o i @sddlmZmZmZmZddlmZmZmZm Z m Z ddl m Z m Z er+ddlmZer:ddlZddlmZmZerBdd lmZe eZee d d Gd d d e ZdS)) TYPE_CHECKINGAnyUnionoverload)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_NAMES)ImageT)has_image_processorc s eZdZdZdZdZdZdZfddZddZ e d e e d fd e d e d eee e ffddZe d ee ed Bd e d e d eeee e ffddZd eee e feeee e fBffdd ZdddZddZdddZddd ee effddZZS)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). FTNcs<tj|i|t|dt}|t||dS)Nvision)super__init__r rcopyupdatercheck_model_type)selfargskwargsmapping __class__i/sda-disk/www/egybert/egybert_env/lib/python3.10/site-packages/transformers/pipelines/object_detection.pyr8s   z ObjectDetectionPipeline.__init__cKs:i}d|vr |d|d<i}d|vr|d|d<|i|fS)Ntimeout thresholdr!)rrpreprocess_paramspostprocess_kwargsr!r!r"_sanitize_parameters@s   z,ObjectDetectionPipeline._sanitize_parametersimagez Image.ImagerrreturncOdSNr!rr(rrr!r!r"__call__Isz ObjectDetectionPipeline.__call__cOr*r+r!r,r!r!r"r-Lscs0d|vrd|vr|d|d<tj|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)poprr-)rrrrr!r"r-Qs cCsjt||d}t|j|jgg}|j|gdd}||j}|jdur/|j|d|ddd}||d<|S)N)r#pt)r.return_tensorswordsboxes)textr4r2 target_size) rtorch IntTensorheightwidthimage_processortodtype tokenizer)rr(r#r6r/r!r!r" preprocessus   z"ObjectDetectionPipeline.preprocesscCsF|d}|jdi|}|d|i|}|jdur!|d|d<|S)Nr6bboxr!)r0modelr r>)r model_inputsr6outputs model_outputsr!r!r"_forwards   z ObjectDetectionPipeline._forward?c sL|d}jdurY|d\fdd|ddjddjdd\}}fdd |D}fd d |d dD}gd fd d t|||D}|Sj||} | d} | d}| d}| d}|| d<fdd |D| d<fdd |D| d<gd fdd t| d| d| dD}|S)Nr6rc sHt|dd|dd|dd|ddgS)Nrir r)_get_bounding_boxr7Tensor)r@)r9rr:r!r" unnormalizesz8ObjectDetectionPipeline.postprocess..unnormalizelogits)dimcsg|] }jjj|qSr!)rAconfigid2label).0 predictionrr!r" sz7ObjectDetectionPipeline.postprocess..csg|]}|qSr!r!)rPr@)rJr!r"rSsr@)scorelabelboxcs&g|]}|dkrtt|qS)rdictziprPvals)keysr$r!r"rSs&scoreslabelsr4csg|] }jjj|qSr!)rArNrOitem)rPrUrRr!r"rSscsg|]}|qSr!)rH)rPrVrRr!r"rSscsg|] }tt|qSr!rWrZ)r\r!r"rSs )r>tolistsqueezesoftmaxmaxrYr;post_process_object_detection) rrDr$r6r]classesr^r4 annotationraw_annotationsraw_annotationr!)r9r\rr$rJr:r" postprocesss. "    z#ObjectDetectionPipeline.postprocessrVz torch.TensorcCs&|\}}}}||||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)intr`)rrVrjrkrlrmr@r!r!r"rHs z)ObjectDetectionPipeline._get_bounding_boxr+)rF)__name__ __module__ __qualname____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrr'rrstrrlistrXr-r?rErirnrH __classcell__r!r!rr"rs2  0 2 $ "-r)typingrrrrutilsrrr r r baser r image_utilsrr7models.auto.modeling_autorrPILr get_loggerrologgerrr!r!r!r"s