fTh% SSKJrJrJrJr SSKrSSKJrJ r J r J r J r SSK JrJr \ "5(a SSKJr SSKJr \ "5(a SS KJrJrJrJr \ R2"\5r\\\4r\\r\"\"S S 95"S S \55rg))AnyDictListUnionN)add_end_docstringsis_torch_availableis_vision_availableloggingrequires_backends)Pipelinebuild_pipeline_init_args)Image) load_image)*MODEL_FOR_IMAGE_SEGMENTATION_MAPPING_NAMES-MODEL_FOR_INSTANCE_SEGMENTATION_MAPPING_NAMES-MODEL_FOR_SEMANTIC_SEGMENTATION_MAPPING_NAMES.MODEL_FOR_UNIVERSAL_SEGMENTATION_MAPPING_NAMEST)has_image_processorcv^\rSrSrSrU4SjrSrS S\\\ \ 44U4Sjjjr S Sjr Sr S S jrS rU=r$)ImageSegmentationPipelineat Image segmentation pipeline using any `AutoModelForXXXSegmentation`. This pipeline predicts masks of objects and their classes. Example: ```python >>> from transformers import pipeline >>> segmenter = pipeline(model="facebook/detr-resnet-50-panoptic") >>> segments = segmenter("https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png") >>> len(segments) 2 >>> segments[0]["label"] 'bird' >>> segments[1]["label"] 'bird' >>> type(segments[0]["mask"]) # This is a black and white mask showing where is the bird on the original image. >>> segments[0]["mask"].size (768, 512) ``` This image segmentation pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"image-segmentation"`. See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=image-segmentation). cZ>[TU]"U0UD6 URS:Xa[SURS35e[ US5 [ R"5nUR[5 UR[5 UR[5 URU5 g)NtfzThe z is only available in PyTorch.vision) super__init__ framework ValueError __class__r rcopyupdaterrrcheck_model_type)selfargskwargsmappingr!s a/var/www/auris/envauris/lib/python3.13/site-packages/transformers/pipelines/image_segmentation.pyr"ImageSegmentationPipeline.__init__Cs $)&) >>T !tDNN#33QRS S$)<AACDEDEEF g&c 0n0nSU;aUSUS'USUS'SU;aUSUS'SU;aUSUS'SU;aUSUS'SU;aUSUS'U0U4$)Nsubtask thresholdmask_thresholdoverlap_mask_area_thresholdtimeout)r%r'preprocess_kwargspostprocess_kwargss r)_sanitize_parameters.ImageSegmentationPipeline._sanitize_parametersPs  ,29,= y )+1)+< i ( & .4[.A { + v %39:J3K / 0 (F 2@FGd@e < =  +1)+< i ( "&888r+returnc p>SU;aURS5nUc [S5e[TU] "U40UD6$)a Perform segmentation (detect masks & 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. subtask (`str`, *optional*): Segmentation task to be performed, choose [`semantic`, `instance` and `panoptic`] depending on model capabilities. If not set, the pipeline will attempt tp resolve in the following order: `panoptic`, `instance`, `semantic`. threshold (`float`, *optional*, defaults to 0.9): Probability threshold to filter out predicted masks. mask_threshold (`float`, *optional*, defaults to 0.5): Threshold to use when turning the predicted masks into binary values. overlap_mask_area_threshold (`float`, *optional*, defaults to 0.5): Mask overlap threshold to eliminate small, disconnected segments. 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 dictionary or a 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 mask, label and score (where applicable) of each detected object and contains the following keys: - **label** (`str`) -- The class label identified by the model. - **mask** (`PIL.Image`) -- A binary mask of the detected object as a Pil Image of shape (width, height) of the original image. Returns a mask filled with zeros if no object is found. - **score** (*optional* `float`) -- Optionally, when the model is capable of estimating a confidence of the "object" described by the label and the mask. imageszICannot call the image-classification pipeline without an inputs argument!)popr r__call__)r%inputsr'r!s r)r;"ImageSegmentationPipeline.__call__asBV v ZZ)F >hi iw1&11r+cF[XS9nURUR4/nURRR R S:XaUc0nOSU/0nUR"S U/SS.UD6nURS:XaURUR5nURUSSURRRURS9SUS'ONpanoptic"post_process_panoptic_segmentation>Ninstance"post_process_instance_segmentationrF)r.r/r0 target_sizesr segmentation segments_infoidL)modelabel_idscore)rflabelmask>Nsemantic"post_process_semantic_segmentation)r^zSubtask z is not supported for model )hasattrrLr[r]r fromarraynumpyastypenpuint8rIrJid2labelappendrjuniquer type)r%rVr-r.r/r0fnoutputs annotationr_segmentrhrgrflabelss r) postprocess%ImageSegmentationPipeline.postprocesss% ( (WT5I5IKo-p-p%%HHB * *wt7K7KMq/r/r%%HHB >#-,G*=9   GJ">2L"?3$ 5<tzz|':':288'D3O ))227:3FG(!!E4"PQ 4.!* *wt7K7KMq/r/r**MM-,HNGJ"==?LYY|,F$-4t{{288'<3G ))2259!!D5"OP  xy0LTRVR\R\M]L^_` `r+r2)N)NN)Ng??r|)rK __module__ __qualname____firstlineno____doc__rr5r Predictionsr Predictionr;rRrWrz__static_attributes__ __classcell__)r!s@r)rrsO!F '9"/2{DDT7T1U/2/2b0kn,,r+r) typingrrrrrmroutilsrr r r r baserrPILr image_utilsrmodels.auto.modeling_autorrrr get_loggerrKloggerstrrrrr2r+r)rs))kk4(   H %#s(^ : ,FG}}H}r+