sg|ddlmZddlmZmZddlmZmZmZerddl m Z eedd Gd d eZ y ) )Dict)add_end_docstringsis_vision_available) GenericTensorPipelinebuild_pipeline_init_args) load_imageT)has_image_processora image_processor_kwargs (`dict`, *optional*): Additional dictionary of keyword arguments passed along to the image processor e.g. {"size": {"height": 100, "width": 100}} pool (`bool`, *optional*, defaults to `False`): Whether or not to return the pooled output. If `False`, the model will return the raw hidden states. cPeZdZdZddZd deeeffdZdZ d dZ fdZ xZ S) ImageFeatureExtractionPipelinea+ Image feature extraction pipeline uses no model head. This pipeline extracts the hidden states from the base transformer, which can be used as features in downstream tasks. Example: ```python >>> from transformers import pipeline >>> extractor = pipeline(model="google/vit-base-patch16-224", task="image-feature-extraction") >>> result = extractor("https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png", return_tensors=True) >>> result.shape # This is a tensor of shape [1, sequence_lenth, hidden_dimension] representing the input image. torch.Size([1, 197, 768]) ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This image feature extraction pipeline can currently be loaded from [`pipeline`] using the task identifier: `"image-feature-extraction"`. All vision models may be used for this pipeline. See a list of all models, including community-contributed models on [huggingface.co/models](https://huggingface.co/models). c P|in|}i}|||d<|||d<d|vr|d|d<|i|fS)Npoolreturn_tensorstimeout)selfimage_processor_kwargsrrkwargspreprocess_paramspostprocess_paramss b/var/www/html/venv/lib/python3.12/site-packages/transformers/pipelines/image_feature_extraction.py_sanitize_parametersz3ImageFeatureExtractionPipeline._sanitize_parameters.s_"8"@BF\  )- v &  %3A / 0  +1)+< i ( "&888returnc t||}|j|fd|ji|}|jdk(r|j|j}|S)N)rrpt)r image_processor frameworkto torch_dtype)rimagerr model_inputss r preprocessz)ImageFeatureExtractionPipeline.preprocess<sU5'2+t++Ek$..kTjk >>T !'??4+;+;>T !>># # ^^t #==?))+ +$rc"t||i|S)a Extract the features of the input(s). 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 used and the call may block forever. Return: A nested list of `float`: The features computed by the model. )super__call__)rargsr __class__s rr4z'ImageFeatureExtractionPipeline.__call__[s*w000r)NNN)N)NF) __name__ __module__ __qualname____doc__rrstrrr%r)r1r4 __classcell__)r6s@rrr s90 94PSUbPbKc,(11rrN) typingrutilsrrbaserr r image_utilsr rrrrrAsL;CC(6 [1X[1 [1r