|h&ddlZddlZddlmZddlmZmZmZmZddlZ ddl m Z ddl m Z mZddlmZddlmZddlmZddlmZmZdd lmZdd lmZmZmZdd lmZm Z Gd d eZ!y)N)copy)AnyDictListOptional)build_dataloaderbuild_yolo_dataset) BaseTrainer)yolo)DetectionModel)LOGGERRANK)override_configs) plot_images plot_labels plot_results) de_paralleltorch_distributed_zero_firstc eZdZdZddededeefdZddeded edefd Zde d e fd Z d Z ddeedeede fdZ dZddeeedefdZdZde eefded dfdZdZdZfdZxZS) DetectionTrainera A class extending the BaseTrainer class for training based on a detection model. This trainer specializes in object detection tasks, handling the specific requirements for training YOLO models for object detection including dataset building, data loading, preprocessing, and model configuration. Attributes: model (DetectionModel): The YOLO detection model being trained. data (Dict): Dictionary containing dataset information including class names and number of classes. loss_names (tuple): Names of the loss components used in training (box_loss, cls_loss, dfl_loss). Methods: build_dataset: Build YOLO dataset for training or validation. get_dataloader: Construct and return dataloader for the specified mode. preprocess_batch: Preprocess a batch of images by scaling and converting to float. set_model_attributes: Set model attributes based on dataset information. get_model: Return a YOLO detection model. get_validator: Return a validator for model evaluation. label_loss_items: Return a loss dictionary with labeled training loss items. progress_string: Return a formatted string of training progress. plot_training_samples: Plot training samples with their annotations. plot_metrics: Plot metrics from a CSV file. plot_training_labels: Create a labeled training plot of the YOLO model. auto_batch: Calculate optimal batch size based on model memory requirements. Examples: >>> from ultralytics.models.yolo.detect import DetectionTrainer >>> args = dict(model="yolo11n.pt", data="coco8.yaml", epochs=3) >>> trainer = DetectionTrainer(overrides=args) >>> trainer.train() Nimg_pathmodebatchc tt|jr-t|jjjndd}t |j |||j||dk(|S)a Build YOLO Dataset for training or validation. Args: img_path (str): Path to the folder containing images. mode (str): 'train' mode or 'val' mode, users are able to customize different augmentations for each mode. batch (int, optional): Size of batches, this is for 'rect' mode. Returns: (Dataset): YOLO dataset object configured for the specified mode. r val)rrectstride)maxintmodelrrr argsdata)selfrrrgss c/var/www/html/test/engine/venv/lib/python3.12/site-packages/ultralytics/models/yolo/detect/train.py build_datasetzDetectionTrainer.build_dataset6s]TZZ[,33779QOQS T!$))XudiidY]afYfoqrr dataset_path batch_sizerankcb|dvs Jd|dt|5|j|||}ddd|dk(}tddr|rtjdd}|dk(r|j j n|j j d z}t|||||S#1swYwxYw) a Construct and return dataloader for the specified mode. Args: dataset_path (str): Path to the dataset. batch_size (int): Number of images per batch. rank (int): Process rank for distributed training. mode (str): 'train' for training dataloader, 'val' for validation dataloader. Returns: (DataLoader): PyTorch dataloader object. >rtrainz#Mode must be 'train' or 'val', not .Nr-rFzJ'rect=True' is incompatible with DataLoader shuffle, setting shuffle=False)rr'getattrr warningr"workersr)r$r)r*r+rdatasetshuffler2s r&get_dataloaderzDetectionTrainer.get_dataloaderEs''V+NtfTU)VV' )$ / I((tZHG I'/ 7FE *w NNg hG'+w$))##DIIFGDIIa"ft{{23dkkA}}00BZ_d0eE%L s?9E$c|jd|j_|jd|j_|j|j_y)z2Set model attributes based on dataset information.ncnamesN)r#r!rSrTr"r$s r&set_model_attributesz%DetectionTrainer.set_model_attributesws;  $ 99W- )) r(cfgweightsverbosect||jd|jd|xr tdk(}|r|j||S)aF Return a YOLO detection model. Args: cfg (str, optional): Path to model configuration file. weights (str, optional): Path to model weights. verbose (bool): Whether to display model information. Returns: (DetectionModel): YOLO detection model. rSchannels)rSchrY)r r#rload)r$rWrXrYr!s r& get_modelzDetectionTrainer.get_modelsFstyy499Z;PZaZpfjnpfpq  JJw  r(cd|_tjj|j|j t |j|jS)z6Return a DetectionValidator for YOLO model validation.)box_losscls_lossdfl_loss)save_dirr" _callbacks) loss_namesr detectDetectionValidator test_loaderrdrr" callbacksrUs r& get_validatorzDetectionTrainer.get_validatorsG<{{--   t}}4 ?W[WeWe.  r( loss_itemsprefixc|jDcgc] }|d| }}|7|Dcgc]}tt|d}}tt ||S|Scc}wcc}w)ah Return a loss dict with labeled training loss items tensor. Args: loss_items (List[float], optional): List of loss values. prefix (str): Prefix for keys in the returned dictionary. Returns: (Dict | List): Dictionary of labeled loss items if loss_items is provided, otherwise list of keys. /)rfroundrAdictzip)r$rlrmrOkeyss r&label_loss_itemsz!DetectionTrainer.label_loss_itemssh*.9A6(!A399  !6@A%a!,AJAD*-. .K :As AAcjdddt|jzzzddg|jddzS)z`Return a formatted string of training progress with epoch, GPU memory, loss, instances and size. z%11sEpochGPU_mem InstancesSize)lenrfrUs r&progress_stringz DetectionTrainer.progress_stringsTvS%9!9::  ? __?   ?  ?   r(nic^t||d|jd|dz |jy)z Plot training samples with their annotations. Args: batch (Dict[str, Any]): Dictionary containing batch data. ni (int): Number of iterations. im_file train_batchz.jpg)labelspathsfnameon_plotN)rrdr)r$rrs r&plot_training_samplesz&DetectionTrainer.plot_training_sampless3  "--Kt4"88LL  r(cFt|j|jy)zPlot metrics from a CSV file.)filerN)rcsvrrUs r& plot_metricszDetectionTrainer.plot_metricss$((DLL9r(ctj|jjjDcgc]}|d c}d}tj|jjjDcgc]}|d c}d}t ||j |jd|j|jycc}wcc}w)z1Create a labeled training plot of the YOLO model.bboxesrclsrT)rTrdrN) np concatenate train_loaderr3rrsqueezer#rdr)r$lbboxesrs r&plot_training_labelsz%DetectionTrainer.plot_training_labelsst7H7H7P7P7W7WX8 XZ[\nn$2C2C2K2K2R2RSBbiSUVWE3;;= '0BT]]dhdpdpq YSs C 7 Cc t|jddi5|_|j|jddd}dddt dj Dd z}~t ||S#1swY8xYw) z Get optimal batch size by calculating memory occupation of model. Returns: (int): Optimal batch size. cacheF) overridesr-)rrNc38K|]}t|dyw)rN)r}).0labels r& z.DetectionTrainer.auto_batch..sN#eEl+Nsrx)rr"r'r#rrsuper auto_batch)r$ train_dataset max_num_obj __class__s r&rzDetectionTrainer.auto_batchsdiiGU3C D [  ..tyy/AWY.ZM [N9M9MNNQRR w!+..  [ [s 'A99B)r-N)rrr-)NNT)Nr-)__name__ __module__ __qualname____doc__strrr r'r5rrQrVboolr_rkrrArur~rrrrr __classcell__)rs@r&rrs@ sc s sxPS} sM3MCMCM[^M.dt6$Xc]HSM[_" 8DK+@QT$   4S>  s  t  :r / /r(r)"rGrCrtypingrrrrnumpyrtorch.nnrIultralytics.datarr ultralytics.engine.trainerr ultralytics.modelsr ultralytics.nn.tasksr ultralytics.utilsr rultralytics.utils.patchesrultralytics.utils.plottingrrrultralytics.utils.torch_utilsrrrr(r&rsE ,,A2#/*6MMSE/{E/r(