a h%@sdZddlZddlmZddlmZddlmZddlm Z ddl m Z m Z m Z dd lmZmZGd d d e d d ZGddde ZdgZdS)z Processor class for TrOCR. N)contextmanager)Union) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInputc@seZdZiZdS)TrOCRProcessorKwargsN)__name__ __module__ __qualname__ _defaultsrrf/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/trocr/processing_trocr.pyr sr F)totalcseZdZdZddgZdZdZdfdd Zdee e e e e e e fe eed d d Zed d ZeddZeddZeddZZS)TrOCRProcessora Constructs a TrOCR processor which wraps a vision image processor and a TrOCR tokenizer into a single processor. [`TrOCRProcessor`] offers all the functionalities of [`ViTImageProcessor`/`DeiTImageProcessor`] and [`RobertaTokenizer`/`XLMRobertaTokenizer`]. See the [`~TrOCRProcessor.__call__`] and [`~TrOCRProcessor.decode`] for more information. Args: image_processor ([`ViTImageProcessor`/`DeiTImageProcessor`], *optional*): An instance of [`ViTImageProcessor`/`DeiTImageProcessor`]. The image processor is a required input. tokenizer ([`RobertaTokenizer`/`XLMRobertaTokenizer`], *optional*): An instance of [`RobertaTokenizer`/`XLMRobertaTokenizer`]. The tokenizer is a required input. image_processor tokenizerZAutoImageProcessorZ AutoTokenizerNc srd}d|vr"tdt|d}|dur.|n|}|durBtd|durRtdt|||j|_d|_ dS)Nfeature_extractorzhThe `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor` instead.z)You need to specify an `image_processor`.z"You need to specify a `tokenizer`.F) warningswarn FutureWarningpop ValueErrorsuper__init__rcurrent_processor_in_target_context_manager)selfrrkwargsr __class__rrr4s zTrOCRProcessor.__init__)imagestextr"returnc Ks|jr|j|fi|S|dur0|dur0td|jtfd|jji|}|durh|j|fi|d}|dur|j|fi|d}|dur|S|dur|S|d|d<|SdS)a When used in normal mode, this method forwards all its arguments to AutoImageProcessor's [`~AutoImageProcessor.__call__`] and returns its output. If used in the context [`~TrOCRProcessor.as_target_processor`] this method forwards all its arguments to TrOCRTokenizer's [`~TrOCRTokenizer.__call__`]. Please refer to the docstring of the above two methods for more information. NzBYou need to specify either an `images` or `text` input to process.Ztokenizer_init_kwargsZ images_kwargsZ text_kwargsZ input_idslabels)r rrZ _merge_kwargsr rZ init_kwargsr) r!r%r&ZaudioZvideosr"Z output_kwargsinputs encodingsrrr__call__Hs* zTrOCRProcessor.__call__cCs|jj}|dgS)Nr()rmodel_input_names)r!Zimage_processor_input_namesrrrr,psz TrOCRProcessor.model_input_namesccs0tdd|_|j|_dV|j|_d|_dS)z Temporarily sets the tokenizer for processing the input. Useful for encoding the labels when fine-tuning TrOCR. z`as_target_processor` is deprecated and will be removed in v5 of Transformers. You can process your labels by using the argument `text` of the regular `__call__` method (either in the same call as your images inputs, or in a separate call.TNF)rrr rrrr!rrras_target_processorusz"TrOCRProcessor.as_target_processorcCstdt|jS)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)rrrimage_processor_classr-rrrfeature_extractor_classs z&TrOCRProcessor.feature_extractor_classcCstdt|jS)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)rrrrr-rrrrs z TrOCRProcessor.feature_extractor)NN)NNNN)r rr__doc__ attributesr/Ztokenizer_classrrrr r listr r rr+propertyr,rr.r0r __classcell__rrr#rr!s. (   r)r1r contextlibrtypingrZimage_processing_utilsrZ image_utilsrZprocessing_utilsrrr Ztokenization_utils_baser r r r__all__rrrrs    u