each IoU threshold. Shape: `(num_iou_thresholds,)` precision_per_class: the precision scores per class and IoU threshold. Shape: `(num_classes, num_iou_thresholds)` iou_thresholds: the IoU thresholds used in the calculations. matched_classes: the class IDs present in either predictions or ground truth. Corresponds to the rows of `precision_per_class`. Classes that appear only in predictions (no ground-truth instances) are included; their per-threshold precision values will be `0.0`. small_objects: the Precision metric results for small objects (area < 32²). medium_objects: the Precision metric results for medium objects (32² ≤ area < 96²). large_objects: the Precision metric results for large objects (area ≥ 96²). rrrrc2t|jdS)NrfloatrBr"s rprecision_at_50zPrecisionResult.precision_at_50*T**1-..r c2t|jdS)Nrr"s rprecision_at_75zPrecisionResult.precision_at_75.rr rrBrCrrDrrEzPrecisionResult | 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 Precision >>> 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]) ... ) >>> precision_metric = Precision() >>> precision_result = precision_metric.update( ... predictions, targets ... ).compute() >>> print(precision_result) # doctest: +ELLIPSIS PrecisionResult: Metric target: MetricTarget.BOXES Averaging method: AveragingMethod.WEIGHTED P @ 50: 1.0000 P @ 75: 1.0000 P @ thresh: [1. ... 1.] IoU thresh: [0.5 0.55 ... 0.95] Precision per class: 0: [1. ... 1.] ... Medium objects: PrecisionResult: Metric target: MetricTarget.BOXES Averaging method: AveragingMethod.WEIGHTED P @ 50: 0.0000 ... ``` z: Metric target: z Averaging method: z P @ 50: z.4fz P @ 75: z P @ thresh: z IoU thresh: z Precision per class: rz No results z z:  z Small objects: z Medium objects: z Large objects: ) __class__rrrrrrBrDrCrNrHrEr1strreplacer3r5)rout_strrJprecision_of_classindentindenteds r__str__zPrecisionResult.__str__;sV~~&&'(!!%!3!3 45!!%!6!6 78//45//450012../0%  &   # # ( (A - ' 'G,/  $":":-  ? (H( H:R(:';2> >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)zP@50zP@75small_objects_medium_objects_large_objects_)index) rpandasrrr1 to_pandasrdr3r5 DataFrame)rpd pandas_datasmall_objects_dfrrmedium_objects_dflarge_objects_dfs rrzPrecisionResult.to_pandass+ !((((    )#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 precision results. ![example_plot]( https://media.roboflow.com/supervision-docs/metrics/precision_plot_example.png ){ align=center width="800" } z Precision@50z Precision@75rrNz Small: P@50z Small: P@75rz Medium: P@50z Medium: P@75z Large: P@50z Large: P@75r monospacez font.family)r?)figsizerkValuebold) fontweightz#Precision, by Object Size (target: z , averaging: )center)coloralign-right)rotationhag{Gz?z.2fbottom)r vaz sans-serif)rrrr1r3r5pltrcParamssubplotsset_ylim set_ylabelrrr set_titleranger'bar set_xticksset_xticklabels get_heighttextget_x get_width tight_layoutshow)rlabelsvaluescolorsr1r3r5_axtitle x_positionsbarsry_values rplotzPrecisionResult.plots!.1&&(<(<=&q)*Q.    ) ..M }m4 4F }44m6S6ST TF +A./!3 3F    *!00N ~~6 6F ~55~7U7UV VF +A./!3 3F    ) ..M }m4 4F }44m6S6ST TF +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 rrYrYsx: %% ////.-00++**))**))FP4<>r rY)' __future__rcopyr dataclassesrtypingrrnumpyrF numpy.typingnpt matplotlibrr supervision.configr supervision.detection.corer 'supervision.detection.utils.iou_and_nmsr r r supervision.draw.colorrsupervision.metrics.corerrr%supervision.metrics.utils.object_sizerrsupervision.metrics.utils.utilsrrrrrYrr rr8sq"!%$71 8JJDg6g6T VV Vr