a yfe@s`ddlmZddlZddlmZddlmZddlmZmZddl m Z m Z Gdd d eZ dS) )copyN)DetectionTrainer)RTDETRDetectionModel)RANKcolorstr) RTDETRDatasetRTDETRValidatorcs<eZdZdZd ddZdddZd d Zfd d ZZS) RTDETRTrainera( Trainer class for the RT-DETR model developed by Baidu for real-time object detection. Extends the DetectionTrainer class for YOLO to adapt to the specific features and architecture of RT-DETR. This model leverages Vision Transformers and has capabilities like IoU-aware query selection and adaptable inference speed. 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. Example: ```python 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() ``` NTcCs.t||jd|otdkd}|r*|||S)a Initialize and return an RT-DETR model for object detection tasks. Args: cfg (dict, optional): Model configuration. Defaults to None. weights (str, optional): Path to pre-trained model weights. Defaults to None. verbose (bool): Verbose logging if True. Defaults to True. Returns: (RTDETRDetectionModel): Initialized model. nc)r verbose)rdatarload)selfcfgweightsr modelr[/var/www/html/django/DPS/env/lib/python3.9/site-packages/ultralytics/models/rtdetr/train.py get_model"s  zRTDETRTrainer.get_modelvalc Cs8t||jj||dk|jd|jjp"dt|d|jd S)a Build 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. Defaults to None. Returns: (RTDETRDataset): Dataset object for the specific mode. trainFNz: ) img_pathimgszZ batch_sizeZaugmentZhyprectcacheprefixr)rargsrrrr)rrmodebatchrrr build_dataset3s   zRTDETRTrainer.build_datasetcCsd|_t|j|jt|jdS)z Returns a DetectionValidator suitable for RT-DETR model validation. Returns: (RTDETRValidator): Validator object for model validation. )Z giou_lossZcls_lossZl1_loss)save_dirr)Z loss_namesr Z test_loaderr"rr)rrrr get_validatorKszRTDETRTrainer.get_validatorcs~t|}t|d}|d}gg}}t|D]F}||d||k|j||d||kj|jtjdq2|S)z Preprocess a batch of images. Scales and converts the images to float format. Args: batch (dict): Dictionary containing a batch of images, bboxes, and labels. Returns: (dict): Preprocessed batch. Zimg batch_idxZbboxescls)deviceZdtype) superpreprocess_batchlenrangeappendtor&torchlong)rr bsr$Zgt_bboxZgt_classi __class__rrr(Us    &zRTDETRTrainer.preprocess_batch)NNT)rN) __name__ __module__ __qualname____doc__rr!r#r( __classcell__rrr1rr s    r ) rr-Zultralytics.models.yolo.detectrZultralytics.nn.tasksrZultralytics.utilsrrrrr r rrrrs