.h:)ddlmZddlZddlZddlmZddlmZddlZddl Z ddl m Z ddl m Z mZddlmZddlmZddlmZdd lmZmZmZdd lmZdd lmZmZdd lmZm Z Gd deZ!y)) annotationsN)copy)Any)build_dataloaderbuild_yolo_dataset) BaseTrainer)yolo)DetectionModel) DEFAULT_CFGLOGGERRANK)override_configs) plot_images plot_labels)torch_distributed_zero_first unwrap_modelceZdZdZeddfdfd ZdddZdddZddZdZ dddZ d Z ddd Z d Z dd Zd ZfdZxZS)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_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() Nc(t||||y)a Initialize a DetectionTrainer object for training YOLO object detection model training. Args: cfg (dict, optional): Default configuration dictionary containing training parameters. overrides (dict, optional): Dictionary of parameter overrides for the default configuration. _callbacks (list, optional): List of callback functions to be executed during training. N)super__init__)selfcfg overrides _callbacks __class__s b/var/www/html/ai-service/venv/lib/python3.12/site-packages/ultralytics/models/yolo/detect/train.pyrzDetectionTrainer.__init__8s i4c 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)moderectstride)maxintmodelrr$rargsdata)rimg_pathr"batchgss r build_datasetzDetectionTrainer.build_datasetCs]djj\$**-4488:aPRT U!$))XudiidY]afYfoqrrrc |dvs Jd|dt|5|j|||}ddd|dk(}tddr|rtjdd}t |||dk(r|j jn|j jd z|||j jxr|dk( S#1swYxYw) 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. >r!trainz#Mode must be 'train' or 'val', not .Nr/r#FzJ'rect=True' is incompatible with DataLoader shuffle, setting shuffle=False)r+workersshufflerank drop_last) rr-getattrr warningrr(r2compile)r dataset_path batch_sizer4r"datasetr3s rget_dataloaderzDetectionTrainer.get_dataloaderRs''V+NtfTU)VV' )$ / I((tZHG I'/ 7FE *w NNg hG )-DII%%dii>O>ORS>Sii'';DGO    I Is CC cp|jD]W\}}t|tjs!|j |j |j j dk(||<Y|djdz |d<|jjr|d}tjt|jjdzt|jjdz|jz|jz|jz}|t|j ddz }|d k7ro|j ddDcgc]4}t#j$||z|jz |jz6}}t&j(j+||d d }||d<|Scc}w) a Preprocess a batch of images by scaling and converting to float. Args: batch (dict): Dictionary containing batch data with 'img' tensor. Returns: (dict): Preprocessed batch with normalized images. cuda) non_blockingimgg?g?r1NbilinearF)sizer" align_corners)items isinstancetorchTensortodevicetypefloatr( multi_scalerandom randranger&imgszr$r%shapemathceilnn functional interpolate) rr+kvimgsszsfxnss rpreprocess_batchz!DetectionTrainer.preprocess_batchosKKM VDAq!U\\*44 $++:J:Jf:T4Ua VU|))+c1e 99 FGDIIa"ft{{23dkkA}}00BZ_d0eE%L s9F3c|jd|j_|jd|j_|j|j_y)z2Set model attributes based on dataset information.ncnamesN)r)r'rarbr(rs rset_model_attributesz%DetectionTrainer.set_model_attributess;  $ 99W- )) rct||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. rachannels)rachverbose)r r)r load)rrweightsrir's r get_modelzDetectionTrainer.get_modelsFstyy499Z;PZaZpfjnpfpq  JJw  rcd|_tjj|j|j t |j|jS)z6Return a DetectionValidator for YOLO model validation.)box_losscls_lossdfl_loss)save_dirr(r) loss_namesr detectDetectionValidator test_loaderrqrr( callbacksrcs r get_validatorzDetectionTrainer.get_validatorsG<{{--   t}}4 ?W[WeWe.  rc|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. /)rrroundrMdictzip)r loss_itemsprefixr]keyss rlabel_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)lenrrrcs rprogress_stringz DetectionTrainer.progress_stringsTvS%9!9::  ? __?   ?  ?   rc^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)rrqr)rr+nis rplot_training_samplesz&DetectionTrainer.plot_training_sampless3  "--Kt4"88LL  rctj|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.bboxesrclsrb)rbrqrN) np concatenate train_loaderr;rrsqueezer)rqr)rlbboxesrs rplot_training_labelsz%DetectionTrainer.plot_training_labelsst7H7H7P7P7W7WX8 XZ[\nn$2C2C2K2K2R2RSBbiSUVWE3;;= '0BT]]dhdpdpq YSs C 7 Cc t|jddi5|_|j|jddd}dddt dj Dd z}~t ||S#1swY8xYw) z Get optimal batch size by calculating memory occupation of model. Returns: (int): Optimal batch size. cacheF)rr/)r"r+Nc38K|]}t|dyw)rN)r).0labels r z.DetectionTrainer.auto_batch..sN#eEl+Nsr)rr(r-r)r%rr auto_batch)r train_dataset max_num_objrs rrzDetectionTrainer.auto_batchsdiiGU3C D [  ..tyy/AWY.ZM [N9M9MNNQRR w!+..  [ [s 'A99B)rzdict[str, Any] | None)r/N)r*strr"rr+z int | None)rrr/)r9rr:r&r4r&r"r)r+r|returnr|)NNT)r str | Nonerkrribool)Nr/)r~zlist[float] | Nonerr)r+zdict[str, Any]rr&rNone)__name__ __module__ __qualname____doc__r rr-r<r_rdrlrwrrrrr __classcell__)rs@rrrsU>'4\` 5 s :<$" $   r / /rr)" __future__rrSrOrtypingrnumpyrrHtorch.nnrUultralytics.datarrultralytics.engine.trainerrultralytics.modelsr ultralytics.nn.tasksr ultralytics.utilsr r r ultralytics.utils.patchesrultralytics.utils.plottingrrultralytics.utils.torch_utilsrrrrrrsH#  A2#/776?TT/{T/r