U 5Af@sddlmZmZddlZddlmZmZmZm Z m Z ddl m Z m Z erbddlmZddlmZer|ddlZdd lmZe eZee d d Gd d d e ZdS))ListUnionN)add_end_docstringsis_torch_availableis_vision_availableloggingrequires_backends)Pipelinebuild_pipeline_init_args)Image) load_image)(MODEL_FOR_DEPTH_ESTIMATION_MAPPING_NAMEST)Zhas_image_processorcsjeZdZdZfddZeeeededfdfdd Zdd d Z dd d Z d dZ ddZ Z S)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). cs&tj||t|d|tdS)NZvision)super__init__r Zcheck_model_typer)selfargskwargs __class__K/tmp/pip-unpacked-wheel-zw5xktn0/transformers/pipelines/depth_estimation.pyr0s z DepthEstimationPipeline.__init__z Image.Image)imagesc stj|f|S)a Predict the depth(s) of the image(s) passed as inputs. Args: images (`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. 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`. )r__call__)rrrrrrr5sz DepthEstimationPipeline.__call__NcKsi}|dk r||d<|iifS)Ntimeoutr)rrrZpreprocess_paramsrrr_sanitize_parametersTsz,DepthEstimationPipeline._sanitize_parameterscCs<t||}|j|_|j||jd}|jdkr8||j}|S)N)rZreturn_tensorspt)rsize image_sizeZimage_processorZ frameworktoZ torch_dtype)rimager model_inputsrrr preprocessZs    z"DepthEstimationPipeline.preprocesscCs|jf|}|S)N)model)rr# model_outputsrrr_forwardbs z DepthEstimationPipeline._forwardcCsx|j}tjjj|d|jdddddd}| }|dt | d}t |}i}||d<||d <|S) Nr ZbicubicF)rmodeZ align_cornersZuint8predicted_depthdepth)r+torchnnZ functionalZ interpolateZ unsqueezer ZsqueezecpunumpynpmaxZastyper Z fromarray)rr&r+Z predictionoutput formattedr,Z output_dictrrr postprocessfs z#DepthEstimationPipeline.postprocess)N)N)__name__ __module__ __qualname____doc__rrstrrrrr$r'r5 __classcell__rrrrrs &  r)typingrrr0r1utilsrrrrr baser r ZPILr Z image_utilsrr-Zmodels.auto.modeling_autorZ get_loggerr6loggerrrrrrs