^j(ddlmZmZmZddlmZmZmZmZm Z ddl m Z m Z erddl mZddlmZmZerddlZdd lmZdd lmZej.eZee d Gd de Zy))AnyUnionoverload)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_processorcneZdZdZdZdZdZdZfdZe de e dfde e e zde d e ee e ffd Ze de ee e fde d e e ee e ffd Z dde e de ee e ffde e e zd zde d e ee e fe e ee e fzffd ZdZddZdZddZddd ee effdZxZS)ZeroShotObjectDetectionPipelinea 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 ft|di|t|d|jty)Nvision)super__init__r check_model_typer)selfkwargs __class__s |/var/www/ramen.bs-engineer-server.com/venv/lib/python3.12/site-packages/transformers/pipelines/zero_shot_object_detection.pyrz(ZeroShotObjectDetectionPipeline.__init__=s, "6"$) PQimagez Image.Imagecandidate_labelsrreturnc yNr)rr"r#rs r __call__z(ZeroShotObjectDetectionPipeline.__call__Cs #r!c yr&r)rr"rs r r'z(ZeroShotObjectDetectionPipeline.__call__Hsber!Nc :d|vr|jd}t|ttjfr||d}nNt|tt fr5t |r*t t| dt||Dfi|S |}t| |fi|}|S)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,K|] \}}||dyw)r+Nr).0imglabelss r z;ZeroShotObjectDetectionPipeline.__call__..spKCs?ps) pop isinstancestrrlisttuplerrr'zip)rr"r#rinputsresultsrs r r'z(ZeroShotObjectDetectionPipeline.__call__Ks~ V #%zz.9  ec5;;/ 0$:JKF e} -,u2E pSVW\^nSop  F'"64V4r!c \i}d|vr|d|d<i}d|vr|d|d<d|vr|d|d<|i|fS)Ntimeout thresholdtop_kr)rrpreprocess_paramspostprocess_paramss r _sanitize_parametersz4ZeroShotObjectDetectionPipeline._sanitize_parameterssc  +1)+< i ( & .4[.A { + f *0/ w ' "&888r!c#Kt|d|}|d}t|tr|jd}t j |j |jggtj}t|D]a\}}|j|d}|j|d} | j|j} |t|dz k(||d || cyw) Nr")r:r#,)dtypept)return_tensorsr )is_last target_sizecandidate_label)rr2r3splittorchtensorheightwidthint32 enumerate tokenizerimage_processortorBlen) rr7r:r"r#rFirG text_inputsimage_featuress r preprocessz*ZeroShotObjectDetectionPipeline.preprocesss6'?G<!"45 & ,/55c: llU\\5;;$?#@ T "+,<"=  A...NK!11%1MN+..tzz:N$4 5 99*#2  !   sC#C%c|jd}|jd}|jd}|jdi|}|||d|}|S)NrFrGrE)rFrGrEr)r1model)r model_inputsrFrGrEoutputs model_outputss r _forwardz(ZeroShotObjectDetectionPipeline._forwards_"&&}5 &**+<=""9-$**,|,(3dkwovw r!cjg}|D]}|d}t|}|jj|||dd}|djD]I}|d|j } |j |d|d} | || d} |j | Kt|dd }|r|d|}|S) NrGrF)rZr; target_sizesrscoresboxes)scorelabelboxc |dS)Nrar)xs r z=ZeroShotObjectDetectionPipeline.postprocess..s ' r!T)keyreverse)rrPpost_process_object_detectionnonzeroitem_get_bounding_boxappendsorted) rr[r;r<r8 model_outputrbrZindexrarcresults r postprocessz+ZeroShotObjectDetectionPipeline.postprocesss) 'L !23E*<8L**HH$ UbHcIG!*224 ')%0557,,WW-=e-DQ-GH#(5Ev&  ' '&:DI fuoGr!rcz torch.TensorcZ|jj\}}}}||||d}|S)a% 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. )xminyminxmaxymax)inttolist)rrcrtrurvrwbboxs r rlz1ZeroShotObjectDetectionPipeline._get_bounding_boxs;"%!1!1!3dD$    r!r&)g?N)__name__ __module__ __qualname____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrrrr3r4rdictr'r?rVr\rrrxrl __classcell__)rs@r rrsl@O #OR #3 -.#BES /#]`# d38n ##ed4S>2eced4PTUXZ]U]P^K_F`ee 48VS-d38n)==>VS /D0V V d38n T$sCx.%9 : : Vp 9&,^S#Xr!r)typingrrrutilsrrr r r baser rPILr image_utilsrrrItransformers.modeling_outputsrmodels.auto.modeling_autor get_loggerr{loggerrrr!r rsm''kk96=^   H %,FG[m[H[r!