bi&ddlmZmZmZddlZddlmZmZm Z m Z m Z ddl m Z mZe r ddlmZddlmZer dd lmZmZmZmZe jeZeed Gd d e ZdS))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 eZdZdZdZdZdZdZfdZdZ e de e dfd e d eee e ffd Ze dee edzd e d eeee e ffd Zde e dee edfd e d eee e feeee e fzffd ZddZdZ ddZxZS)ImageSegmentationPipelinea 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). FTNcFtj|i|t|dtj}|t |t|t| |dS)Nvision) super__init__r rcopyupdaterrrcheck_model_type)selfargskwargsmapping __class__s d/root/projects/butler/venv/lib/python3.11/site-packages/transformers/pipelines/image_segmentation.pyrz"ImageSegmentationPipeline.__init__Ds$)&)))$)))<ACCDEEEDEEEEFFF g&&&&&c i}i}d|vr|d|d<|d|d<d|vr |d|d<d|vr |d|d<d|vr |d|d<d|vr |d|d<|i|fS)Nsubtask thresholdmask_thresholdoverlap_mask_area_thresholdtimeout)rr!preprocess_kwargspostprocess_kwargss r$_sanitize_parametersz.ImageSegmentationPipeline._sanitize_parametersNs   ,29,= y )+1)+< i ( & .4[.A { + v % %39:J3K / 0 (F 2 2@FGd@e < =   +1)+< i ( "&888r%inputsz Image.Imager!returnc dSNr,rr0r!s r$__call__z"ImageSegmentationPipeline.__call___sbeber%c dSr3r,r4s r$r5z"ImageSegmentationPipeline.__call__bsnqnqr%c d|vr|d}|tdtj|fi|S)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. imagesNzICannot call the image-classification pipeline without an inputs argument!)pop ValueErrorrr5)rr0r!r#s r$r5z"ImageSegmentationPipeline.__call__esUX v  ZZ))F >hii iuww11&111r%ct||}|j|jfg}|jjjjdkrm|i}nd|gi}|jd |gdd|}||j }| |dd|jjj dd|d<n2||gd}||j }||d <|S) N)r+OneFormerConfig task_inputspt)r8return_tensors max_length)paddingr@r? input_ids target_sizer,) rheightwidthmodelconfigr#__name__image_processortodtype tokenizer task_seq_len)rimager'r+rCr!r0s r$ preprocessz$ImageSegmentationPipeline.preprocesss 5'222 ek23 :  & /3D D D''3)T)X%XXQWXXFYYtz**F$(NN}%$:,9# %3%%  %F= ! !))%)NNFYYtz**F +} r%cT|d}|jdi|}||d<|S)NrCr,)r9rF)r model_inputsrC model_outputss r$_forwardz"ImageSegmentationPipeline._forwards<"&&}55 " 22\22 '2 m$r%??c6d}|dvr"t|jdr |jj}n%|dvr!t|jdr |jj}|||||||dd}g}|d} |d D]} | | d kd z} t j| tj d } |j j j | d} | d} | | | | dn|dvrt|jdr|j||dd}g}|} tj| }|D]n} | | kd z} t j| tj d } |j j j | } | d| | don't!d|dt#|j |S)N>Npanoptic"post_process_panoptic_segmentation>Ninstance"post_process_instance_segmentationrC)r(r)r* target_sizesr segmentation segments_infoidL)modelabel_idscore)rclabelmask>Nsemantic"post_process_semantic_segmentation)r[zSubtask z is not supported for model )hasattrrIrXrZr fromarraynumpyastypenpuint8rFrGid2labelappendrguniquer:type)rrRr'r(r)r*fnoutputs annotationr\segmentrerdrclabelss r$ postprocessz%ImageSegmentationPipeline.postprocesssh ( ( (WT5IKo-p-p (%HBB * * *wt7KMq/r/r *%HB >b#-,G*=9   GJ">2L"?3 R R$ 5<tzz||':':28'D'D3OOO )27:3FG(!!EE4"P"PQQQQ  R* * *wt7KMq/r/r **MMM-,HNGJ"==??LY|,,F Q Q$-4t{{28'<'<3GGG )259!!D5$"O"OPPPP  Q ___TRVR\M]M]__`` `r%)NN)NrTrUrU)rH __module__ __qualname____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrr/rrstrrlistdictr5rOrSrw __classcell__)r#s@r$rrs!!FO #O'''''999"euS-%78eCeDQUVY[^V^Q_L`eeeXe qtCy4 +>>q#qRVW[\`adfiai\jWkRlqqqXq02CS 4 ;NNO02[^02 d38n T$sCx.%9 : :020202020202d,kn,,,,,,,,r%r)typingrrrrjrlutilsrrr r r baser rPILr image_utilsrmodels.auto.modeling_autorrrr get_loggerrHloggerrr,r%r$rso''''''''''kkkkkkkkkkkkkk44444444)((((((  H % %,,FFFGGDDDDDDDHGDDDr%