a h!@sddlmZmZmZmZddlmZmZmZm Z m Z ddl m Z m Z erVddlmZertddlZddlmZmZerdd 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)Zhas_image_processorc seZdZdZdZdZdZdZfddZddZ e e e d fe e eee e fd d d Ze e ee ed fe e eeee e fd d d Ze eee e feeee e ffdfdd ZdddZddZdddZdee efdddZZS)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). FTNcsXtj|i||jdkr.td|jdt|dt}|t | |dS)NtfzThe z is only available in PyTorch.Zvision) super__init__ framework ValueError __class__r rcopyupdaterZcheck_model_type)selfargskwargsmappingrc/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/pipelines/object_detection.pyr8s   z ObjectDetectionPipeline.__init__cKs:i}d|vr|d|d<i}d|vr0|d|d<|i|fS)Ntimeout thresholdr!)rrZpreprocess_paramsZpostprocess_kwargsr!r!r"_sanitize_parametersCs  z,ObjectDetectionPipeline._sanitize_parametersz Image.Image)imagerrreturncOsdSNr!rr&rrr!r!r"__call__Lsz ObjectDetectionPipeline.__call__cOsdSr(r!r)r!r!r"r*Os)r'cs0d|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*)rrrr r!r"r*Ts cCstt||d}t|j|jgg}|j|gdd}|jdkrF||j}|j durh|j |d|ddd}||d<|S)N)r#pt)r+return_tensorswordsboxes)textr1r/ target_size) rtorchZ IntTensorheightwidthimage_processorrtoZdtype tokenizer)rr&r#r3r,r!r!r" preprocessxs    z"ObjectDetectionPipeline.preprocesscCsF|d}|jfi|}|d|i|}|jdurB|d|d<|S)Nr3bbox)r-modelrr9)rZ model_inputsr3outputs model_outputsr!r!r"_forwards    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)Nr3rc sHt|dd|dd|dd|ddgS)Nrir r)_get_bounding_boxr4ZTensor)r;)r5rr6r!r" unnormalizesz8ObjectDetectionPipeline.postprocess..unnormalizeZlogits)dimcsg|]}jjj|qSr!)r<configid2label).0Z predictionrr!r" z7ObjectDetectionPipeline.postprocess..csg|] }|qSr!r!)rHr;)rCr!r"rJrKr;)Zscorelabelboxcs&g|]}|dkrtt|qS)rdictziprHvals)keysr$r!r"rJrKscoreslabelsr1csg|]}jjj|qSr!)r<rFrGitem)rHrLrIr!r"rJrKcsg|]}|qSr!)rB)rHrMrIr!r"rJrKcsg|]}tt|qSr!rNrQ)rSr!r"rJs)r9tolistZsqueezeZsoftmaxmaxrPr7Zpost_process_object_detection) rr>r$r3rTclassesrUr1 annotationZraw_annotationsZraw_annotationr!)r5rSrr$rCr6r" postprocesss,  ""  z#ObjectDetectionPipeline.postprocessz torch.Tensor)rMr'cCs8|jdkrtd|\}}}}||||d}|S)a% Turns list [xmin, xmax, ymin, ymax] into dict { "xmin": xmin, ... } Args: box (`torch.Tensor`): Tensor containing the coordinates in corners format. Returns: bbox (`dict[str, int]`): Dict containing the coordinates in corners format. r.z9The ObjectDetectionPipeline is only available in PyTorch.)xminyminxmaxymax)rrintrW)rrMr\r]r^r_r;r!r!r"rBs z)ObjectDetectionPipeline._get_bounding_box)N)r@)__name__ __module__ __qualname____doc__Z_load_processorZ_load_image_processorZ_load_feature_extractorZ_load_tokenizerrr%rrstrrlistrOr*r:r?r[r`rB __classcell__r!r!r r"rs$  *6$  -r)typingrrrrutilsrrr r r baser rZ image_utilsrr4Zmodels.auto.modeling_autorrZPILrZ get_loggerraloggerrr!r!r!r"s