h"SSKJr SSKJr SSKJr SSKrSSKJr SSK J r J r J r SSK Jr SSKJrJr S r"S S \5r"S S \5rg)) annotations)Path)AnyN) YOLODataset)ComposeFormat v8_transforms)DetectionValidator)colorstrops)RTDETRValidatorcN^\rSrSrSrSS.U4SjjrS U4SjjrS SjrSrU=r $) RTDETRDataseta? Real-Time DEtection and TRacking (RT-DETR) dataset class extending the base YOLODataset class. This specialized dataset class is designed for use with the RT-DETR object detection model and is optimized for real-time detection and tracking tasks. Attributes: augment (bool): Whether to apply data augmentation. rect (bool): Whether to use rectangular training. use_segments (bool): Whether to use segmentation masks. use_keypoints (bool): Whether to use keypoint annotations. imgsz (int): Target image size for training. Methods: load_image: Load one image from dataset index. build_transforms: Build transformation pipeline for the dataset. Examples: Initialize an RT-DETR dataset >>> dataset = RTDETRDataset(img_path="path/to/images", imgsz=640) >>> image, hw = dataset.load_image(0) N)datac*>[TU]"USU0UD6 g)a Initialize the RTDETRDataset class by inheriting from the YOLODataset class. This constructor sets up a dataset specifically optimized for the RT-DETR (Real-Time DEtection and TRacking) model, building upon the base YOLODataset functionality. Args: *args (Any): Variable length argument list passed to the parent YOLODataset class. data (dict | None): Dictionary containing dataset information. If None, default values will be used. **kwargs (Any): Additional keyword arguments passed to the parent YOLODataset class. rN)super__init__)selfrargskwargs __class__s W/home/james-whalen/.local/lib/python3.13/site-packages/ultralytics/models/rtdetr/val.pyrRTDETRDataset.__init__*s $4T4V4c>[TU]XS9$)a Load one image from dataset index 'i'. Args: i (int): Index of the image to load. rect_mode (bool, optional): Whether to use rectangular mode for batch inference. Returns: im (torch.Tensor): The loaded image. resized_hw (tuple): Height and width of the resized image with shape (2,). Examples: Load an image from the dataset >>> dataset = RTDETRDataset(img_path="path/to/images") >>> image, hw = dataset.load_image(0) )i rect_mode)r load_image)rrrrs rrRTDETRDataset.load_image8s"w!A!;;rc 4UR(aUR(aUR(d UROSUlUR(aUR(d UROSUlUR(aUR(d UROSUl[ XR USS9nO [/5nUR[SSURURSURURS95 U$)z Build transformation pipeline for the dataset. Args: hyp (dict, optional): Hyperparameters for transformations. Returns: (Compose): Composition of transformation functions. gT)stretchxywh) bbox_format normalize return_maskreturn_keypoint batch_idx mask_ratio mask_overlap)augmentrectmosaicmixupcutmixr imgszrappendr use_segments use_keypointsr) overlap_mask)rhyp transformss rbuild_transformsRTDETRDataset.build_transformsKs <<'+||DII3CJ%)\\$)) CI'+||DII3CJ&tZZdKJ!J " -- $ 2 2>> --  r)F)N) __name__ __module__ __qualname____firstlineno____doc__rrr7__static_attributes__ __classcell__)rs@rrrs&.$( 5 5<&rrc>\rSrSrSrSSjrS SjrS SjrSrg) r ka RTDETRValidator extends the DetectionValidator class to provide validation capabilities specifically tailored for the RT-DETR (Real-Time DETR) object detection model. The class allows building of an RTDETR-specific dataset for validation, applies Non-maximum suppression for post-processing, and updates evaluation metrics accordingly. Attributes: args (Namespace): Configuration arguments for validation. data (dict): Dataset configuration dictionary. Methods: build_dataset: Build an RTDETR Dataset for validation. postprocess: Apply Non-maximum suppression to prediction outputs. Examples: Initialize and run RT-DETR validation >>> from ultralytics.models.rtdetr import RTDETRValidator >>> args = dict(model="rtdetr-l.pt", data="coco8.yaml") >>> validator = RTDETRValidator(args=args) >>> validator() Notes: For further details on the attributes and methods, refer to the parent DetectionValidator class. Nc [UURRUSURSURR=(d S[ US35UR S9 $)af Build an RTDETR Dataset. Args: img_path (str): Path to the folder containing images. mode (str, optional): `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`. Returns: (RTDETRDataset): Dataset configured for RT-DETR validation. FNz: ) img_pathr0 batch_sizer+r5r,cacheprefixr)rrr0rFr r)rrDmodebatchs r build_datasetRTDETRValidator.build_datasetsT))// ))//)TtfBK(  rc[U[[45(dUS/nUSRup#nUSR SUS- 4SS9upVXPR R -n[R"SURS9/U-n[U5H{up[R"U 5n XhRS5up[R"XSU S/SS9n XRS S 9n XUR R :Xx'M} UV s/sHoSS2SS24U SS2S4U SS2S 4S .PM! sn $s sn f) a; Apply Non-maximum suppression to prediction outputs. Args: preds (torch.Tensor | list | tuple): Raw predictions from the model. If tensor, should have shape (batch_size, num_predictions, num_classes + 4) where last dimension contains bbox coords and class scores. Returns: (list[dict[str, torch.Tensor]]): List of dictionaries for each image, each containing: - 'bboxes': Tensor of shape (N, 4) with bounding box coordinates - 'conf': Tensor of shape (N,) with confidence scores - 'cls': Tensor of shape (N,) with class indices Nr)dim)r)device).NT) descending)bboxesconfcls) isinstancelisttupleshapesplitrr0torchzerosrQ enumerater xywh2xyxymaxcatargsortrU)rpredsbs_ndrTscoresoutputsrbboxscorerVpredxs r postprocessRTDETRValidator.postprocesss1 %$//DME!HNN rqBF <))//!;;vfmm<=B (GA==&Dr*JE99d)$4c)nE2ND  67Ddiinn45GJ )PWWw!QU8Qq!tWQq!tWEwWWWs&D>c ([US5nURnUR5(a [U5OUnUSR 5nUSSS/4==USSUR R - -ss'USSS/4==USSUR R - -ss'[R"U5nUS S 2S S24==US S 2SS 24S- -ss'[UR5US R5US R55Hlupxn URRUURUR[U 5UV s/sHn [U S5PM sn [US 5S .5 Mn g s sn f)a\ Serialize YOLO predictions to COCO json format. Args: predn (dict[str, torch.Tensor]): Predictions dictionary containing 'bboxes', 'conf', and 'cls' keys with bounding box coordinates, confidence scores, and class predictions. pbatch (dict[str, Any]): Batch dictionary containing 'imgsz', 'ori_shape', 'ratio_pad', and 'im_file'. im_filerT.r ori_shapeNrUrVrS)image_id file_name category_idrirj)rstem isnumericintclonerr0r xyxy2xywhziptolistjdictr1name class_mapround) rprednpbatchpathrxruboxbscrls r pred_to_jsonRTDETRValidator.pred_to_jsonsdF9%&yy $ 0 03t9dHo##% C!QKF;/2TYY__DD C!QKF;/2TYY__DDmmC  ArrE c!QR%j1n$ 3::<v)=)=)?uATATAVWGA! JJ   (!%#'>>#aΛ4!QU1a[!4"1a[  X 5s Fr9)valN)rcz7torch.Tensor | list[torch.Tensor] | tuple[torch.Tensor]returnzlist[dict[str, torch.Tensor]])rzdict[str, torch.Tensor]rzdict[str, Any]rNone) r:r;r<r=r>rJrmrr?r9rrr r ks*4 2XLX &XBrr ) __future__rpathlibrtypingrr\ultralytics.datarultralytics.data.augmentrrr ultralytics.models.yolo.detectr ultralytics.utilsr r __all__rr r9rrrsE# (CC=+ VKVro(or