U 5Af|@sfddlmZddlmZmZddlmZmZmZerBddl m Z eeddd Gd d d eZ d S) )Dict)add_end_docstringsis_vision_available) GenericTensorPipelinebuild_pipeline_init_args) 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. csTeZdZdZdddZdeeefdddZdd Z dd d Z fd dZ Z 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). NcKsR|dkr in|}i}|dk r$||d<|dk r4||d<d|krH|d|d<|i|fS)Npoolreturn_tensorstimeout)selfimage_processor_kwargsr r kwargsZpreprocess_paramsZpostprocess_paramsrrS/tmp/pip-unpacked-wheel-zw5xktn0/transformers/pipelines/image_feature_extraction.py_sanitize_parameters.s z3ImageFeatureExtractionPipeline._sanitize_parameters)returncKs>t||d}|j|fd|ji|}|jdkr:||j}|S)N)rr pt)r Zimage_processor frameworktoZ torch_dtype)rimagerr model_inputsrrr preprocess<s    z)ImageFeatureExtractionPipeline.preprocesscCs|jf|}|S)N)model)rr model_outputsrrr_forwardCs z'ImageFeatureExtractionPipeline._forwardFcCsj|dk r |nd}|r.d|kr$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) ValueErrorrtolistZnumpy)rrr r outputsrrr postprocessGs   z*ImageFeatureExtractionPipeline.postprocesscstj||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__rrr%[sz'ImageFeatureExtractionPipeline.__call__)NNN)N)NF) __name__ __module__ __qualname____doc__rrstrrrrr#r% __classcell__rrr'rr s    r N) typingrutilsrrbaserrr Z image_utilsr r rrrrs