hfSSKrSSKrSSKJr SSKJr SSKJr "SS\5r "SS\ \5r g) N)LoadVisualPrompt)DetectionPredictor)SegmentationPredictorcl^\rSrSrSrS S\4U4SjjjrSrU4SjrS U4Sjjr U4Sjr S r S r U=r $) YOLOEVPDetectPredictor a A mixin class for YOLO-EVP (Enhanced Visual Prompting) predictors. This mixin provides common functionality for YOLO models that use visual prompting, including model setup, prompt handling, and preprocessing transformations. Attributes: model (torch.nn.Module): The YOLO model for inference. device (torch.device): Device to run the model on (CPU or CUDA). prompts (dict | torch.Tensor): Visual prompts containing class indices and bounding boxes or masks. Methods: setup_model: Initialize the YOLO model and set it to evaluation mode. set_prompts: Set the visual prompts for the model. pre_transform: Preprocess images and prompts before inference. inference: Run inference with visual prompts. get_vpe: Process source to get visual prompt embeddings. verbosec.>[TU]XS9 SUlg)z Set up the model for prediction. Args: model (torch.nn.Module): Model to load or use. verbose (bool, optional): If True, provides detailed logging. )r TN)super setup_model done_warmup)selfmodelr __class__s _/home/james-whalen/.local/lib/python3.13/site-packages/ultralytics/models/yolo/yoloe/predict.pyr "YOLOEVPDetectPredictor.setup_models E3cXlg)z Set the visual prompts for the model. Args: prompts (dict): Dictionary containing class indices and bounding boxes or masks. Must include a 'cls' key with class indices. N)prompts)rrs r set_prompts"YOLOEVPDetectPredictor.set_prompts*s  rc >[T U]U5nURRSS5nURRSS5nURSn[ U5S:Xa`UR USR SSUSR SSXSU5nURS5RUR5nGOuUc SUS 35e[U[5(a[S U55(d S US 35e[U[5(a[S U55(d S US 35e[ U5[ U5s=:Xa[ U5:Xd.O S [ U5S[ U5S[ U5S 35e[[ U55Vs/sH9nUR X(R SSXR SSXXX85PM; nn[RR R"R%USS9RUR5nUR&R((aUR+5UlU$UR-5UlU$s snf)a Preprocess images and prompts before inference. This method applies letterboxing to the input image and transforms the visual prompts (bounding boxes or masks) accordingly. Args: im (list): List containing a single input image. Returns: (list): Preprocessed image ready for model inference. Raises: ValueError: If neither valid bounding boxes nor masks are provided in the prompts. bboxesNmasksclsrzExpected bboxes, but got !c3V# UHn[U[R5v M! g7fN isinstancenpndarray.0bs r 7YOLOEVPDetectPredictor.pre_transform..Os!3^W]RSJq"**4M4MW]')z#Expected list[np.ndarray], but got c3V# UHn[U[R5v M! g7fr r!r%s rr(r)Rs!5bYaTUjBJJ6O6OYar*z-Expected same length for all inputs, but got vsT) batch_first)r pre_transformrpoplen_process_single_imageshape unsqueezetodevicer"listallrangetorchnnutilsrnn pad_sequencerfp16halffloat) rimimgrrcategoryvisualsrirs rr.$YOLOEVPDetectPredictor.pre_transform4sT g#B'!!(D1   $/<<& s8q=00Qbq1A2a5;;rPQ?T\fklG''*--dkk:G% L)B6(!'L L%fd++3^W]3^0^0^ 5fXQ? ^h--#5bYa5b2b2b 5hZqA br7c(m:s6{: ?By3x=/Y[\_`f\g[hhij : s3x(A**36<<+;RU[[!_hk[a[de( hhnn((55g45PSSTXT_T_`G)-w||~  ?Fmmo  s/AJcF>Ub[U5(a[R"U[RS9nURS:Xa USSS24n[ USUS- USUS- 5nXF-nUSSSS24==[ USUSU-- S- S- 5- ss'USSSS24==[ USUSU-- S- S- 5- ss'O;Ub-[TU]!U5n[R"U5nSXUS:H'O [S 5e[5RX1XE5$) af Process a single image by resizing bounding boxes or masks and generating visuals. Args: dst_shape (tuple): The target shape (height, width) of the image. src_shape (tuple): The original shape (height, width) of the image. category (str): The category of the image for visual prompts. bboxes (list | np.ndarray, optional): A list of bounding boxes in the format [x1, y1, x2, y2]. masks (np.ndarray, optional): A list of masks corresponding to the image. Returns: (torch.Tensor): The processed visuals for the image. Raises: ValueError: If neither `bboxes` nor `masks` are provided. N)dtyperr.rg?rz$Please provide valid bboxes or masks) r0r#arrayfloat32ndimminroundr r.stack ValueErrorr get_visuals) r dst_shape src_shaperCrrgain resized_masksrs rr1,YOLOEVPDetectPredictor._process_single_image`s8"  #f++XXfBJJ7F{{aay|il2IaL9Q<4OPD NF 319  ! y|d7J(Ja'ORU'U!V V  319  ! y|d7J(Ja'ORU'U!V V   !G1%8MHH]+E"#E3, CD D !--h6QQrcD>[TU]"U/UQ7SUR0UD6$)z Run inference with visual prompts. Args: im (torch.Tensor): Input image tensor. *args (Any): Variable length argument list. **kwargs (Any): Arbitrary keyword arguments. Returns: (torch.Tensor): Model prediction results. vpe)r inferencer)rrAargskwargsrs rrY YOLOEVPDetectPredictor.inferences(w GGGGGrcURU5 [UR5S:XdS5eURH1up#nURU5nUR X@R SS9s $ g)a Process the source to get the visual prompt embeddings (VPE). Args: source (str | Path | int | PIL.Image | np.ndarray | torch.Tensor | list | tuple): The source of the image to make predictions on. Accepts various types including file paths, URLs, PIL images, numpy arrays, and torch tensors. Returns: (torch.Tensor): The visual prompt embeddings (VPE) from the model. rz get_vpe only supports one image!T)rX return_vpeN) setup_sourcer0dataset preprocessrr)rsource_im0srAs rget_vpeYOLOEVPDetectPredictor.get_vpesf &!4<< A%I'II%,,JAQ&B::bllt:D D'r)r r)T)NN)__name__ __module__ __qualname____firstlineno____doc__boolr rr.r1rYre__static_attributes__ __classcell__)rs@rrr s=&  $   *X#RJ HEErrc\rSrSrSrSrg)YOLOEVPSegPredictorz\Predictor for YOLO-EVP segmentation tasks combining detection and segmentation capabilities.N)rgrhrirjrkrmrrrrrprpsfrrp) numpyr#r9ultralytics.data.augmentrultralytics.models.yolo.detectrultralytics.models.yolo.segmentrrrprrrrrws8 5=AXE/XEv 02G r