/jrddlmZddlmZddlmZddlmZddlmZm Z ddl m Z m Z Gdd eZ d S) ) annotations)copy)DetectionTrainer)RTDETRDetectionModel)RANKcolorstr) RTDETRDatasetRTDETRValidatorc,eZdZdZddd ZdddZdZdS) RTDETRTraineraTrainer class for the RT-DETR model developed by Baidu for real-time object detection. This class extends the DetectionTrainer class for YOLO to adapt to the specific features and architecture of RT-DETR. The model leverages Vision Transformers and has capabilities like IoU-aware query selection and adaptable inference speed. Attributes: loss_names (tuple): Names of the loss components used for training. data (dict): Dataset configuration containing class count and other parameters. args (dict): Training arguments and hyperparameters. save_dir (Path): Directory to save training results. test_loader (DataLoader): DataLoader for validation/testing data. Methods: get_model: Initialize and return an RT-DETR model for object detection tasks. build_dataset: Build and return an RT-DETR dataset for training or validation. get_validator: Return a DetectionValidator suitable for RT-DETR model validation. Examples: >>> from ultralytics.models.rtdetr.train import RTDETRTrainer >>> args = dict(model="rtdetr-l.yaml", data="coco8.yaml", imgsz=640, epochs=3) >>> trainer = RTDETRTrainer(overrides=args) >>> trainer.train() Notes: - F.grid_sample used in RT-DETR does not support the `deterministic=True` argument. - AMP training can lead to NaN outputs and may produce errors during bipartite graph matching. NTcfg dict | Noneweights str | Noneverboseboolct||jd|jd|o tdk}|r|||S)aWInitialize and return an RT-DETR model for object detection tasks. Args: cfg (dict, optional): Model configuration. weights (str, optional): Path to pre-trained model weights. verbose (bool): Verbose logging if True. Returns: (RTDETRDetectionModel): Initialized model. ncchannels)rchr)rdatarload)selfrrrmodels d/home/longshao/multi-rider-rag/.venv/lib/python3.11/site-packages/ultralytics/models/rtdetr/train.py get_modelzRTDETRTrainer.get_model,sS%STYt_:AV`g`vlptvlvwww  JJw    valimg_pathstrmodebatch int | Nonect||jj||dk|jd|jjpd|jjpdt |d|jj|j|dkr |jjnd S)asBuild and return an RT-DETR dataset for training or validation. Args: img_path (str): Path to the folder containing images. mode (str): Dataset mode, either 'train' or 'val'. batch (int, optional): Batch size for rectangle training. Returns: (RTDETRDataset): Dataset object for the specific mode. trainFNz: g?) r!imgsz batch_sizeaugmenthyprectcache single_clsprefixclassesrfraction) r argsr(r-r.rr0rr1)rr!r#r$s r build_datasetzRTDETRTrainer.build_dataset<s)/GO )/)Ty+4utKKK((I%+/7??TY''    rcld|_t|j|jt |jS)z@Return an RTDETRValidator suitable for RT-DETR model validation.) giou_losscls_lossl1_loss)save_dirr2) loss_namesr test_loaderr8rr2)rs r get_validatorzRTDETRTrainer.get_validatorVs-<t/$-dSWS\oo^^^^r)NNT)rrrrrr)r N)r!r"r#r"r$r%)__name__ __module__ __qualname____doc__rr3r;rrr r sd:      4_____rr N) __future__rrultralytics.models.yolo.detectrultralytics.nn.tasksrultralytics.utilsrrr r r r r@rrrEs#""""";;;;;;555555,,,,,,,,////////K_K_K_K_K_$K_K_K_K_K_r