fThtSSKJrJr SSKJrJrJrJrJr SSK J r J r \"5(a SSK J r SSKJr \"5(aSSKJr \R$"\5r\"\ "S S 95"S S \ 55rg ))ListUnion)add_end_docstringsis_torch_availableis_vision_availableloggingrequires_backends)Pipelinebuild_pipeline_init_args)Image) load_image)(MODEL_FOR_DEPTH_ESTIMATION_MAPPING_NAMEST)has_image_processorc~^\rSrSrSrU4SjrS S\\\\S\S44U4Sjjjr S Sjr S Sjr S r S r S rU=r$)DepthEstimationPipelinea` Depth estimation pipeline using any `AutoModelForDepthEstimation`. This pipeline predicts the depth of an image. Example: ```python >>> from transformers import pipeline >>> depth_estimator = pipeline(task="depth-estimation", model="LiheYoung/depth-anything-base-hf") >>> output = depth_estimator("http://images.cocodataset.org/val2017/000000039769.jpg") >>> # This is a tensor with the values being the depth expressed in meters for each pixel >>> output["predicted_depth"].shape torch.Size([1, 384, 384]) ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This depth estimation pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"depth-estimation"`. See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=depth-estimation). ch>[TU]"U0UD6 [US5 UR[5 g)Nvision)super__init__r check_model_typer)selfargskwargs __class__s _/var/www/auris/envauris/lib/python3.13/site-packages/transformers/pipelines/depth_estimation.pyr DepthEstimationPipeline.__init__2s. $)&)$) FGinputsz Image.Imagec p>SU;aURS5nUc [S5e[TU] "U40UD6$)a( Predict the depth(s) of the image(s) passed as inputs. Args: inputs (`str`, `List[str]`, `PIL.Image` or `List[PIL.Image]`): The pipeline handles three types of images: - A string containing a http link pointing to an image - A string containing a local path to an image - An image loaded in PIL directly The pipeline accepts either a single image or a batch of images, which must then be passed as a string. Images in a batch must all be in the same format: all as http links, all as local paths, or all as PIL images. parameters (`Dict`, *optional*): A dictionary of argument names to parameter values, to control pipeline behaviour. The only parameter available right now is `timeout`, which is the length of time, in seconds, that the pipeline should wait before giving up on trying to download an image. timeout (`float`, *optional*, defaults to None): The maximum time in seconds to wait for fetching images from the web. If None, no timeout is set and the call may block forever. Return: A dictionary or a list of dictionaries containing result. If the input is a single image, will return a dictionary, if the input is a list of several images, will return a list of dictionaries corresponding to the images. The dictionaries contain the following keys: - **predicted_depth** (`torch.Tensor`) -- The predicted depth by the model as a `torch.Tensor`. - **depth** (`PIL.Image`) -- The predicted depth by the model as a `PIL.Image`. imageszECannot call the depth-estimation pipeline without an inputs argument!)pop ValueErrorr__call__)rr!rrs rr& DepthEstimationPipeline.__call__7sBD v ZZ)F >de ew1&11r c d0nUbXS'[U[5(aSU;aUSUS'U004$)Ntimeout) isinstancedict)rr) parametersrpreprocess_paramss r_sanitize_parameters,DepthEstimationPipeline._sanitize_parameters_sG  +2i ( j$ ' 'I,C+5i+@ i ( "b((r c[X5nURXRS9nURS:XaURUR5nUR SSS2US'U$)N)r#return_tensorspt target_size)rimage_processor frameworkto torch_dtypesize)rimager) model_inputss r preprocess"DepthEstimationPipeline.preprocessgs`5*++5+X >>T !'??4+;+;OOr r?)N)NN)__name__ __module__ __qualname____firstlineno____doc__rrstrrr&r.r<rBrV__static_attributes__ __classcell__)rs@rrrsR0H &2uS$s)]DDW%WX&2&2P) PPr rN)typingrrutilsrrrr r baser r PILr image_utilsrmodels.auto.modeling_autor get_loggerrXloggerrr?r rrhsq5(T   H %,FGlPhlPHlPr