9i6HSSKrSSKrSSKJrJr SSKrSSKrSSKrSSK J r J r J r J r SSKJr SSKJr SSKJrJr SSKJr SSKJrJrJr SS KJr SS KJr SS KJ r S \ l!\ "5r"S /r#\RH"\RJ\RLS9"SS \55r'g)N)AnyDict)Image ImageDraw ImageFile ImageFont) Pipelines) OutputKeys)InputPipeline) PIPELINES) _get_anchorsgenerate post_process) LoadImage)Tasks) get_loggerTTBSDetectionPipeline) module_namec^\rSrSrSrS/SSSS.r\S5rS \4U4S jjr S \ S \ \\ 44S jr S \ \\ 4S \ \\ 44SjrS \ \\ 4S \ \\ 44SjrSrU=r$)raTBS Detection Pipeline. Example: ```python >>> from modelscope.pipelines import pipeline >>> tbs_detect = pipeline(Tasks.image_object_detection, model='landingAI/LD_CytoBrainCerv') >>> tbs_detect(input='data/test/images/tbs_detection.jpg') { "boxes": [ [ 446.9007568359375, 36.374977111816406, 907.0919189453125, 337.439208984375 ], [ 454.3310241699219, 336.08477783203125, 921.26904296875, 641.7871704101562 ] ], "labels": [ ["Positive"] ], "scores": [ 0.9296008944511414, 0.9260380268096924 ] } >>> # ``` positive)rg?g333333?) class_namesmodel_image_size confidenceioucNXR;aURU$SU-S-$)NzUnrecognized attribute name '') _defaults)clsns n/var/www/html/land-doc-ocr/venv/lib/python3.13/site-packages/modelscope/pipelines/cv/tbs_detection_pipeline.py get_defaults!TBSDetectionPipeline.get_defaultsKs+ ==# #2Q6< <modelc >[TU]"SUSS.UD6 URRUR5 [ U5Ul[U5 g)z$ model: model id on modelscope hub. F)r( auto_collateN)super__init____dict__updater!ranchorsr)selfr(kwargs __class__s r$r-TBSDetectionPipeline.__init__RsE Cu5CFC T^^,#D) r'inputreturncd[R"U5nUR[5nX!S.nU$)a Detect objects (bounding boxes) in the image(s) passed as inputs. Args: input (`Image` or `List[Image]`): The pipeline handles three types of images: - A string containing an HTTP(S) link pointing to an image - A string containing a local path to an image - An image loaded in PIL or opencv directly The pipeline accepts either a single image or a batch of images. Images in a batch must all be in the same format. Return: A dictionary of result or a list of dictionary of result. If the input is an image, a dictionary is returned. If input is a list of image, a list of dictionary is returned. The dictionary contain the following keys: - **scores** (`List[float]`) -- The detection score for each card in the image. - **boxes** (`List[float]) -- The bounding boxe [x1, y1, x2, y2] of detected objects in in image's original size. - **labels** (`List[str]`, optional) -- The boxes's class_names of detected object in image. )imgimg_path)rconvert_to_ndarrayastypefloat)r1r5r8results r$ preprocessTBSDetectionPipeline.preprocess[s/6**51jj0 r'c2USR[R5n[R"US5nUR[R 5n[R "US- S5n[R"U5R[R5n[R"USS9n[RRURS5n[R "USS 9nU"UR#55nXaS S .nU$) Nr8)rrgo@)rr)dimzpytorch_yolov4.ptT) weights_onlyr9)datar9)r;npuint8cv2resizefloat32 transposetorch from_numpytype FloatTensor unsqueezeospathjoinr(loadcuda)r1r5r8tmp_inp model_pathr(outputsr=s r$forwardTBSDetectionPipeline.forward{sEl!!"((+jjj)jj$,,sU{I6""7+001B1BCoog1-WW\\$**.AB  :D9 #!Z/@A r'c[XSUS5upEUc$[R/[R/0nU$[RUR 5[R S/[RU0nU$)NrEr9Positive)rr SCORESBOXEStolistLABELS)r1r5argsr2bboxesscoresrXs r$ postprocess TBSDetectionPipeline.postprocesssv&d&M5;LM >!(("j.>.>CGN   v}}    |   f  r')r0)__name__ __module__ __qualname____firstlineno____doc__r! classmethodr%strr-r rrr>rYrd__static_attributes__ __classcell__)r3s@r$rrs"H#|) I== c$sCx.@ T#s(^ S#X  c3h !%c3h  r')(colorsysrQtypingrrrHnumpyrFrLPILrrrrmodelscope.metainfor modelscope.outputsr modelscope.pipelines.baser r modelscope.pipelines.builderr 1modelscope.pipelines.cv.tbs_detection_utils.utilsrrrmodelscope.preprocessorsrmodelscope.utils.constantrmodelscope.utils.loggerrLOAD_TRUNCATED_IMAGESlogger__all__register_moduleimage_object_detection tbs_detectionrr+r'r$rs   66))52MM/+."&   ! "    i.E.EGu8uGur'