cCi) SSKJrJrJrJr SSKJrJrJrJ r J r SSK J r J r \"5(aSSKJr SSKJrJr \"5(aSSKrSS KJr SS KJr \ R0"\5r\"\ "S S 95"S S\ 55rg))AnyOptionalUnionoverload)add_end_docstringsis_torch_availableis_vision_availableloggingrequires_backends) ChunkPipelinebuild_pipeline_init_args)Image) load_image valid_imagesN)BaseModelOutput)2MODEL_FOR_ZERO_SHOT_OBJECT_DETECTION_MAPPING_NAMEST)has_image_processorc^\rSrSrSrSrSrSrSrU4Sjr \ S\ \ S4S\ \ \ \ 4S \S \ \\ \44S j5r\ S\ \\ \4S \S \ \ \\ \44S j5rSS\ \ S\ \\ \44S\\ \ \ \ 4S \S \ \ \\ \4\ \ \\ \444U4S jjjrSrSSjrSrSSjrSSS \\ \44SjrSrU=r$)ZeroShotObjectDetectionPipelineaN Zero shot object detection pipeline using `OwlViTForObjectDetection`. This pipeline predicts bounding boxes of objects when you provide an image and a set of `candidate_labels`. Example: ```python >>> from transformers import pipeline >>> detector = pipeline(model="google/owlvit-base-patch32", task="zero-shot-object-detection") >>> detector( ... "http://images.cocodataset.org/val2017/000000039769.jpg", ... candidate_labels=["cat", "couch"], ... ) [{'score': 0.287, 'label': 'cat', 'box': {'xmin': 324, 'ymin': 20, 'xmax': 640, 'ymax': 373}}, {'score': 0.254, 'label': 'cat', 'box': {'xmin': 1, 'ymin': 55, 'xmax': 315, 'ymax': 472}}, {'score': 0.121, 'label': 'couch', 'box': {'xmin': 4, 'ymin': 0, 'xmax': 642, 'ymax': 476}}] >>> detector( ... "https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png", ... candidate_labels=["head", "bird"], ... ) [{'score': 0.119, 'label': 'bird', 'box': {'xmin': 71, 'ymin': 170, 'xmax': 410, 'ymax': 508}}] ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This object detection pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"zero-shot-object-detection"`. See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=zero-shot-object-detection). FTc >[TU]"S0UD6 URS:Xa[SURS35e[ US5 UR [5 g)NtfzThe z is only available in PyTorch.vision)super__init__ framework ValueError __class__r check_model_typer)selfkwargsr!s k/home/james-whalen/.local/lib/python3.13/site-packages/transformers/pipelines/zero_shot_object_detection.pyr(ZeroShotObjectDetectionPipeline.__init__=sR "6" >>T !tDNN#33QRS S$) PQimagez Image.Imagecandidate_labelsr$returnc gNr)r#r(r)r$s r%__call__(ZeroShotObjectDetectionPipeline.__call__Fs #r'c gr,r)r#r(r$s r%r-r.Ksber'c \>SU;aURS5n[U[[R45(aXS.nOX[U[[ 45(a:[ U5(a*[ [TU] "S[X5540UD65$Un[TU] "U40UD6nU$)a$ Detect objects (bounding boxes & classes) in the image(s) passed as inputs. Args: image (`str`, `PIL.Image` or `list[dict[str, Any]]`): The pipeline handles three types of images: - A string containing an http url pointing to an image - A string containing a local path to an image - An image loaded in PIL directly You can use this parameter to send directly a list of images, or a dataset or a generator like so: ```python >>> from transformers import pipeline >>> detector = pipeline(model="google/owlvit-base-patch32", task="zero-shot-object-detection") >>> detector( ... [ ... { ... "image": "http://images.cocodataset.org/val2017/000000039769.jpg", ... "candidate_labels": ["cat", "couch"], ... }, ... { ... "image": "http://images.cocodataset.org/val2017/000000039769.jpg", ... "candidate_labels": ["cat", "couch"], ... }, ... ] ... ) [[{'score': 0.287, 'label': 'cat', 'box': {'xmin': 324, 'ymin': 20, 'xmax': 640, 'ymax': 373}}, {'score': 0.25, 'label': 'cat', 'box': {'xmin': 1, 'ymin': 55, 'xmax': 315, 'ymax': 472}}, {'score': 0.121, 'label': 'couch', 'box': {'xmin': 4, 'ymin': 0, 'xmax': 642, 'ymax': 476}}], [{'score': 0.287, 'label': 'cat', 'box': {'xmin': 324, 'ymin': 20, 'xmax': 640, 'ymax': 373}}, {'score': 0.254, 'label': 'cat', 'box': {'xmin': 1, 'ymin': 55, 'xmax': 315, 'ymax': 472}}, {'score': 0.121, 'label': 'couch', 'box': {'xmin': 4, 'ymin': 0, 'xmax': 642, 'ymax': 476}}]] ``` candidate_labels (`str` or `list[str]` or `list[list[str]]`): What the model should recognize in the image. threshold (`float`, *optional*, defaults to 0.1): The probability necessary to make a prediction. top_k (`int`, *optional*, defaults to None): The number of top predictions that will be returned by the pipeline. If the provided number is `None` or higher than the number of predictions available, it will default to the number of predictions. timeout (`float`, *optional*, defaults to None): The maximum time in seconds to wait for fetching images from the web. If None, no timeout is set and the call may block forever. Return: A list of lists containing prediction results, one list per input image. Each list contains dictionaries with the following keys: - **label** (`str`) -- Text query corresponding to the found object. - **score** (`float`) -- Score corresponding to the object (between 0 and 1). - **box** (`dict[str,int]`) -- Bounding box of the detected object in image's original size. It is a dictionary with `x_min`, `x_max`, `y_min`, `y_max` keys. text_queriesr(r)c3.# UH upXS.v M g7f)r2Nr).0imglabelss r% ;ZeroShotObjectDetectionPipeline.__call__..spSoKCs?Sos) pop isinstancestrrlisttuplerrr-zip)r#r(r)r$inputsresultsr!s r%r-r.Ns~ V #%zz.9  ec5;;/ 0 0$KF e} - -,u2E2E pSVW\Sop  F'"64V4r'c h0nSU;aUSUS'0nSU;aUSUS'SU;aUSUS'U0U4$)Ntimeout thresholdtop_kr)r#r$preprocess_paramspostprocess_paramss r%_sanitize_parameters4ZeroShotObjectDetectionPipeline._sanitize_parameterssc  +1)+< i ( & .4[.A { + f *0/ w ' "&888r'c## [USUS9nUSn[U[5(aURS5n[R "UR UR//[RS9n[U5H}upgURXpRS9nURX0RS9n URS:XaU RUR5n U[U5S- :HUUS .UEU Ev M g7f) Nr()rBr),)dtype)return_tensorsptr )is_last target_sizecandidate_label)rr:r;splittorchtensorheightwidthint32 enumerate tokenizerrimage_processortorKlen) r#r?rBr(r)rOirP text_inputsimage_featuress r% preprocess*ZeroShotObjectDetectionPipeline.preprocesss6'?G<!"45 & , ,/55c: llU\\5;;$?#@ T "+,<"= A...XK!11%1WN~~%!/!2!24::!>$4 5 99*#2  !   #>sDDcURS5nURS5nURS5nUR"S0UD6nX#US.UEnU$)NrOrPrN)rOrPrNr)r9model)r# model_inputsrOrPrNoutputs model_outputss r%_forward(ZeroShotObjectDetectionPipeline._forwards["&&}5 &**+<=""9-**,|,(3dkwovw r'cl/nUHnUSn[U5nURRXRUSS9SnUSR5HInUSUR 5n UR USUS5n XU S.n UR U 5 MK M [USS S 9nU(aUSUnU$) NrPrO)rdrC target_sizesrscoresboxes)scorelabelboxc US$)Nrlr)xs r%=ZeroShotObjectDetectionPipeline.postprocess..s' r'T)keyreverse)rrYpost_process_object_detectionnonzeroitem_get_bounding_boxappendsorted) r#rerCrDr@ model_outputrmrdindexrlrnresults r% postprocess+ZeroShotObjectDetectionPipeline.postprocesss)L !23E*<8L**HH$ UbHcIG!*224)%0557,,WW-=e-DQ-GH#(Ev& 5*&:DI fuoGr'rnz torch.TensorcURS:wa [S5eUR5R5up#pEUUUUS.nU$)z Turns list [xmin, xmax, ymin, ymax] into dict { "xmin": xmin, ... } Args: box (`torch.Tensor`): Tensor containing the coordinates in corners format. Returns: bbox (`dict[str, int]`): Dict containing the coordinates in corners format. rMzAThe ZeroShotObjectDetectionPipeline is only available in PyTorch.)xminyminxmaxymax)rr inttolist)r#rnrrrrbboxs r%rx1ZeroShotObjectDetectionPipeline._get_bounding_boxsO >>T !`a a!$!1!1!3D    r'rr,)g?N)__name__ __module__ __qualname____firstlineno____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrrrr;r<rdictr-rrGr_rfr~rrx__static_attributes__ __classcell__)r!s@r%rrs@O #OR#3 -.#BGTRUYBW#cf# d38n ##ed4S>2eced4PTUXZ]U]P^K_F`ee =AVS-d38n)==>V#5d3i#89V V tDcN#T$tCH~*>%?? @ VVp 9(,^S#Xr'r)typingrrrrutilsrr r r r baserrPILr image_utilsrrrRtransformers.modeling_outputsrmodels.auto.modeling_autor get_loggerrloggerrrr'r%rsq11kk96=^   H %,FGamaHar'