h+ddlmZddlmZddlmZmZmZmZddl Z ddl Z ddl m cmZddlmZddlmZmZmZddlmZddlmZmZGd d eZy) ) ThreadPool)Path)AnyDictListTupleN)DetectionValidator)LOGGER NUM_THREADSops)check_requirements)SegmentMetricsmask_iouc ^eZdZdZddfd Zdeeefdeeefffd Zde jjddffd Z defd Z d ee jdeeee jfffd Zd edeeefdeeefffd Zd eee jfdeeefdeeej(fffd Zdeeefd eeee jfdeddffd Zde jdedeeefdeddf dZdeee jfdeeefddffd Zdeeefdeeefffd ZxZS)SegmentationValidatora A class extending the DetectionValidator class for validation based on a segmentation model. This validator handles the evaluation of segmentation models, processing both bounding box and mask predictions to compute metrics such as mAP for both detection and segmentation tasks. Attributes: plot_masks (list): List to store masks for plotting. process (callable): Function to process masks based on save_json and save_txt flags. args (namespace): Arguments for the validator. metrics (SegmentMetrics): Metrics calculator for segmentation tasks. stats (dict): Dictionary to store statistics during validation. Examples: >>> from ultralytics.models.yolo.segment import SegmentationValidator >>> args = dict(model="yolo11n-seg.pt", data="coco8-seg.yaml") >>> validator = SegmentationValidator(args=args) >>> validator() Nreturncxt|||||d|_d|j_t |_y)a Initialize SegmentationValidator and set task to 'segment', metrics to SegmentMetrics. Args: dataloader (torch.utils.data.DataLoader, optional): Dataloader to use for validation. save_dir (Path, optional): Directory to save results. args (namespace, optional): Arguments for the validator. _callbacks (list, optional): List of callback functions. Nsegment)super__init__processargstaskrmetrics)self dataloadersave_dirr _callbacks __class__s a/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/ultralytics/models/yolo/segment/val.pyrzSegmentationValidator.__init__&s4 XtZ@ " %' batchct||}|dj|jj |d<|S)z Preprocess batch of images for YOLO segmentation validation. Args: batch (Dict[str, Any]): Batch containing images and annotations. Returns: (Dict[str, Any]): Preprocessed batch. masks)r preprocesstodevicefloat)rr"rs r r%z SegmentationValidator.preprocess5s>"5)w**4;;7==?g r!modelct|||jjr t d|jjs|jj rt j|_ yt j|_ y)z Initialize metrics and select mask processing function based on save_json flag. Args: model (torch.nn.Module): Model to validate. zfaster-coco-eval>=1.6.7N) r init_metricsr save_jsonr save_txtr process_mask_native process_maskr)rr)rs r r+z"SegmentationValidator.init_metricsCsZ U# 99   8 926))2E2EI[I[s.. adaqaq r!c ddzS)z5Return a formatted description of evaluation metrics.z,%22s%11s%11s%11s%11s%11s%11s%11s%11s%11s%11s) ClassImages InstanceszBox(PRmAP50 mAP50-95)zMask(Pr4r5r6)rs r get_desczSegmentationValidator.get_descPs$ )  r!predsct|ddk(r|ddn|d}t| |d}|jddDcgc]}d|z }}t |D]\}}|j d}t|r|j ||||d | natjdg|j tjur|n|jddtj|d j |d <|Scc}w) a Post-process YOLO predictions and return output detections with proto. Args: preds (List[torch.Tensor]): Raw predictions from the model. Returns: List[Dict[str, torch.Tensor]]: Processed detection predictions with masks. rNextrabboxes)shape)dtyper'r$) lenr postprocessrB enumeratepoprtorchzerosr r.uint8r') rr9protoximgszipred coefficientrs r rEz!SegmentationValidator.postprocess`s !$E!H  2a a#E!H- % AB01Q00 ' GAt((7+K{# U1X{DN% P[[a4<<33J3J#J%PUP[P[\]\^P_a++>00 M  1s Dsict|||}|jjr|gn|d|k(}|d||d<|S)a< Prepare a batch for training or inference by processing images and targets. Args: si (int): Batch index. batch (Dict[str, Any]): Batch data containing images and annotations. Returns: (Dict[str, Any]): Prepared batch with processed annotations. batch_idxr$)r_prepare_batchr overlap_mask)rrQr"prepared_batchmidxrs r rTz$SegmentationValidator._prepare_batchzsN/E:yy--t53E3K"'."6wr!ct |||}|d|d}}t|dk(st|ddk(r5tjt|d|j ft }n\|d}|jjrmt|}tj||jj|dddz} |j|dd}tj|| k(dd}|jdd |jdd k7r=t!j"|d |jdd d d d}|j%d }t'|j|jdd|j|jdd} |j)|d|| j+j-}|j/d|i|S)a  Compute correct prediction matrix for a batch based on bounding boxes and optional masks. Args: preds (Dict[str, torch.Tensor]): Dictionary containing predictions with keys like 'cls' and 'masks'. batch (Dict[str, Any]): Dictionary containing batch data with keys like 'cls' and 'masks'. Returns: (Dict[str, np.ndarray]): A dictionary containing correct prediction matrices including 'tp_m' for mask IoU. Notes: - If `masks` is True, the function computes IoU between predicted and ground truth masks. - If `overlap` is True and `masks` is True, overlapping masks are taken into account when computing IoU. Examples: >>> preds = {"cls": torch.tensor([1, 0]), "masks": torch.rand(2, 640, 640), "bboxes": torch.rand(2, 4)} >>> batch = {"cls": torch.tensor([1, 0]), "masks": torch.rand(2, 640, 640), "bboxes": torch.rand(2, 4)} >>> correct_preds = validator._process_batch(preds, batch) clsr$rrC)r'r;g?gNbilinearF)mode align_cornersg?r=tp_m)r_process_batchrDnprIniouboolrrUrHaranger'viewrepeatwhererBF interpolategt_rmatch_predictionscpunumpyupdate) rr9r"tpgt_clsgt_masksr^ pred_masksnlindexiours r r_z$SegmentationValidator._process_batchs(W #E5 1 <w v;! s5<0A588Su. :$GDwJyy%%[ R@EEb!QORSS#??2q!4 ;;x5'8#sC~~ab!Z%5%5ab%99==$9I9I!"9MT^nstuvw#<<,8==):B?Q[QaQabcQdfhAijC))%,DHHJPPRD 64.! r!nic|D]g}|d}|jddkDrtjdtj|ddtj j |d<it|!|||dy)a Plot batch predictions with masks and bounding boxes. Args: batch (Dict[str, Any]): Batch containing images and annotations. preds (List[Dict[str, torch.Tensor]]): List of predictions from the model. ni (int): Batch index. r$r2zBLimiting validation plots to first 50 items per image for speed...NrZ)max_det) rBr warningrH as_tensorrJrkrplot_predictions)rr"r9rupr$rs r r{z&SegmentationValidator.plot_predictionss{ NAgJE{{1~"cds5;;GKKMAgJ  N  r2 >r!predn save_confrBfilec ddlm}|tj|d|dftjd|j t j|d|djd|d jdgd t j|d t j j|| y)a Save YOLO detections to a txt file in normalized coordinates in a specific format. Args: predn (torch.Tensor): Predictions in the format (x1, y1, x2, y2, conf, class). save_conf (bool): Whether to save confidence scores. shape (Tuple[int, int]): Shape of the original image. file (Path): File path to save the detections. r)Resultsr;rZNrAconfr=rY)dimr$)pathnamesboxesr$)r~) ultralytics.engine.resultsrr`rIrJrrHcat unsqueezerzr-)rr}r~rBrrs r save_one_txtz"SegmentationValidator.save_one_txts 7 HHeAha) :**))U8_eFm.E.Eb.I5QV>> result = {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236} r)encodectj|dddddfddd}|djd|d<|S)z:Encode predicted masks as RLE and append results to jdict.NrgrJ)orderrCrcountszutf-8)r`asarraydecode)rLrlers r single_encodez9SegmentationValidator.pred_to_json..single_encodesFAaDjMGLMaPCM009CMJr!r$rZr;r> ori_shape ratio_pad)r)r>rr;N segmentation)faster_coco_eval.core.maskrrHrzrJr scale_imagepermute contiguousrkrlr` transposerr mapr pred_to_jsonrFjdictrD) rr}rr coco_masksrqpoolrlesrNrrrs @r rz"SegmentationValidator.pred_to_jsons 6  __U7^5;;G __   q!Q ' 2 2 4 8 8 : @ @ B ; [) \\*i8  $ 788M:6D 7 UF+dO ;DAq9:DJJD zA~ &~ 6 ; 7 7s 4DDstatsc|jdz }|jddz |jrdnd|jjdz }t ||||ddgd d g S) z;Return COCO-style instance segmentation evaluation metrics.zpredictions.jsonr annotationszinstances_val2017.jsonlvis_v1_z.jsonbboxsegmBoxMask)suffix)rdatais_cocorsplitr coco_evaluate)rr pred_json anno_jsonrs r eval_jsonzSegmentationValidator.eval_jsonsyMM$66 IIf  +/<<'x GXX]=^ `  w$UIy66BR\aci[j$kkr!)NNNN)rN)__name__ __module__ __qualname____doc__rrstrrr%rHnnModuler+r8rTensorrEintrTr`ndarrayr_r{rbrrrrr __classcell__)rs@r rrs( ( S#X 4S>  r%((// rd r # ell!3T#u||BS=T8U4T#s(^S#X %Dell):$;%DcN%W[\_acakak\kWl%N?d38n?T$sELLGXBY=Z?`c?hl? .%,,.4.cSVh._c.hl.(;$sELL'8"9;4S>;VZ;@ltCH~l$sCx.llr!r)multiprocessing.poolrpathlibrtypingrrrrrlr`rHtorch.nn.functionalr functionalrgultralytics.models.yolo.detectr ultralytics.utilsr r r ultralytics.utils.checksr ultralytics.utils.metricsrrrr7r!r rs?,)) =667>ll.llr!