a hb@svddlmZmZddlmZmZddlmZmZm Z erRddl m Z ddl m Z ee dd d Gd d d eZd S))AnyUnion)add_end_docstringsis_vision_available) GenericTensorPipelinebuild_pipeline_init_args)Image) load_imageT)Zhas_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. cseZdZdZdZdZdZdZdddZde e e fddd Z d d Z dd d Zee dedee feeedfdd ZZS)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). FTNcKsR|dur in|}i}|dur$||d<|dur4||d<d|vrH|d|d<|i|fS)Npoolreturn_tensorstimeout)selfimage_processor_kwargsrrkwargsZpreprocess_paramsZpostprocess_paramsrrk/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/pipelines/image_feature_extraction.py_sanitize_parameters5s z3ImageFeatureExtractionPipeline._sanitize_parameters)returncKs>t||d}|j|fd|ji|}|jdkr:||j}|S)N)rrpt)r Zimage_processor frameworktoZdtype)rimagerr model_inputsrrr preprocessCs    z)ImageFeatureExtractionPipeline.preprocesscCs|jfi|}|S)N)model)rr model_outputsrrr_forwardJsz'ImageFeatureExtractionPipeline._forwardcCsj|dur |nd}|r.d|vr$td|d}n|d}|r>|S|jdkrP|S|jdkrf|SdS)NFZ pooler_outputzeNo pooled output was returned. Make sure the model has a `pooler` layer when using the `pool` option.rrtf) ValueErrorrtolistnumpy)rrrroutputsrrr postprocessNs   z*ImageFeatureExtractionPipeline.postprocessz Image.Image)argsrrcstj|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__)rr'r __class__rrr)bsz'ImageFeatureExtractionPipeline.__call__)NNN)N)NF)__name__ __module__ __qualname____doc__Z_load_processorZ_load_image_processorZ_load_feature_extractorZ_load_tokenizerrdictstrrrr r&rlistrr) __classcell__rrr*rr s   r N)typingrrutilsrrbaserr r ZPILr Z image_utilsr r rrrrs