§
    l¬¸jÛM  ã                  ó  — d Z ddlmZ ddlZddlZddlmZ ddlmZ ddl	Z
ddlZddlmZ ddlmZmZ ddlmZmZmZ ddlmZ dd	lmZmZmZmZmZmZmZ dd
l m!Z! ddl"m#Z#m$Z$ ddl%m&Z&m'Z'm(Z(m)Z)m*Z*m+Z+m,Z,  G d„ d¦  «        Z-dS )a‡  
Check a model's accuracy on a test or val split of a dataset.

Usage:
    $ yolo val model=yolo26n.pt data=coco8.yaml imgsz=640

Usage - formats:
    $ yolo val model=yolo26n.pt                 # PyTorch
                     yolo26n.torchscript        # TorchScript
                     yolo26n.onnx               # ONNX Runtime or OpenCV DNN with dnn=True
                     yolo26n_openvino_model     # OpenVINO
                     yolo26n.engine             # TensorRT
                     yolo26n.mlpackage          # CoreML (macOS-only)
                     yolo26n_saved_model        # TensorFlow SavedModel
                     yolo26n.pb                 # TensorFlow GraphDef
                     yolo26n_edgetpu.tflite     # TensorFlow Edge TPU
                     yolo26n_paddle_model       # PaddlePaddle
                     yolo26n.mnn                # MNN
                     yolo26n_ncnn_model         # NCNN
                     yolo26n_imx_model          # Sony IMX
                     yolo26n_rknn_model         # Rockchip RKNN
                     yolo26n_executorch_model   # ExecuTorch
                     yolo26n_axelera_model      # Axelera AI
                     yolo26n_deepx_model        # DEEPX
                     yolo26n_qnn.onnx           # Qualcomm QNN
                     yolo26n.tflite             # LiteRT
                     yolo26n_ascend_model       # Huawei Ascend
é    )ÚannotationsN)Údeepcopy)ÚPath)Úget_cfgÚget_save_dir)Úcheck_cls_datasetÚcheck_det_datasetÚ convert_ndjson_to_yolo_if_needed)ÚAutoBackend)Ú
LOCAL_RANKÚLOGGERÚRANKÚTQDMÚ	callbacksÚcolorstrÚemojis)Úcheck_imgsz)ÚProfileÚlinear_sum_assignment)Úattempt_compileÚautocastÚget_torch_device_backendÚselect_deviceÚsmart_inference_modeÚtorch_distributed_zero_firstÚunwrap_modelc                  ó  — e Zd ZdZd&d'd„Z e¦   «         d(d„¦   «         Z	 d)d*d„Z ed¦  «        d+d„¦   «         Zd,d„Z	d,d„Z
d„ Zd„ Zd„ Zd„ Zd„ Zd„ Zd„ Zd„ Zd„ Zd„ Zd„ Zed „ ¦   «         Zd+d!„Zd"„ Zd#„ Zd$„ Zd%„ ZdS )-ÚBaseValidatora  A base class for creating validators.

    This class provides the foundation for validation processes, including model evaluation, metric computation, and
    result visualization.

    Attributes:
        args (SimpleNamespace): Configuration for the validator.
        dataloader (DataLoader): DataLoader to use for validation.
        model (nn.Module): Model to validate.
        data (dict): Data dictionary containing dataset information.
        device (torch.device): Device to use for validation.
        batch_i (int): Current batch index.
        training (bool): Whether the model is in training mode.
        names (dict): Class names mapping.
        seen (int): Number of images seen so far during validation.
        stats (dict): Statistics collected during validation.
        confusion_matrix: Confusion matrix for classification evaluation.
        nc (int): Number of classes.
        iouv (torch.Tensor): IoU thresholds from 0.50 to 0.95 in steps of 0.05.
        jdict (list): List to store JSON validation results.
        speed (dict): Dictionary with keys 'preprocess', 'inference', 'loss', 'postprocess' and their respective batch
            processing times in milliseconds.
        save_dir (Path): Directory to save results.
        plots (dict): Dictionary to store plots for visualization.
        callbacks (dict): Dictionary to store various callback functions.
        stride (int): Model stride for padding calculations.
        loss (dict): Accumulated loss items during training validation.

    Methods:
        __call__: Execute validation process, running inference on dataloader and computing performance metrics.
        match_predictions: Match predictions to ground truth objects using IoU.
        add_callback: Append the given callback to the specified event.
        run_callbacks: Run all callbacks associated with a specified event.
        get_dataloader: Get data loader from dataset path and batch size.
        build_dataset: Build dataset from image path.
        preprocess: Preprocess an input batch.
        postprocess: Postprocess the predictions.
        init_metrics: Initialize performance metrics for the YOLO model.
        update_metrics: Update metrics based on predictions and batch.
        finalize_metrics: Finalize and return all metrics.
        get_stats: Return statistics about the model's performance.
        print_results: Print the results of the model's predictions.
        get_desc: Get description of the YOLO model.
        on_plot: Register plots for visualization.
        plot_val_samples: Plot validation samples during training.
        plot_predictions: Plot YOLO model predictions on batch images.
        pred_to_json: Convert predictions to JSON format.
        eval_json: Evaluate and return JSON format of prediction statistics.
    NÚ
_callbacksúdict | Nonec                ó€  — ddl }t          |¬¦  «        | _        || _        d| _        d| _        d| _        d| _        d| _        d| _	        d| _
        d| _        d| _        d| _        d| _        d| _        dddddœ| _        |pt#          | j        ¦  «        | _        | j        j        r
| j        dz  n| j                             dd¬¦  «         | j        j        €| j        j        d	k    rd
nd| j        _        t/          | j        j        d¬¦  «        | j        _        i | _        |pt5          j        ¦   «         | _        dS )aŒ  Initialize a BaseValidator instance.

        Args:
            dataloader (torch.utils.data.DataLoader, optional): DataLoader to be used for validation.
            save_dir (Path, optional): Directory to save results.
            args (SimpleNamespace, optional): Configuration for the validator.
            _callbacks (dict, optional): Dictionary to store various callback functions.
        r   N)Ú	overridesTg        )Ú
preprocessÚ	inferenceÚlossÚpostprocessÚlabels)ÚparentsÚexist_okÚobbg{®Gáz„?gü©ñÒMbP?é   )Úmax_dim)Útorchvisionr   ÚargsÚ
dataloaderÚstrideÚdataÚdeviceÚbatch_iÚtrainingÚnamesÚseenÚstatsÚconfusion_matrixÚncÚiouvÚjdictÚspeedr   Úsave_dirÚsave_txtÚmkdirÚconfÚtaskr   ÚimgszÚplotsr   Úget_default_callbacks)Úselfr/   r=   r.   r   r-   s         úl/root/private/project/pallet_detection_v2/.venv/lib/python3.11/site-packages/ultralytics/engine/validator.pyÚ__init__zBaseValidator.__init__n   s:  € ð 	ÐÐÐå dÐ+Ñ+Ô+ˆŒ	Ø$ˆŒØˆŒØˆŒ	ØˆŒØˆŒØˆŒØˆŒ
ØˆŒ	ØˆŒ
Ø $ˆÔØˆŒØˆŒ	ØˆŒ
Ø$'°cÀ3ÐWZÐ[Ð[ˆŒ
à Ð;¥L°´Ñ$;Ô$;ˆŒØ%)¤YÔ%7Ð	JˆŒ˜Ñ	!Ð	!¸T¼]×QÒQÐZ^ÐimÐQÑnÔnÐnØŒ9Œ>Ð!Ø%)¤Y¤^°uÒ%<Ð%<˜T˜TÀ%ˆDŒIŒNÝ% d¤i¤o¸qÐAÑAÔAˆŒ	ŒàˆŒ
Ø#ÐH¥yÔ'FÑ'HÔ'HˆŒˆˆó    c                ó‚  ‡ — |du‰ _          ‰ j        ||fi |¤Ž}‰ j        j        o‰ j          }‰ j         rät	          |d¦  «        r‰ j        j        du |_        |j        ‰ _        |j        ‰ _        ‰ j        j	        dk    r	|j
        rdnd‰ j        _        |                     ¦   «         }d„ |j                             ¦   «         D ¦   «         ‰ _        ‰ j        xj        |j        j        p|j        |j        dz
  k    z  c_        |                     ¦   «          �n¦t-          ‰ j        j        ¦  «                             d¦  «        r|€t3          j        d	¦  «         t7          j        ‰ ¦  «         t;          t<          ¦  «        5  t?          ‰ j        j        ‰ j        j         ¦  «        ‰ j        _        ddd¦  «         n# 1 swxY w Y   t-          ‰ j        j        ¦  «         !                    d
d¦  «        d         }|dv r|nd}tE          |p‰ j        j        tF          dk    rtI          ‰ j        j        ¦  «        n3tK          j        |tM          |¦  «         '                    ¦   «         ¦  «        ‰ j        j(        ‰ j        j        ‰ j        j        dk    ‰ j        j)        ‰ j        j        du ¬¦  «        }|j        ‰ _        |j*        rdnd‰ j        _        |j+        |j,        }}|dk    }|r!|j-        st3          j        d|› d�¦  «         d}t]          ‰ j        j/        |¬¦  «        }	|dvr›ta          |dd¦  «        sŠt	          |d¦  «        r tc          |j/        ¦  «        x‰ j        _/        }	|j2         3                    dd¦  «        ‰ j        _4        t3          j5        d‰ j        j4        › d‰ j        j4        › d|	› d|	› d�	¦  «         ‰ j        j6        dk    r+to          ‰ j        j        ‰ j        j!        ¬¦  «        ‰ _        n¥t-          ‰ j        j        ¦  «         8                    dd¦  «        d         d v s‰ j        j6        d!v r+ts          ‰ j        j        ‰ j        j!        ¬¦  «        ‰ _        n7tu          tw          d"‰ j        j        › d#‰ j        j6        › d$�¦  «        ¦  «        ‚‰ j        j	        d%v rd‰ j        _<        |s#ta          |dd¦  «        r|d&k    sd‰ j        _=        |j+        ‰ _+        |j>        ‰ _>        ‰ j?        pA‰  @                    ‰ j         3                    ‰ j        j!        ¦  «        ‰ j        j4        ¦  «        ‰ _?        |                     ¦   «          ‰ j        jA        r!t…          |‰ j        ‰ j        jA        ¬'¦  «        }| C                    |rdn‰ j        j4        ‰ j        d(         |	|	f¬)¦  «         ‰  D                    d*¦  «         t‹          ‰ j        ¬+¦  «        t‹          ‰ j        ¬+¦  «        t‹          ‰ j        ¬+¦  «        t‹          ‰ j        ¬+¦  «        f}
t�          ‰ j?        ‰  G                    ¦   «         t‘          ‰ j?        ¦  «        ¬,¦  «        }‰  I                    t•          |¦  «        ¦  «         g ‰ _K        t™          |¦  «        D �]ê\  }}‰  D                    d-¦  «         |‰ _M        |
d         5  ‰  N                    |¦  «        }ddd¦  «         n# 1 swxY w Y   tŸ          ‰ j         o‰ j        j        dk    ‰ j        j	        ¬+¦  «        5  |
d         5   ||d.         |¬/¦  «        }ddd¦  «         n# 1 swxY w Y   |
d0         5  ‰ j         rI|                     ||¦  «        d                              ¦   «         D ]\  }}‰ j        |xx         |z  cc<   Œddd¦  «         n# 1 swxY w Y   ddd¦  «         n# 1 swxY w Y   |
d1         5  ‰  P                    |¦  «        }ddd¦  «         n# 1 swxY w Y   ‰  Q                    ||¦  «         ‰ j        j        r<|d1k     r6tF          d2v r-‰  R                    ||¦  «         ‰  S                    |||¦  «         ‰  D                    d3¦  «         �Œìi }‰  T                    ¦   «          tF          d2v r–‰  U                    ¦   «         }t­          t¯          ‰ jX         Y                    ¦   «         ˆ fd4„|
D ¦   «         ¦  «        ¦  «        ‰ _X        ‰  Z                    ¦   «          ‰  [                    ¦   «          ‰  D                    d5¦  «         ‰ j         rÑd6„ ‰ j                             ¦   «         D ¦   «         }|j\        dk    r=| ]                    ¦   «         D ](}t½          j_        |dt¼          j`        ja        ¬7¦  «         Œ)tF          dk    rdS ˆ fd8„|                     ¦   «         D ¦   «         }i |¥| b                    |d9¬:¦  «        ¥}d;„ |                     ¦   «         D ¦   «         S tF          dk    r|S t3          j5         d<j,        tÇ          ‰ jX         ]                    ¦   «         ¦  «        Ž ¦  «         ‰ j        jd        r’‰ jK        r‹tË          t-          ‰ jf        d=z  ¦  «        d>d?¬@¦  «        5 }t3          j5        dA|jg        › dB�¦  «         tÑ          ji        ‰ jK        |¦  «         ddd¦  «         n# 1 swxY w Y   ‰  j                    |¦  «        }‰ j        j        s‰ j        jd        r*t3          j5        dCt×          dD‰ jf        ¦  «        › �¦  «         |S )Ea¿  Execute validation process, running inference on dataloader and computing performance metrics.

        Args:
            trainer (object, optional): Trainer object that contains the model to validate.
            model (nn.Module, optional): Model to validate if not using a trainer.
            **kwargs (Any): Task-specific model preparation arguments.

        Returns:
            (dict): Dictionary containing validation statistics.
        NÚend2endFÚcpué   c                ó>   — i | ]\  }}|t          j        |¦  «        “ŒS © )ÚtorchÚ
zeros_like©Ú.0ÚkÚvs      rF   ú
<dictcomp>z*BaseValidator.__call__.<locals>.<dictcomp>©   s)   € ÐWÐWÐW±D°A°q˜�EÔ,¨QÑ/Ô/ÐWÐWÐWrH   r+   z.yamlz8validating an untrained model YAML will result in 0 mAP.ú:r   >   ÚnpuÚxpuÚcudaéÿÿÿÿ)Úmodelr2   Údnnr1   Úfp16Úchannels_lastrJ   Úptz2'augment' is not supported by this model (format='z'), ignoring.)r0   >   r_   ÚtorchscriptÚdynamicrB   ÚbatchzSetting batch=z input of shape (z, 3, z, ú)Úclassify)Úsplitú.>   ÚymlÚyaml>   r*   ÚposeÚdepthÚdetectÚsegmentÚsemanticz	Dataset 'z' for task=u    not found â�Œ>   rK   ÚmpsÚimx)r2   ÚmodeÚchannels)rB   Úon_val_start)r2   )ÚdescÚtotalÚon_val_batch_startÚimg)Úaugmenté   é   >   r   rZ   Úon_val_batch_endc              3  ó`   •K  — | ](}|j         t          ‰j        j        ¦  «        z  d z  V — Œ)dS )g     @�@N)ÚtÚlenr/   Údataset)rR   ÚxrE   s     €rF   ú	<genexpr>z)BaseValidator.__call__.<locals>.<genexpr>  s>   øè è € Ð5kÐ5kÐcd°a´c½CÀÄÔ@WÑ<XÔ<XÑ6XÐ[^Ñ6^Ð5kÐ5kÐ5kÐ5kÐ5kÐ5krH   Ú
on_val_endc                ób   — i | ],\  }}||                      ¦   «                              ¦   «         “Œ-S rN   )ÚcloneÚdetachrQ   s      rF   rU   z*BaseValidator.__call__.<locals>.<dictcomp>  s2   € ÐHÐHÐH©d¨a°�A�q—w’w‘y”y×'Ò'Ñ)Ô)ÐHÐHÐHrH   )ÚdstÚopc                ój   •— i | ]/\  }}||                      ¦   «         t          ‰j        ¦  «        z  “Œ0S rN   )rK   r}   r/   )rR   rS   rT   rE   s      €rF   rU   z*BaseValidator.__call__.<locals>.<dictcomp>!  s6   ø€ ÐOÐOÐO¹$¸!¸Q�A�q—u’u‘w”w¥ T¤_Ñ!5Ô!5Ñ5ÐOÐOÐOrH   Úval)Úprefixc                óP   — i | ]#\  }}|t          t          |¦  «        d ¦  «        “Œ$S )é   )ÚroundÚfloatrQ   s      rF   rU   z*BaseValidator.__call__.<locals>.<dictcomp>#  s.   € ÐFÐFÐF©d¨a°�A•u�U 1™XœX qÑ)Ô)ÐFÐFÐFrH   z]Speed: {:.1f}ms preprocess, {:.1f}ms inference, {:.1f}ms loss, {:.1f}ms postprocess per imagezpredictions.jsonÚwzutf-8)ÚencodingzSaving z...zResults saved to Úbold)lr4   Ú	get_modelr.   rw   ÚhasattrÚnmsrJ   r2   r1   ÚtypeÚampÚquantizer�   Ú
loss_itemsÚitemsr%   rC   ÚstopperÚpossible_stopÚepochÚepochsÚevalÚstrr[   Úendswithr   Úwarningr   Úadd_integration_callbacksr   r   r
   Úfractionre   r   r   r   rO   r   Úcurrent_devicer\   r^   r]   r0   ÚformatÚ
base_modelr   rB   ÚgetattrÚmaxÚmetadataÚgetrb   ÚinforA   r   Úrsplitr	   ÚFileNotFoundErrorr   ÚworkersÚrectr5   r/   Úget_dataloaderÚcompiler   ÚwarmupÚrun_callbacksr   r   Úget_descr}   Úinit_metricsr   r;   Ú	enumerater3   r#   r   r&   Úupdate_metricsÚplot_val_samplesÚplot_predictionsÚgather_statsÚ	get_statsÚdictÚzipr<   ÚkeysÚfinalize_metricsÚprint_resultsÚ
world_sizeÚvaluesÚdistÚreduceÚReduceOpÚAVGÚlabel_loss_itemsÚtupleÚ	save_jsonÚopenr=   ÚnameÚjsonÚdumpÚ	eval_jsonr   )rE   Útrainerr[   Úkwargsrw   Údevice_typer0   Úfmtr_   rB   ÚdtÚbarr3   rb   ÚpredsrS   rT   r7   r%   ÚresultsÚfs   `                    rF   Ú__call__zBaseValidator.__call__’   sw  ø€ ð   tÐ+ˆŒØ�”˜u gÐ8Ð8°Ð8Ð8ˆØ”)Ô#Ð;¨T¬]Ð):ˆØŒ=ð F	dÝ�u˜iÑ(Ô(ð 7Ø $¤	¤°Ð 6�”Ø!œ.ˆDŒKØœˆDŒIà(,¬Ô(8¸EÒ(AÐ(AÀgÄkÐ(A  ÐX\ˆDŒIÔØ—K’K‘M”MˆEØWÐW¸GÔ<N×<TÒ<TÑ<VÔ<VÐWÑWÔWˆDŒIØŒIˆOŒO˜wœÔ<ÐeÀÄÐRYÔR`ÐcdÑRdÒAdÑeˆOŒOØ�JŠJ‰LŒLˆL‰Lå�4”9”?Ñ#Ô#×,Ò,¨WÑ5Ô5ð [¸%¸-Ý”ÐYÑZÔZÐZÝÔ/°Ñ5Ô5Ð5Ý-­jÑ9Ô9ð fð fÝ!AÀ$Ä)Ä.ÐRVÔR[ÔRdÑ!eÔ!e�”	”ðfð fð fñ fô fð fð fð fð fð fð føøøð fð fð fð få˜dœiÔ.Ñ/Ô/×5Ò5°c¸1Ñ=Ô=¸aÔ@ˆKØ)4¸Ð)FÐ)F˜+˜+ÈFˆKÝØÐ.˜tœyœõ ˜2’:�:õ % T¤YÔ%5Ñ6Ô6Ð6å”\ +Õ/GÈÑ/TÔ/T×/cÒ/cÑ/eÔ/eÑfÔfØ”I”MØ”Y”^Ø”YÔ'¨2Ò-Ø"œiÔ5Øœ	œ¨Ð.ðñ ô ˆEð  œ,ˆDŒKØ',¤zÐ!;  °tˆDŒIÔØœ,¨¬�CˆFØ˜’ˆBØð  ˜uÔ/ð  Ý”ÐfÐTWÐfÐfÐfÑgÔgÐgØ�Ý ¤	¤¸Ð?Ñ?Ô?ˆEØÐ/Ð/Ð/½ÀÀyÐRWÑ8XÔ8XÐ/Ý˜5 'Ñ*Ô*ð ?Ý.1°%´+Ñ.>Ô.>Ð>�D”I”O eØ"'¤.×"4Ò"4°W¸aÑ"@Ô"@�”	”Ý”Ðv¨T¬Y¬_ÐvÐvÈtÌyÌÐvÐvÐejÐvÐvÐnsÐvÐvÐvÑwÔwÐwàŒyŒ~ Ò+Ð+Ý-¨d¬i¬nÀDÄIÄOÐTÑTÔT�”	�	Ý�T”Y”^Ñ$Ô$×+Ò+¨C°Ñ3Ô3°BÔ7¸?ÐJÐJÈdÌiÌnð að Oð Oõ .¨d¬i¬nÀDÄIÄOÐTÑTÔT�”	�	å'­Ð/t¸4¼9¼>Ð/tÐ/tÐVZÔV_ÔVdÐ/tÐ/tÐ/tÑ(uÔ(uÑvÔvÐvàŒ{Ô >Ð1Ð1Ø$%�”	Ô!Øð '�7 5¨)°UÑ;Ô;ð 'ÀÀuÂÀØ!&�”	”Øœ,ˆDŒKØœˆDŒJØ"œoÐu°×1DÒ1DÀTÄYÇ]Â]ÐSWÔS\ÔSbÑEcÔEcÐeiÔenÔetÑ1uÔ1uˆDŒOà�JŠJ‰LŒLˆLØŒyÔ ð [Ý'¨°d´kÈÌ	ÔHYÐZÑZÔZ�Ø�LŠL RÐ <  ¨T¬Y¬_¸d¼iÈ
Ô>SÐUZÐ\aÐbˆLÑcÔcÐcà×Ò˜>Ñ*Ô*Ð*å˜4œ;Ð'Ñ'Ô'Ý˜4œ;Ð'Ñ'Ô'Ý˜4œ;Ð'Ñ'Ô'Ý˜4œ;Ð'Ñ'Ô'ð	
ˆõ �4”?¨¯ª©¬ÅÀDÄOÑ@TÔ@TÐUÑUÔUˆØ×Ò�, uÑ-Ô-Ñ.Ô.Ð.ØˆŒ
Ý'¨™nœnð 	3ñ 	3‰NˆG�UØ×ÒÐ3Ñ4Ô4Ð4Ø"ˆDŒLà�A”ð /ð /ØŸš¨Ñ.Ô.�ð/ð /ð /ñ /ô /ð /ð /ð /ð /ð /ð /øøøð /ð /ð /ð /õ ˜$œ-ÐD¨D¬IÔ,>À"Ò,DÈTÌ[ÔM]Ð^Ñ^Ô^ð 	.ð 	.à˜”Uð Að AØ!˜E %¨¤,¸Ð@Ñ@Ô@�EðAð Að Añ Aô Að Að Að Að Að Að Aøøøð Að Að Að Að ˜”Uð .ð .Ø”}ð .Ø$)§J¢J¨u°eÑ$<Ô$<¸QÔ$?×$EÒ$EÑ$GÔ$Gð .ð .™D˜A˜qØ œI a˜L˜LœL¨AÑ-˜L˜L™L˜Lð.ð .ð .ñ .ô .ð .ð .ð .ð .ð .ð .øøøð .ð .ð .ð .ð	.ð 	.ð 	.ñ 	.ô 	.ð 	.ð 	.ð 	.ð 	.ð 	.ð 	.øøøð 	.ð 	.ð 	.ð 	.ð �A”ð 0ð 0Ø×(Ò(¨Ñ/Ô/�ð0ð 0ð 0ñ 0ô 0ð 0ð 0ð 0ð 0ð 0ð 0øøøð 0ð 0ð 0ð 0ð ×Ò  uÑ-Ô-Ð-ØŒyŒð = 7¨Q¢; ;µ4¸7°?°?Ø×%Ò% e¨WÑ5Ô5Ð5Ø×%Ò% e¨U°GÑ<Ô<Ð<à×ÒÐ1Ñ2Ô2Ð2Ñ2àˆØ×ÒÑÔÐÝ�7ˆ?ˆ?Ø—N’NÑ$Ô$ˆEÝ�c $¤*§/¢/Ñ"3Ô"3Ð5kÐ5kÐ5kÐ5kÐhjÐ5kÑ5kÔ5kÑlÔlÑmÔmˆDŒJØ×!Ò!Ñ#Ô#Ð#Ø×ÒÑ Ô Ð Ø×Ò˜|Ñ,Ô,Ð,àŒ=ð 	àHÐH°d´i·o²oÑ6GÔ6GÐHÑHÔHˆDØÔ! AÒ%Ð%ØŸš™œð @ð @�AÝ”K  q­T¬]Ô->Ð?Ñ?Ô?Ð?Ð?Ý�aŠxˆxØ�ØOÐOÐOÐOÀ$Ç*Â*Á,Ä,ÐOÑOÔOˆDØO˜ÐO '×":Ò":¸4ÈÐ":Ñ"NÔ"NÐOˆGØFÐF°g·m²m±o´oÐFÑFÔFÐFå�aŠxˆxØ�ÝŒKØvÐoÔvÝ˜4œ:×,Ò,Ñ.Ô.Ñ/Ô/ðñô ð ð
 ŒyÔ"ð . t¤zð .Ý�#˜dœmÐ.@Ñ@ÑAÔAÀ3ÐQXÐYÑYÔYð -Ð]^Ý”KÐ 5¨!¬&Ð 5Ð 5Ð 5Ñ6Ô6Ð6Ý”I˜dœj¨!Ñ,Ô,Ð,ð-ð -ð -ñ -ô -ð -ð -ð -ð -ð -ð -øøøð -ð -ð -ð -ð Ÿš uÑ-Ô-�ØŒyŒð S $¤)Ô"5ð SÝ”ÐQµ¸ÀÄÑ0OÔ0OÐQÐQÑRÔRÐRØˆLs£   Æ/F>Æ>GÇGÛ[%Û%[)	Û,[)	Ü 	_Ü)]	Ü=_Ý	]Ý_Ý]Ý_ÝA^9Þ-_Þ9^=Þ=_ß ^=ß_ß_	ß_	ß#`à`		à`		ê8këk!ë$k!FÚpred_classesútorch.TensorÚtrue_classesÚiouÚ	use_scipyÚboolÚreturnc                ó”  — t          j        |j        d         | j        j        d         f¦  «                             t
          ¦  «        }|dd…df         |k    }||z  }|                     ¦   «                              ¦   «         }t          | j                             ¦   «          	                    ¦   «         ¦  «        D �]w\  }}|r`|||k    z  }	|	 
                    ¦   «         rBt          |	 ¦  «        \  }
}|	|
|f         dk    }| 
                    ¦   «         rd|||         |f<   Œht          j        ||k    ¦  «        }t          j        |¦  «        j        }|j        d         rÑ|j        d         dk    r—|||dd…df         |dd…df         f                              ¦   «         ddd…                  }|t          j        |dd…df         d¬¦  «        d                  }|t          j        |dd…df         d¬¦  «        d                  }d||dd…df                              t"          ¦  «        |f<   �Œyt%          j        |¦  «        S )a&  Match predictions to ground truth objects using IoU.

        Args:
            pred_classes (torch.Tensor): Predicted class indices of shape (N,).
            true_classes (torch.Tensor): Target class indices of shape (M,).
            iou (torch.Tensor): An NxM tensor containing the pairwise IoU values for predictions and ground truth.
            use_scipy (bool, optional): Whether to use Hungarian one-to-one matching (more precise).

        Returns:
            (torch.Tensor): Correct tensor of shape (N, 10) for 10 IoU thresholds.
        r   NTr+   rZ   )Úreturn_index)ÚnpÚzerosÚshaper:   ÚastyperÝ   rK   Únumpyrµ   ÚtolistÚanyr   ÚnonzeroÚarrayÚTÚargsortÚuniqueÚintrO   Ú
from_numpy)rE   rØ   rÚ   rÛ   rÜ   ÚcorrectÚcorrect_classÚiÚ	thresholdÚcost_matrixÚ
labels_idxÚdetections_idxÚvalidÚmatchess                 rF   Úmatch_predictionszBaseValidator.match_predictions5  s=  € õ ”(˜LÔ.¨qÔ1°4´9´?À1Ô3EÐFÑGÔG×NÒNÍtÑTÔTˆà$ Q Q Q¨ WÔ-°Ò=ˆØ�MÑ!ˆØ�gŠg‰iŒi�oŠoÑÔˆÝ% d¤i§m¢m¡o¤o×&<Ò&<Ñ&>Ô&>Ñ?Ô?ð 	Añ 	A‰LˆAˆyØð AØ! S¨IÒ%5Ñ6�Ø—?’?Ñ$Ô$ð AÝ1FÈÀ|Ñ1TÔ1TÑ.�J Ø'¨
°NÐ(BÔCÀaÒG�EØ—y’y‘{”{ð AØ<@˜ ¨uÔ 5°qÐ 8Ñ9øåœ* S¨IÒ%5Ñ6Ô6�Ýœ( 7Ñ+Ô+Ô-�Ø”= Ô#ð AØ”} QÔ'¨!Ò+Ð+Ø")¨#¨g°a°a°a¸°d¬m¸WÀQÀQÀQÈÀT¼]Ð.JÔ*K×*SÒ*SÑ*UÔ*UÐVZÐVZÐXZÐVZÔ*[Ô"\˜Ø")­"¬)°G¸A¸A¸A¸q¸D´MÐPTÐ*UÑ*UÔ*UÐVWÔ*XÔ"Y˜Ø")­"¬)°G¸A¸A¸A¸q¸D´MÐPTÐ*UÑ*UÔ*UÐVWÔ*XÔ"Y˜Ø<@�G˜G A A A q DœM×0Ò0µÑ5Ô5°qÐ8Ñ9ùÝÔ Ñ(Ô(Ð(rH   c                ó<   — |�|j         j         nt          |¦  «        S )a�  Return the training EMA or an independent model for standalone validation.

        Args:
            model (torch.nn.Module | str | Path | None): Model or checkpoint for standalone validation.
            trainer (object, optional): Trainer whose EMA is used during training validation.

        Returns:
            (torch.nn.Module | str | Path | None): Model to prepare for inference.
        )Úemar   )rE   r[   rÎ   s      rF   r‘   zBaseValidator.get_model\  s   € ð #*Ð"5ˆwŒ{Œˆ½8ÀE¹?¼?ÐJrH   Úeventrž   c                óF   — | j         |                              |¦  «         dS )z1Append the given callback to the specified event.N)r   Úappend©rE   rû   Úcallbacks      rF   Úadd_callbackzBaseValidator.add_callbacki  s#   € àŒ�uÔ×$Ò$ XÑ.Ô.Ð.Ð.Ð.rH   c                óX   — | j                              |g ¦  «        D ]} || ¦  «         ŒdS )z4Run all callbacks associated with a specified event.N)r   r©   rþ   s      rF   r²   zBaseValidator.run_callbacksm  s<   € àœ×*Ò*¨5°"Ñ5Ô5ð 	ð 	ˆHØˆH�T‰NŒNˆNˆNð	ð 	rH   c                ó    — t          d¦  «        ‚)z1Get data loader from dataset path and batch size.z:get_dataloader function not implemented for this validator©ÚNotImplementedError)rE   Údataset_pathÚ
batch_sizes      rF   r¯   zBaseValidator.get_dataloaderr  s   € å!Ð"^Ñ_Ô_Ð_rH   c                ó    — t          d¦  «        ‚)zBuild dataset from image path.z3build_dataset function not implemented in validatorr  )rE   Úimg_paths     rF   Úbuild_datasetzBaseValidator.build_datasetv  s   € å!Ð"WÑXÔXÐXrH   c                ó   — |S )zPreprocess an input batch.rN   )rE   rb   s     rF   r#   zBaseValidator.preprocessz  ó   € àˆrH   c                ó   — |S )zPostprocess the predictions.rN   )rE   rÔ   s     rF   r&   zBaseValidator.postprocess~  r  rH   c                ó   — dS )z2Initialize performance metrics for the YOLO model.NrN   )rE   r[   s     rF   r´   zBaseValidator.init_metrics‚  ó   € € € rH   c                ó   — dS )z.Update metrics based on predictions and batch.NrN   ©rE   rÔ   rb   s      rF   r¶   zBaseValidator.update_metrics…  r  rH   c                ó   — dS )z Finalize and return all metrics.NrN   ©rE   s    rF   r¾   zBaseValidator.finalize_metricsˆ  r  rH   c                ó   — i S )z0Return statistics about the model's performance.rN   r  s    rF   rº   zBaseValidator.get_stats‹  s   € àˆ	rH   c                ó   — dS )zAGather statistics from all the GPUs during DDP training to GPU 0.NrN   r  s    rF   r¹   zBaseValidator.gather_stats�  r  rH   c                ó   — dS )z-Print the results of the model's predictions.NrN   r  s    rF   r¿   zBaseValidator.print_results’  r  rH   c                ó   — dS )z"Get description of the YOLO model.NrN   r  s    rF   r³   zBaseValidator.get_desc•  r  rH   c                ó   — g S )z8Return the metric keys used in YOLO training/validation.rN   r  s    rF   Úmetric_keyszBaseValidator.metric_keys˜  s	   € ð ˆ	rH   c                ó\   — |t          j         ¦   «         dœ| j        t          |¦  «        <   dS )zARegister a plot by its unique path for visualization and logging.)r1   Ú	timestampN)ÚtimerC   r   )rE   rÊ   r1   s      rF   Úon_plotzBaseValidator.on_plot�  s(   € à*.½T¼Y¹[¼[Ð!IÐ!IˆŒ
•4˜‘:”:ÑÐÐrH   c                ó   — dS )z(Plot validation samples during training.NrN   )rE   rb   Únis      rF   r·   zBaseValidator.plot_val_samples¡  r  rH   c                ó   — dS )z,Plot YOLO model predictions on batch images.NrN   )rE   rb   rÔ   r  s       rF   r¸   zBaseValidator.plot_predictions¤  r  rH   c                ó   — dS )z#Convert predictions to JSON format.NrN   r  s      rF   Úpred_to_jsonzBaseValidator.pred_to_json§  r  rH   c                ó   — dS )z9Evaluate and return JSON format of prediction statistics.NrN   )rE   r7   s     rF   rÍ   zBaseValidator.eval_jsonª  r  rH   )NNNN)r   r    )NN)F)
rØ   rÙ   rÚ   rÙ   rÛ   rÙ   rÜ   rÝ   rÞ   rÙ   )N)rû   rž   )Ú__name__Ú
__module__Ú__qualname__Ú__doc__rG   r   r×   rø   r‘   r   r²   r¯   r	  r#   r&   r´   r¶   r¾   rº   r¹   r¿   r³   Úpropertyr  r  r·   r¸   r!  rÍ   rN   rH   rF   r   r   ;   s  € € € € € ð0ð 0ðd"Ið "Ið "Ið "Ið "IðH ÐÑÔð`ð `ð `ñ Ôð`ðF lqð%)ð %)ð %)ð %)ð %)ðN Ð˜%Ñ Ô ð
Kð 
Kð 
Kñ !Ô ð
Kð/ð /ð /ð /ðð ð ð ð
`ð `ð `ðYð Yð Yðð ð ðð ð ðAð Að Að=ð =ð =ð/ð /ð /ðð ð ðPð Pð Pð<ð <ð <ð1ð 1ð 1ð ðð ñ „XððJð Jð Jð Jð7ð 7ð 7ð;ð ;ð ;ð2ð 2ð 2ðHð Hð Hð Hð HrH   r   ).r&  Ú
__future__r   rË   r  Úcopyr   Úpathlibr   rå   rá   rO   Útorch.distributedÚdistributedrÂ   Úultralytics.cfgr   r   Úultralytics.data.utilsr   r	   r
   Úultralytics.nn.autobackendr   Úultralytics.utilsr   r   r   r   r   r   r   Úultralytics.utils.checksr   Úultralytics.utils.opsr   r   Úultralytics.utils.torch_utilsr   r   r   r   r   r   r   r   rN   rH   rF   ú<module>r4     sÈ  ððð ð: #Ð "Ð "Ð "Ð "Ð "à €€€Ø €€€Ø Ð Ð Ð Ð Ð Ø Ð Ð Ð Ð Ð à Ð Ð Ð Ø €€€Ø  Ð  Ð  Ð  Ð  Ð  à 1Ð 1Ð 1Ð 1Ð 1Ð 1Ð 1Ð 1Ø iÐ iÐ iÐ iÐ iÐ iÐ iÐ iÐ iÐ iØ 2Ð 2Ð 2Ð 2Ð 2Ð 2Ø YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YÐ YØ 0Ð 0Ð 0Ð 0Ð 0Ð 0Ø @Ð @Ð @Ð @Ð @Ð @Ð @Ð @ðð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ð ðpHð pHð pHð pHð pHñ pHô pHð pHð pHð pHrH   