jSSKJrJrJr SSKJrJrJrJrJ r SSK J r J r \"5(a SSK Jr SSKJr \"5(aSSKJr \R&"\5r\"\ "S S 95"S S \ 55rg ))AnyUnionoverload)add_end_docstringsis_torch_availableis_vision_availableloggingrequires_backends)Pipelinebuild_pipeline_init_args)Image) load_image)(MODEL_FOR_DEPTH_ESTIMATION_MAPPING_NAMEST)has_image_processorc &^\rSrSrSrSrSrSrSrU4Sjr \ S\ \ S4S\ S \\ \ 44S j5r\ S\\ \ S4S\ S \\\ \ 44S j5rS\ \ \\ S\S4S\ S \\ \ 4\\\ \ 4-4U4S jjrSS jrSSjrSrSrSrU=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). FTch>[TU]"U0UD6 [US5 UR[5 g)Nvision)super__init__r check_model_typer)selfargskwargs __class__s ڵC:\Users\johnn\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.13_qbz5n2kfra8p0\LocalCache\local-packages\Python313\site-packages\transformers/pipelines/depth_estimation.pyr DepthEstimationPipeline.__init__7s. $)&)$) FGinputsz Image.Imagerreturnc gNrr"rs r__call__ DepthEstimationPipeline.__call__<s\_r!c gr%r&r's rr(r)?shkr!c p>SU;aURS5nUc [S5e[TU] "U40UD6$)a( Predict the depth(s) of the image(s) passed as inputs. Args: inputs (`str`, `list[str]`, `PIL.Image` or `list[PIL.Image]`): The pipeline handles three types of images: - A string containing a http link pointing to an image - A string containing a local path to an image - An image loaded in PIL directly The pipeline accepts either a single image or a batch of images, which must then be passed as a string. Images in a batch must all be in the same format: all as http links, all as local paths, or all as PIL images. parameters (`Dict`, *optional*): A dictionary of argument names to parameter values, to control pipeline behaviour. The only parameter available right now is `timeout`, which is the length of time, in seconds, that the pipeline should wait before giving up on trying to download an image. timeout (`float`, *optional*, defaults to None): The maximum time in seconds to wait for fetching images from the web. If None, no timeout is set and the call may block forever. Return: A dictionary or a list of dictionaries containing result. If the input is a single image, will return a dictionary, if the input is a list of several images, will return a list of dictionaries corresponding to the images. The dictionaries contain the following keys: - **predicted_depth** (`torch.Tensor`) -- The predicted depth by the model as a `torch.Tensor`. - **depth** (`PIL.Image`) -- The predicted depth by the model as a `PIL.Image`. imageszECannot call the depth-estimation pipeline without an inputs argument!)pop ValueErrorrr()rr"rrs rr(r)BsBH v ZZ)F >de ew1&11r!c d0nUbXS'[U[5(aSU;aUSUS'U004$)Ntimeout) isinstancedict)rr0 parametersrpreprocess_paramss r_sanitize_parameters,DepthEstimationPipeline._sanitize_parameterslsG  +2i ( j$ ' 'I,C+5i+@ i ( "b((r!c[X5nURUSS9nURUR5nURSSS2US'U$)Npt)r,return_tensors target_size)rimage_processortodtypesize)rimager0 model_inputss r preprocess"DepthEstimationPipeline.preprocesstsP5*++5+N #tzz2 &+jj2&6 ]#r!cTURS5nUR"S0UD6nX#S'U$)Nr;r&)r-model)rrAr; model_outputss r_forward DepthEstimationPipeline._forward{s1"&&}5  2\2 '2m$r!cURRUUS/5n/nUHnUSR5R5R 5nXUR 5- UR 5UR 5- - n[R"US-RS55nURUSUS.5 M [U5S:XaUS$U$)Nr;predicted_depthuint8)rJdepthr r) r<post_process_depth_estimationdetachcpunumpyminmaxr fromarrayastypeappendlen)rrFoutputsformatted_outputsoutputrMs r postprocess#DepthEstimationPipeline.postprocesss&&DD = ) *  F,-446::<BBDEYY[(UYY[599;-FGEOOUS[$8$8$ABE  $ $@Q9R]b%c d (+7|q'8 #O>OOr!r&)NNr%)__name__ __module__ __qualname____firstlineno____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrrrstrrr2r(listr5rBrGr[__static_attributes__ __classcell__)rs@rrrs0O #OH _uS-%78_C_DQTVYQYN__ ktE#}*<$=>k#kRVW[\_ad\dWeRfkk(2CcM4 ;NNO(2[^(2 c3h$tCH~. .(2T) PPr!rN)typingrrrutilsrrr r r baser rPILr image_utilsrmodels.auto.modeling_autor get_loggerr]loggerrr&r!rrrst''5(T   H %,FGxPhxPHxPr!