+ j^RIHtHt^RIHtHt^RIHtHtH t ]!4'd ^RI H t ^RI H t ]!] !RR7R4!R R ]44tR #) )AnyUnion)add_end_docstringsis_vision_available) GenericTensorPipelinebuild_pipeline_init_args)Image) 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. caa]tRt^ toRtRtRtRtRtR Rlt R V3RlRllt Rt RRlt V3R lV3R llt R tVtV;t#)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_length, 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). FTc fVf/MTp/pVeW6R&VeW&R&RV9d VR,VR&V/V3#)Npoolreturn_tensorstimeout)selfimage_processor_kwargsrrkwargspreprocess_paramspostprocess_paramss&&&&, p/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/pipelines/image_feature_extraction.py_sanitize_parameters3ImageFeatureExtractionPipeline._sanitize_parameters5sY"8"@BF\  )-v &  %3A/ 0  +1)+< i ( "&888c6<V^8dQhRS[S[S[3,/#)return)dictstrr)format __classdict__s"r __annotate__+ImageFeatureExtractionPipeline.__annotate__Cs 4PSUbPbKcrc ~\WR7pVP!V3RR/VBpVPVP4pV#))rrpt)r image_processortodtype)rimagerr model_inputss&&&, r preprocess)ImageFeatureExtractionPipeline.preprocessCs?52++Ea$aJ`a #tzz2 rc*VP!R/VBpV#)Nr)model)rr, model_outputss&& r_forward'ImageFeatureExtractionPipeline._forwardIs 2\2 rcVeTMRpV'dRV9d \R4hVR,pM V^,pV'dV#VP4#)NF pooler_outputzeNo pooled output was returned. Make sure the model has a `pooler` layer when using the `pool` option.) ValueErrortolist)rr1rroutputss&&&& r postprocess*ImageFeatureExtractionPipeline.postprocessMsV'tU m3 {$O4G$A&G N~~rcv<V^8dQhRS[S[RS[R,S[S[,3,RS[RS[S[,/#)rargsz Image.Imagerr)rr!listr)r"r#s"rr$r%^sB11eC]8KTRUY$VW1cf1kopskt1rc $<\SV`!V/VB#)aG 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__)rr<r __class__s&*,rr@'ImageFeatureExtractionPipeline.__call__^s*w000rr)NNN)N)NF)__name__ __module__ __qualname____firstlineno____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrr-r2r9r@__static_attributes____classdictcell__ __classcell__)rAr#s@@rrr sJ0O #O 9  "111rrN)typingrrutilsrrbaserrr PILr image_utilsr rrrrrTsR;CC(6 \1X\1 \1r