.h5BdZddlZddlZddlmZddlZddlZddlm Z m Z ddl m Z m Z ddlmZddlmZmZmZmZmZddlmZdd lmZdd lmZmZmZmZGd d Zy) a Check a model's accuracy on a test or val split of a dataset. Usage: $ yolo mode=val model=yolo11n.pt data=coco8.yaml imgsz=640 Usage - formats: $ yolo mode=val model=yolo11n.pt # PyTorch yolo11n.torchscript # TorchScript yolo11n.onnx # ONNX Runtime or OpenCV DNN with dnn=True yolo11n_openvino_model # OpenVINO yolo11n.engine # TensorRT yolo11n.mlpackage # CoreML (macOS-only) yolo11n_saved_model # TensorFlow SavedModel yolo11n.pb # TensorFlow GraphDef yolo11n.tflite # TensorFlow Lite yolo11n_edgetpu.tflite # TensorFlow Edge TPU yolo11n_paddle_model # PaddlePaddle yolo11n.mnn # MNN yolo11n_ncnn_model # NCNN yolo11n_imx_model # Sony IMX yolo11n_rknn_model # Rockchip RKNN N)Path)get_cfg get_save_dir)check_cls_datasetcheck_det_dataset) AutoBackend)LOGGERTQDM callbackscolorstremojis) check_imgsz)Profile)attempt_compile select_devicesmart_inference_mode unwrap_modelc (eZdZdZddZeddZ d dejdejdejde d ejf d Z d e fd Z d e fd Z dZdZdZdZdZdZdZdZdZdZedZd!dZdZdZdZdZy)" 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 spaces 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 (torch.Tensor): Accumulated loss 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. Ncddl}t||_||_d|_d|_d|_d|_d|_d|_ d|_ d|_ d|_ d|_ d|_d|_ddddd|_|xst#|j|_|jj&r|j$dz n |j$j)dd|jj*,|jj,d k(rd nd |j_t/|jj0d |j_i|_|xst5j6|_y)a 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. rN) overridesTg) preprocess inferenceloss postprocesslabels)parentsexist_okobbg{Gz?gMbP?)max_dim) torchvisionrargs dataloaderstridedatadevicebatch_itrainingnamesseenstatsconfusion_matrixnciouvjdictspeedrsave_dirsave_txtmkdirconftaskrimgszplotsr get_default_callbacks)selfr$r2r# _callbacksr"s Z/var/www/html/ai-service/venv/lib/python3.12/site-packages/ultralytics/engine/validator.py__init__zBaseValidator.__init__^s% d+ $        $  $'c3WZ[  ;L$; %)YY%7%7 !T]]QQZ^imQn 99>> !%)YY^^u%ymlyamlclassify)splitz Dataset 'z ' for task=u not found ❌>r@mpsrchannels)r7 on_val_start)desctotalon_val_batch_startimg)augmenton_val_batch_endc3|K|]3}|jtjjz dz5yw)g@@N)tlenr$dataset).0xr:s r< z)BaseValidator.__call__..s01g_`!##DOO>"))#q1"5H-diinn= :--diinnDIIOOT '499>>:J+VZV_V_VdVdUees/t(uvv{{>1$% !75)U;EII!& ,,DK"oou1D1DTYY]]SWS\S\SbSbEceienenetet1uDO JJLyy  'dkkB LLRTYY__dii >SUZ\abL c >* 4;; ' 4;; ' 4;; ' 4;; '   4??DOO@TU ,u-. 'n 3NGU   3 4"DLA /. /A =eElG< =A ===IIE5!9!!<? ALAy!SI%56 ??$161U1UVa1b.J' N(BCaGEyy{<@u 5q 89**SI%56((7+--==#}}Q'!+")#gadmWQT].J*K*S*S*UVZXZVZ*["\")"))GAqDMPT*UVW*X"Y")"))GAqDMPT*UVW*X"Y<@GGAqDM005q89' A(||G5::l>Q>QRRr>eventc@|j|j|y)z1Append the given callback to the specified event.N)r appendr:rcallbacks r< add_callbackzBaseValidator.add_callback*s u$$X.r>cV|jj|gD] }|| y)z4Run all callbacks associated with a specified event.N)r r~rs r<rzBaseValidator.run_callbacks.s)**5"5 H TN r>ctd)z1Get data loader from dataset path and batch size.z:get_dataloader function not implemented for this validatorNotImplementedError)r: dataset_path batch_sizes r<rzBaseValidator.get_dataloader3s!"^__r>ctd)zBuild dataset from image path.z3build_dataset function not implemented in validatorr)r:img_paths r< build_datasetzBaseValidator.build_dataset7s!"WXXr>c|S)zPreprocess an input batch.)r:rFs r<rzBaseValidator.preprocess; r>c|S)zPostprocess the predictions.r)r:rs r<rzBaseValidator.postprocess?rr>cy)z2Initialize performance metrics for the YOLO model.Nr)r:rBs r<rzBaseValidator.init_metricsC r>cy)z.Update metrics based on predictions and batch.Nrr:rrFs r<rzBaseValidator.update_metricsGrr>cy)z Finalize and return all metrics.Nrr:s r<rzBaseValidator.finalize_metricsKrr>ciS)z0Return statistics about the model's performance.rrs r<rzBaseValidator.get_statsOs r>cy)z-Print the results of the model's predictions.Nrrs r<rzBaseValidator.print_resultsSrr>cy)z"Get description of the YOLO model.Nrrs r<rzBaseValidator.get_descWrr>cgS)z8Return the metric keys used in YOLO training/validation.rrs r< metric_keyszBaseValidator.metric_keys[s  r>c^|tjd|jt|<y)z!Register plots for visualization.)r& timestampN)timer8r)r:rr&s r<on_plotzBaseValidator.on_plot`s*.TYY[!I 4:r>cy)z(Plot validation samples during training.Nr)r:rFnis r<rzBaseValidator.plot_val_samplesdrr>cy)z,Plot YOLO model predictions on batch images.Nr)r:rFrrs r<rzBaseValidator.plot_predictionshrr>cy)z#Convert predictions to JSON format.Nrrs r< pred_to_jsonzBaseValidator.pred_to_jsonlrr>cy)z9Evaluate and return JSON format of prediction statistics.Nr)r:r,s r<rzBaseValidator.eval_jsonprr>)NNNN)NN)F)N)__name__ __module__ __qualname____doc__r=rrrnTensorrrrvrrrrrrrrrrrrpropertyrrrrrrrr>r<rr*s1f#IJyyxlq)S!LL)S8= )SKP<<)Sdh)S )SV/#/3 `Y     J    r>r) rrrpathlibrrrrnultralytics.cfgrrultralytics.data.utilsrrultralytics.nn.autobackendrultralytics.utilsr r r r r ultralytics.utils.checksrultralytics.utils.opsrultralytics.utils.torch_utilsrrrrrrr>r<rsB0  1G2GG0)llH H r>