U 9%e@sddlmZddlmZmZddlZddlmZmZm Z m Z m Z ddl m Z mZerjddlZddlmZe r|dd lmZe eZee Gd d d eZdS) )BytesIO)ListUnionN)add_end_docstringsis_decord_availableis_torch_availableloggingrequires_backends)PIPELINE_INIT_ARGSPipeline) VideoReader),MODEL_FOR_VIDEO_CLASSIFICATION_MAPPING_NAMEScsdeZdZdZfddZdddZeeeefdfdd Z dd d Z d dZ dddZ Z S)VideoClassificationPipelinea Video classification pipeline using any `AutoModelForVideoClassification`. This pipeline predicts the class of a video. This video classification pipeline can currently be loaded from [`pipeline`] using the following task identifier: `"video-classification"`. See the list of available models on [huggingface.co/models](https://huggingface.co/models?filter=video-classification). cs&tj||t|d|tdS)Ndecord)super__init__r Zcheck_model_typer)selfargskwargs __class__j/var/www/html/Darija-Ai-API/env/lib/python3.8/site-packages/transformers/pipelines/video_classification.pyr"s z$VideoClassificationPipeline.__init__NcCsBi}|dk r||d<|dk r$||d<i}|dk r8||d<|i|fS)Nframe_sampling_rate num_framestop_kr)rrrrZpreprocess_paramsZpostprocess_paramsrrr_sanitize_parameters'sz0VideoClassificationPipeline._sanitize_parameters)videosc stj|f|S)a$ Assign labels to the video(s) passed as inputs. Args: videos (`str`, `List[str]`): The pipeline handles three types of videos: - A string containing a http link pointing to a video - A string containing a local path to a video The pipeline accepts either a single video or a batch of videos, which must then be passed as a string. Videos in a batch must all be in the same format: all as http links or all as local paths. 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. num_frames (`int`, *optional*, defaults to `self.model.config.num_frames`): The number of frames sampled from the video to run the classification on. If not provided, will default to the number of frames specified in the model configuration. frame_sampling_rate (`int`, *optional*, defaults to 1): The sampling rate used to select frames from the video. If not provided, will default to 1, i.e. every frame will be used. Return: A dictionary or a list of dictionaries containing result. If the input is a single video, will return a dictionary, if the input is a list of several videos, will return a list of dictionaries corresponding to the videos. 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. )r__call__)rrrrrrr 3s!z$VideoClassificationPipeline.__call__r c Cs|dkr|jjj}|ds&|dr6tt|j}t|}| dd}||d}t j |||t j d}| |}t|}|j||jd}|S)Nzhttp://zhttps://rr )numZdtype)Zreturn_tensors)modelconfigr startswithrrequestsgetcontentrseeknpZlinspaceZint64Z get_batchZasnumpylistZimage_processor framework) rZvideorrZ videoreaderZ start_idxZend_idxindices model_inputsrrr preprocessVs   z&VideoClassificationPipeline.preprocesscCs|jf|}|S)N)r")rr- model_outputsrrr_forwardjs z$VideoClassificationPipeline._forwardcsz|jjjkrjjj}jdkrB|jdd}||\}}ntdj|}|}fddt ||DS)NptrzUnsupported framework: cs$g|]\}}|jjj|dqS))scorelabel)r"r#Zid2label).0r4Z_idrrr zsz;VideoClassificationPipeline.postprocess..) r"r#Z num_labelsr+ZlogitsZsoftmaxZtopk ValueErrortolistzip)rr/rZprobsZscoresZidsrr7r postprocessns  z'VideoClassificationPipeline.postprocess)NNN)Nr )r1)__name__ __module__ __qualname____doc__rrrstrrr r.r0r< __classcell__rrrrrs  # r)iortypingrrr%utilsrrrr r baser r numpyr)rrZmodels.auto.modeling_autorZ get_loggerr=loggerrrrrrs