`icddlmZmZddlmZmZddlmZmZm Z er ddl m Z ddl m Z ee d d Gd d eZd S))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. ceZdZdZdZdZdZdZddZdde e e ffdZ dZ dd Zd ee d ed ee fd edeeffd ZxZS)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). FTNc V|in|}i}|||d<|||d<d|vr |d|d<|i|fS)Npoolreturn_tensorstimeout)selfimage_processor_kwargsrrkwargspreprocess_paramspostprocess_paramss /home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/pipelines/image_feature_extraction.py_sanitize_parametersz3ImageFeatureExtractionPipeline._sanitize_parameters5sd"8"@BBF\  )- v &  %3A / 0   +1)+< i ( "&888returnc t||}|j|fd|ji|}|jdkr||j}|S)N)rrpt)r image_processor frameworktodtype)rimagerr model_inputss r preprocessz)ImageFeatureExtractionPipeline.preprocessCs\5'222+t+Ekk$.kTjkk >T ! !'??4:66Lrc |jdi|}|S)Nr)model)rr& model_outputss r_forwardz'ImageFeatureExtractionPipeline._forwardJs" 22\22 rc||nd}|rd|vrtd|d}n|d}|r|S|jdkr|S|jdkr&|SdS)NF pooler_outputzeNo pooled output was returned. Make sure the model has a `pooler` layer when using the `pool` option.rr tf) ValueErrorr"tolistnumpy)rr*rroutputss r postprocessz*ImageFeatureExtractionPipeline.postprocessNs'ttU  'm33 {$O4GG$A&G  N >T ! !>>## # ^t # #==??))++ +$ #rargsz Image.Imagerc6tj|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__)rr4r __class__s rr7z'ImageFeatureExtractionPipeline.__call__bs!* uww0000r)NNN)N)NF)__name__ __module__ __qualname____doc___load_processor_load_image_processor_load_feature_extractor_load_tokenizerrdictstrr r'r+r3rlistrr7 __classcell__)r8s@rrr s0O #O 9 9 9 94PSUbPbKc,,,,(1eC]8KTRUY$VW1cf1kopskt1111111111rrN)typingrrutilsrrbaser r r PILr image_utilsr rrrrrJs;;;;;;;;CCCCCCCCCC)((((((666  `1`1`1`1`1X`1`1  `1`1`1r