o i&@sddlmZmZmZddlZddlmZmZm Z m Z m Z ddl m Z mZe r3ddlmZddlmZerBdd lmZmZmZmZe eZeed d Gd d 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 seZdZdZdZdZdZdZfddZddZ e d e e d fd e d eee e ffd dZe d ee ed Bd e d eeee e ffddZd e e d ee ed fd e d eee e feeee e fBffdd ZdddZddZ dddZZS)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). FTNcsPtj|i|t|dt}|t|t|t| |dS)Nvision) super__init__r rcopyupdaterrrcheck_model_type)selfargskwargsmapping __class__k/sda-disk/www/egybert/egybert_env/lib/python3.10/site-packages/transformers/pipelines/image_segmentation.pyrDs    z"ImageSegmentationPipeline.__init__cKsi}i}d|vr|d|d<|d|d<d|vr|d|d<d|vr(|d|d<d|vr2|d|d<d|vr<|d|d<|i|fS)Nsubtask thresholdmask_thresholdoverlap_mask_area_thresholdtimeoutr")rrpreprocess_kwargspostprocess_kwargsr"r"r#_sanitize_parametersNs       z.ImageSegmentationPipeline._sanitize_parametersinputsz Image.ImagerreturncKdSNr"rr,rr"r"r#__call___z"ImageSegmentationPipeline.__call__cKr.r/r"r0r"r"r#r1br2c s6d|vr |d}|durtdtj|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 ValueErrorrr1r0r r"r#r1es , cCst||d}|j|jfg}|jjjjdkrF|duri}nd|gi}|jd |gdd|}||j }|j |dd|jjj ddd|d<n|j|gdd}||j }||d <|S) N)r(OneFormerConfig task_inputspt)r3return_tensors max_length)paddingr:r9 input_ids target_sizer") rheightwidthmodelconfigr!__name__image_processortodtype tokenizer task_seq_len)rimager$r(r=rr,r"r"r# preprocesss(     z$ImageSegmentationPipeline.preprocesscCs&|d}|jdi|}||d<|S)Nr=r")r4r@)r model_inputsr= model_outputsr"r"r#_forwards z"ImageSegmentationPipeline._forward??cCsd}|dvrt|jdr|jj}n|dvrt|jdr|jj}|durj||||||ddd}g}|d} |d D]-} | | d kd } tj| tj d d } |j j j | d} | d} | | | | dq:|S|dvrt|jdr|jj||ddd}g}|} t| }|D]#} | | kd } tj| tj d d } |j j j | } | d| | dq|Std|dt|j )N>Npanoptic"post_process_panoptic_segmentation>Ninstance"post_process_instance_segmentationr=)r%r&r' target_sizesr segmentation segments_infoidL)modelabel_idscore)r[labelmask>Nsemantic"post_process_semantic_segmentation)rSzSubtask z is not supported for model )hasattrrCrPrRr fromarraynumpyastypenpuint8r@rAid2labelappendr_uniquer5type)rrKr$r%r&r'fnoutputs annotationrTsegmentr]r\r[labelsr"r"r# postprocesssP    z%ImageSegmentationPipeline.postprocess)NN)NrMrNrN)rB __module__ __qualname____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrr+rrstrrlistdictr1rIrLro __classcell__r"r"r r#rs.#  ,4" 2r)typingrrrrbrdutilsrrrr r baser r PILr image_utilsrmodels.auto.modeling_autorrrr get_loggerrBloggerrr"r"r"r#s