Zj&SSKJrJrJr SSKrSSKJrJrJ r J r J r SSK J r Jr \ "5(a SSKJr SSKJr \"5(a SS KJrJrJrJr \ R0"\5r\"\"S S 95"S S \ 55rg))AnyUnionoverloadN)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_processorc B^\rSrSrSrSrSrSrSrU4Sjr Sr \ S\ \ S 4S \S \\\ \44S j5r\ S\\ \S -S \S \\\\ \44S j5rS\ \ S \\ \S 4S \S \\\ \4\\\\ \4-4U4SjjrSSjrSrSSjrSrU=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). FTNc>[TU]"U0UD6 [US5 [R"5nUR [ 5 UR [5 UR [5 URU5 g)Nvision) super__init__r rcopyupdaterrrcheck_model_type)selfargskwargsmapping __class__s z/root/GenerationalWealth/GenerationalWealth/venv/lib/python3.13/site-packages/transformers/pipelines/image_segmentation.pyr"ImageSegmentationPipeline.__init__Dsb $)&)$)<AACDEDEEF g&c 0n0nSU;aUSUS'USUS'SU;aUSUS'SU;aUSUS'SU;aUSUS'SU;aUSUS'U0U4$)Nsubtask thresholdmask_thresholdoverlap_mask_area_thresholdtimeout)r r"preprocess_kwargspostprocess_kwargss r%_sanitize_parameters.ImageSegmentationPipeline._sanitize_parametersNs  ,29,= y )+1)+< i ( & .4[.A { + v %39:J3K / 0 (F 2@FGd@e < =  +1)+< i ( "&888r'inputsz Image.Imager"returnc gNr.r r3r"s r%__call__"ImageSegmentationPipeline.__call___sber'c gr6r.r7s r%r8r9bsnqr'c p>SU;aURS5nUc [S5e[TU] "U40UD6$)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: 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!)pop ValueErrorrr8)r r3r"r$s r%r8r9esBX v ZZ)F >hi iw1&11r'c[XS9nURUR4/nURRR R S:XavUc0nOSU/0nUR"S U/SS.UD6nURUR5nURUSSURRRSS9SUS'O,URU/SS9nURUR5nXFS 'U$) N)r-OneFormerConfig task_inputspt)r<return_tensors max_length)paddingrDrC input_ids target_sizer.) rheightwidthmodelconfigr$__name__image_processortodtype tokenizer task_seq_len)r imager)r-rGr"r3s r% preprocess$ImageSegmentationPipeline.preprocesss52 ekk23 ::   & & / /3D D''3))X%XQWXFYYtzz*F$(NN}%$::,,99# %3%  %F= !))%)NFYYtzz*F +} r'cTURS5nUR"S0UD6nX#S'U$)NrGr.)r=rJ)r model_inputsrG model_outputss r%_forward"ImageSegmentationPipeline._forwards1"&&}5  2\2 '2m$r'cTSnUS;a2[URS5(aURRnO7US;a1[URS5(aURRnUbU"UUUUUSS9Sn/nUSn US Hn XS :HS -n [R "U R 5R[R5S S 9n URRRU Sn U Sn URXU S.5 M U$US;a[URS5(aURRXSS9Sn/nUR 5n [R"U 5nUHsn X:HS -n [R "U R[R5S S 9n URRRU n URSXS.5 Mu U$[!SUS[#UR535e)N>Npanoptic"post_process_panoptic_segmentation>Ninstance"post_process_instance_segmentationrG)r*r+r, target_sizesr segmentation segments_infoidL)modelabel_idscore)rglabelmask>Nsemantic"post_process_semantic_segmentation)r_zSubtask z is not supported for model )hasattrrMr\r^r fromarraynumpyastypenpuint8rJrKid2labelappendrkuniquer>type)r rWr)r*r+r,fnoutputs annotationr`segmentrirhrglabelss 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$-4t{{288'<3G ))2259!!D5"OP  xy0LTRVR\R\M]L^_` `r'r.)NN)Ng??r})rL __module__ __qualname____firstlineno____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrr1rrstrrlistdictr8rSrXr{__static_attributes__ __classcell__)r$s@r%rrs!FO #O'9"euS-%78eCeDQUVY[^V^Q_L`ee qtCy4 +>>q#qRVW[\`adfiai\jWkRlqq02CS 4 ;NNO02[^02 d38n T$sCx.%9 : :02d,kn,,r'r)typingrrrrnrputilsrrr r r baser rPILr image_utilsrmodels.auto.modeling_autorrrr get_loggerrLloggerrr.r'r%rsw''kk4(   H %,FGDDHDr'