a  d@sddlmZmZmZmZddlmZmZmZm Z m Z ddl m Z m Z erVddlmZertddlZddlmZmZe eZeeefZeeZee Gd d d e ZdS) )AnyDictListUnion)add_end_docstringsis_torch_availableis_vision_availableloggingrequires_backends)PIPELINE_INIT_ARGSPipeline) load_imageN)"MODEL_FOR_OBJECT_DETECTION_MAPPING&MODEL_FOR_TOKEN_CLASSIFICATION_MAPPINGcsxeZdZdZfddZddZeeee fdfdd Z d d Z d d Z dddZ deeefdddZZS)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). csVtj|i||jdkr.td|jdt|d|tt t dS)NtfzThe z is only available in PyTorch.Zvision) super__init__ framework ValueError __class__r Zcheck_model_typedictritemsrselfargskwargsrp/var/www/html/stable-diffusion-webui/venv/lib/python3.9/site-packages/transformers/pipelines/object_detection.pyr1s  z ObjectDetectionPipeline.__init__cKs"i}d|vr|d|d<ii|fS)N thresholdr )rrZpostprocess_kwargsr r r!_sanitize_parameters<s z,ObjectDetectionPipeline._sanitize_parameters)returncstj|i|S)a Detect objects (bounding boxes & classes) in the image(s) passed as inputs. Args: images (`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 0.9): The probability necessary to make a prediction. 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. )r__call__rrr r!r%Bsz ObjectDetectionPipeline.__call__cCsZt|}t|j|jgg}|j|gdd}|jdurN|j|d|ddd}||d<|S)Npt)Zimagesreturn_tensorswordsboxes)textr)r' target_size)rtorchZ IntTensorheightwidthimage_processor tokenizer)rimager+inputsr r r! preprocessas z"ObjectDetectionPipeline.preprocesscCsF|d}|jfi|}|d|i|}|jdurB|d|d<|S)Nr+bbox)popmodelrr0)rZ model_inputsr+outputs model_outputsr r r!_forwardjs    z ObjectDetectionPipeline._forward?c sJ|d}jdur|d\fdd|ddjddjdd\}}fdd |D}fd d |d dD}gd fd d t|||D}nj||} | d} | d}| d}| d}|| d<fdd |D| d<fdd |D| d<gd fdd t| d| d| dD}|S)Nr+rc sHt|dd|dd|dd|ddgS)Nrir r)_get_bounding_boxr,ZTensor)r4)r-rr.r r! unnormalizeysz8ObjectDetectionPipeline.postprocess..unnormalizeZlogits)Zdimcsg|]}jjj|qSr )r6configid2label).0Z predictionrr r! z7ObjectDetectionPipeline.postprocess..csg|] }|qSr r )rAr4)r=r r!rCrDr4)Zscorelabelboxcs&g|]}|dkrtt|qS)rrziprAvals)keysr"r r!rCrDscoreslabelsr)csg|]}jjj|qSr )r6r?r@item)rArErBr r!rCrDcsg|]}|qSr )r<)rArFrBr r!rCrDcsg|]}tt|qSr rGrI)rKr r!rCs)r0tolistZsqueezeZsoftmaxmaxrHr/Zpost_process_object_detection) rr8r"r+rLclassesrMr) annotationZraw_annotationsZraw_annotationr )r-rKrr"r=r.r! postprocessrs,  ""  z#ObjectDetectionPipeline.postprocessz torch.Tensor)rFr$cCs8|jdkrtd|\}}}}||||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. r&z9The ObjectDetectionPipeline is only available in PyTorch.)xminyminxmaxymax)rrintrO)rrFrTrUrVrWr4r r r!r<s z)ObjectDetectionPipeline._get_bounding_box)r:)__name__ __module__ __qualname____doc__rr#r Predictionsr Predictionr%r3r9rSrstrrXr< __classcell__r r rr!rs   -r)typingrrrrutilsrrr r r baser rZ image_utilsrr,Zmodels.auto.modeling_autorrZ get_loggerrYloggerr_r^r]rr r r r!s