sg ddlmZmZmZmZddlmZmZmZm Z m Z ddl m Z m Z erddlmZer ddlZddlmZmZe j(eZeeefZeeZee d Gd d e Zy) )AnyDictListUnion)add_end_docstringsis_torch_availableis_vision_availableloggingrequires_backends)Pipelinebuild_pipeline_init_args) load_imageN)(MODEL_FOR_OBJECT_DETECTION_MAPPING_NAMES,MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING_NAMEST)has_image_processorcxeZdZdZfdZdZdeeee fffd Z d dZ dZ d dZ d d deeeffd ZxZS)ObjectDetectionPipelinea Object detection pipeline using any `AutoModelForObjectDetection`. This pipeline predicts bounding boxes of objects and their classes. Example: ```python >>> from transformers import pipeline >>> detector = pipeline(model="facebook/detr-resnet-50") >>> detector("https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png") [{'score': 0.997, 'label': 'bird', 'box': {'xmin': 69, 'ymin': 171, 'xmax': 396, 'ymax': 507}}, {'score': 0.999, 'label': 'bird', 'box': {'xmin': 398, 'ymin': 105, 'xmax': 767, 'ymax': 507}}] >>> # x, y are expressed relative to the top left hand corner. ``` 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: `"object-detection"`. See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=object-detection). ct||i||jdk(rtd|jdt |dt j}|jt|j|y)NtfzThe z is only available in PyTorch.vision) super__init__ framework ValueError __class__r rcopyupdatercheck_model_type)selfargskwargsmappingrs Z/var/www/html/venv/lib/python3.12/site-packages/transformers/pipelines/object_detection.pyrz ObjectDetectionPipeline.__init__4sn $)&) >>T !tDNN#33QRS S$):??ACD g&c Di}d|vr|d|d<i}d|vr|d|d<|i|fS)Ntimeout threshold)r!r#preprocess_paramspostprocess_kwargss r%_sanitize_parametersz,ObjectDetectionPipeline._sanitize_parameters?sL  +1)+< i ( & .4[.A { + "&888r&returncZd|vrd|vr|jd|d<t||i|S)ai Detect objects (bounding boxes & classes) in the image(s) passed as inputs. Args: inputs (`str`, `List[str]`, `PIL.Image` or `List[PIL.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 directly The pipeline accepts either a single image or a batch of images. Images in a batch must all be in the same format: all as HTTP(S) links, all as local paths, or all as PIL images. threshold (`float`, *optional*, defaults to 0.5): The probability necessary to make a prediction. 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 dictionaries or a list of list of dictionaries containing the result. If the input is a single image, will return a list of dictionaries, if the input is a list of several images, will return a list of list of dictionaries corresponding to each image. The dictionaries contain the following keys: - **label** (`str`) -- The class label identified by the model. - **score** (`float`) -- The score attributed by the model for that label. - **box** (`List[Dict[str, int]]`) -- The bounding box of detected object in image's original size. imagesinputs)popr__call__)r!r"r#rs r%r3z ObjectDetectionPipeline.__call__Hs=@ v (&"8%zz(3F8 w000r&cJt||}tj|j|jgg}|j |gd}|j dk(r|j|j}|j|j|d|dd}||d<|S)N)r(pt)r0return_tensorswordsboxes)textr8r6 target_size) rtorch IntTensorheightwidthimage_processorrto torch_dtype tokenizer)r!imager(r:r1s r% preprocessz"ObjectDetectionPipeline.preprocessls5'2oo ekk'B&CD %%eWT%J >>T !YYt//0F >> %^^w`d^eF +} r&c|jd}|jdi|}|jd|i|}|j|d|d<|S)Nr:bboxr*)r2modelrrB)r! model_inputsr:outputs model_outputss r%_forwardz ObjectDetectionPipeline._forwardws^"&&}5 $**,|,))=+*Q*QR >> %$0$8M& !r&c 6|d}j|dj\fd}|djdjdj d\}}|jDcgc]%}j j j|'}}|djdD cgc] } ||  } } gd} t|j|| D cgc] } | d|kDs tt| | "} } | Sjj|||}|d}|d }|d }|d } |j|d <|Dcgc]3}j j j|j5c}|d <| Dcgc]}j|c}|d <gd} t|d |d |d D cgc]} tt| | } } | Scc}wcc} wcc} wcc}wcc}wcc} w) Nr:rc jtj|dzdz |dzdz |dzdz |dzdz gS)Nrir r)_get_bounding_boxr;Tensor)rFr=r!r>s r% unnormalizez8ObjectDetectionPipeline.postprocess..unnormalizesi--LL"T!W_t3#d1g-4"T!W_t3#d1g-4   r&logits)dimrF)scorelabelboxscoreslabelsr8)rBtolistsqueezesoftmaxmaxrGconfigid2labelzipdictr?post_process_object_detectionitemrO)r!rJr)r:rQrXclasses predictionrYrFr8keysvals annotationraw_annotationsraw_annotationrVrWr=r>s` @@r% postprocessz#ObjectDetectionPipeline.postprocesss$#M2 >> %(N113MFE ,H5==a@HHRHPTTY[T\OFGOV~~O_`djj''00<`F`3@3H3P3PQR3ST4[&TET,DH0 H>H!8H #HHrWz torch.Tensorc|jdk7r td|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. r5z9The ObjectDetectionPipeline is only available in PyTorch.)xminyminxmaxymax)rrintrZ)r!rWrmrnrorprFs r%rOz)ObjectDetectionPipeline._get_bounding_boxsS >>T !XY Y!$!1!1!3dD$    r&)N)g?)__name__ __module__ __qualname____doc__rr-r Predictionsr Predictionr3rDrKrkrstrrqrO __classcell__)rs@r%rrsY0 '9"15d:>N1N+O"1H +Z^S#Xr&r)typingrrrrutilsrr r r r baserr image_utilsrr;models.auto.modeling_autorr get_loggerrrloggerrxrwrvrr*r&r%rs))kk4(   H %#s(^ : ,FGdhdHdr&