o  h5&@sddlmZmZddlZddlmZmZmZm Z m Z m Z m Z ddl mZmZe r5ddlmZddlmZer>dd lmZe rKddlZdd lmZe eZd d Zd dZGdddeZeedddGdddeZdS))ListUnionN) ExplicitEnumadd_end_docstringsis_tf_availableis_torch_availableis_vision_availableloggingrequires_backends)Pipelinebuild_pipeline_init_args)Image) load_image)/TF_MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMES),MODEL_FOR_IMAGE_CLASSIFICATION_MAPPING_NAMEScCsddt| S)Ng?)npexp)_outputsr/var/www/html/construction_image-detection-poc/venv/lib/python3.10/site-packages/transformers/pipelines/image_classification.pysigmoid/srcCs0tj|ddd}t||}||jdddS)NT)axiskeepdims)rmaxrsum)rmaxes shifted_exprrrsoftmax4sr c@seZdZdZdZdZdS)ClassificationFunctionrr noneN)__name__ __module__ __qualname__SIGMOIDSOFTMAXNONErrrrr!;sr!T)has_image_processoraZ function_to_apply (`str`, *optional*, defaults to `"default"`): The function to apply to the model outputs in order to retrieve the scores. Accepts four different values: - `"default"`: if the model has a single label, will apply the sigmoid function on the output. If the model has several labels, will apply the softmax function on the output. - `"sigmoid"`: Applies the sigmoid function on the output. - `"softmax"`: Applies the softmax function on the output. - `"none"`: Does not apply any function on the output.cs~eZdZUdZejZeed<fddZdddZ dde e e e d e d fffd d Z dd d ZddZdddZZS)ImageClassificationPipelinea Image classification pipeline using any `AutoModelForImageClassification`. This pipeline predicts the class of an image. Example: ```python >>> from transformers import pipeline >>> classifier = pipeline(model="microsoft/beit-base-patch16-224-pt22k-ft22k") >>> classifier("https://huggingface.co/datasets/Narsil/image_dummy/raw/main/parrots.png") [{'score': 0.442, 'label': 'macaw'}, {'score': 0.088, 'label': 'popinjay'}, {'score': 0.075, 'label': 'parrot'}, {'score': 0.073, 'label': 'parodist, lampooner'}, {'score': 0.046, 'label': 'poll, poll_parrot'}] ``` Learn more about the basics of using a pipeline in the [pipeline tutorial](../pipeline_tutorial) This image classification pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"image-classification"`. See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=image-classification). function_to_applycs>tj|i|t|d||jdkrtdStdS)Nvisiontf)super__init__r check_model_type frameworkrr)selfargskwargs __class__rrr/gs  z$ImageClassificationPipeline.__init__NcCsXi}|dur ||d<i}|dur||d<t|trt|}|dur'||d<|i|fS)Ntimeouttop_kr+) isinstancestrr!lower)r2r8r+r7preprocess_paramspostprocess_paramsrrr_sanitize_parametersps   z0ImageClassificationPipeline._sanitize_parametersinputsz Image.Imagec s6d|vr |d}|durtdtj|fi|S)a Assign labels to the image(s) passed as inputs. Args: inputs (`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. function_to_apply (`str`, *optional*, defaults to `"default"`): The function to apply to the model outputs in order to retrieve the scores. Accepts four different values: If this argument is not specified, then it will apply the following functions according to the number of labels: - If the model has a single label, will apply the sigmoid function on the output. - If the model has several labels, will apply the softmax function on the output. Possible values are: - `"sigmoid"`: Applies the sigmoid function on the output. - `"softmax"`: Applies the softmax function on the output. - `"none"`: Does not apply any function on the output. top_k (`int`, *optional*, defaults to 5): The number of top labels that will be returned by the pipeline. If the provided number is higher than the number of labels available in the model configuration, it will default to the number of labels. timeout (`float`, *optional*, defaults to None): The maximum time in seconds to wait for fetching images from the web. If None, no timeout is set and the call may block forever. Return: A dictionary or a list of dictionaries containing result. If the input is a single image, will return a dictionary, if the input is a list of several images, will return a list of dictionaries corresponding to the images. The dictionaries contain the following keys: - **label** (`str`) -- The label identified by the model. - **score** (`int`) -- The score attributed by the model for that label. imagesNzICannot call the image-classification pipeline without an inputs argument!)pop ValueErrorr.__call__)r2r?r4r5rrrC}s 0 z$ImageClassificationPipeline.__call__cCs6t||d}|j||jd}|jdkr||j}|S)N)r7)r@return_tensorspt)rimage_processorr1to torch_dtype)r2imager7 model_inputsrrr preprocesss   z&ImageClassificationPipeline.preprocesscCs|jdi|}|S)Nr)model)r2rJ model_outputsrrr_forwardsz$ImageClassificationPipeline._forwardcsX|dur<jjjdksjjjdkrtj}n&jjjdks$jjjdkr(tj}ntjjdr9|dur9jjj}ntj }|jjjkrHjjj}|dd}j dkre|j t j t jfvre|t j}n|}|tjkrst|}n|tjkr}t|}n|tj kr|}ntd|fd d t|D}|jd d d d|dur|d|}|S)Nmulti_label_classificationr single_label_classificationr+logitsrrEz+Unrecognized `function_to_apply` argument: cs(g|]\}}jjj||dqS))labelscore)rLconfigid2labelitem).0irTr2rr sz;ImageClassificationPipeline.postprocess..cSs|dS)NrTr)xrrrsz9ImageClassificationPipeline.postprocess..T)keyreverse)rLrU problem_type num_labelsr!r&r'hasattrr+r(r1dtypetorchbfloat16float16rGfloat32numpyrr rB enumeratesort)r2rMr+r8outputsscores dict_scoresrrZr postprocesss8          z'ImageClassificationPipeline.postprocess)NNN)N)NrO)r#r$r%__doc__r!r(r+__annotations__r/r>rr:rrCrKrNrn __classcell__rrr5rr*As    ( 6r*) typingrrrhrutilsrrrrr r r baser rPILr image_utilsrmodels.auto.modeling_tf_autorrdmodels.auto.modeling_autor get_loggerr#loggerrr r!r*rrrrs* $