h5jSSKrSSKrSSKJr SSKJr SSKJr SSKJ r SSK J r J r "SS\5r g) N)Image)classify_transforms) BasePredictor)Results) DEFAULT_CFGopscN^\rSrSrSr\SS4U4SjjrU4SjrSrSr Sr U=r $) ClassificationPredictor am A class extending the BasePredictor class for prediction based on a classification model. This predictor handles the specific requirements of classification models, including preprocessing images and postprocessing predictions to generate classification results. Attributes: args (dict): Configuration arguments for the predictor. Methods: preprocess: Convert input images to model-compatible format. postprocess: Process model predictions into Results objects. Notes: - Torchvision classification models can also be passed to the 'model' argument, i.e. model='resnet18'. Examples: >>> from ultralytics.utils import ASSETS >>> from ultralytics.models.yolo.classify import ClassificationPredictor >>> args = dict(model="yolo11n-cls.pt", source=ASSETS) >>> predictor = ClassificationPredictor(overrides=args) >>> predictor.predict_cli() NcH>[TU]XU5 SURlg)a6 Initialize the ClassificationPredictor with the specified configuration and set task to 'classify'. This constructor initializes a ClassificationPredictor instance, which extends BasePredictor for classification tasks. It ensures the task is set to 'classify' regardless of input configuration. Args: cfg (dict): Default configuration dictionary containing prediction settings. overrides (dict, optional): Configuration overrides that take precedence over cfg. _callbacks (list, optional): List of callback functions to be executed during prediction. classifyN)super__init__argstask)selfcfg overrides _callbacks __class__s b/home/james-whalen/.local/lib/python3.13/site-packages/ultralytics/models/yolo/classify/predict.pyr ClassificationPredictor.__init__&s 4# cH>[TU]U5 [URRS5(a[URRRRSS5(aMURRRRSR [ UR5:gOSnU(dURR(d[UR5UlgURRRUlg)z9Set up source and inference mode and classify transforms. transformsrsizeFN) r setup_sourcehasattrmodelrrmaximgszptr)rsourceupdatedrs rr$ClassificationPredictor.setup_source5s V$tzz''6674::CSCSC^C^CiCijkClnt;u;u JJ   ' ' 2 21 5 : :c$**o M  07djjmm  + QUQ[Q[QaQaQlQl rc J[U[R5(dk[R"UVs/sHJo R [ R "[R"U[R555PML snSS9n[U[R5(aUO[R"U5RURR5nURR(aUR5$UR!5$s snf)zVConvert input images to model-compatible tensor format with appropriate normalization.r)dim) isinstancetorchTensorstackrr fromarraycv2cvtColor COLOR_BGR2RGB from_numpytordevicefp16halffloat)rimgims r preprocess"ClassificationPredictor.preprocessAs#u||,,++adead[]b#BSBS1T!UVadeklC!ell33s9I9I#9NRRSWS]S]SdSde!ZZ__sxxz=#))+=fsAD c F[U[5(d[R"U5n[U[[45(aUSOUn[ XUR S5VVVs/sH%upEn[XVURRUS9PM' snnn$s snnnf)a Process predictions to return Results objects with classification probabilities. Args: preds (torch.Tensor): Raw predictions from the model. img (torch.Tensor): Input images after preprocessing. orig_imgs (list[np.ndarray] | torch.Tensor): Original images before preprocessing. Returns: (list[Results]): List of Results objects containing classification results for each image. r)pathnamesprobs) r(listrconvert_torch2numpy_batchtuplezipbatchrrr<)rpredsr6 orig_imgspredorig_imgimg_paths r postprocess#ClassificationPredictor.postprocessJs)T**55i@I&utUm<<a%-0$**Q-,P ,P( H4::3C3C4 P,P   s+,B)r) __name__ __module__ __qualname____firstlineno____doc__rrrr8rH__static_attributes__ __classcell__)rs@rr r s*0'$4 $  >  rr )r-r)PILrultralytics.data.augmentrultralytics.engine.predictorrultralytics.engine.resultsrultralytics.utilsrrr rrrWs* 86..P mP r