o Zh @sddlmZmZmZmZddlmZddlmZddl m Z m Z m Z ddl mZmZddlmZdd lmZGd d d e d d ZGddde ZdgZdS))DictListOptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput) TensorType) AutoTokenizerc@s$eZdZddidddejdZdS)AriaProcessorKwargspaddingF)Zmax_image_sizeZ split_image) text_kwargs images_kwargsreturn_tensorsN)__name__ __module__ __qualname__rZPYTORCH _defaultsrrW/var/www/auris/lib/python3.10/site-packages/transformers/models/aria/processing_aria.pyrs rF)totalc seZdZdZddgZddgZdZdZ    ddee e fde e de e ee efefffd d Z   dd eeeeeeefd e ed eedefddZddZddZeddZZS) AriaProcessora AriaProcessor is a processor for the Aria model which wraps the Aria image preprocessor and the LLama slow tokenizer. Args: image_processor (`AriaImageProcessor`, *optional*): The AriaImageProcessor to use for image preprocessing. tokenizer (`PreTrainedTokenizerBase`, *optional*): An instance of [`PreTrainedTokenizerBase`]. This should correspond with the model's text model. The tokenizer is a required input. chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. size_conversion (`Dict`, *optional*): A dictionary indicating size conversions for images. image_processor tokenizer chat_templatesize_conversionZAriaImageProcessorrNcsf|dur ddd}dd|D|_|j|_|j|_|dur(|jdur(|j|_tj|||ddS)N)ircSsi|] \}}t||qSr)int).0kvrrr Isz*AriaProcessor.__init__..)r!)itemsr" image_tokenZimage_token_idZ pad_tokenZ unk_tokensuper__init__)selfrr r!r" __class__rrr-@s zAriaProcessor.__init__textimageskwargsreturncKs|jtfd|jji|}t|tr|g}nt|ts&t|dts&td|dur^|j|fi|d}|j |j j d}g} | d|} |D]} | |jj|jj| } | | qIni}|} |d d d} |j| fi|d} |j| | d gd ti| || d S) a Main method to prepare for the model one or several sequences(s) and image(s). Args: text (`TextInput`, `PreTokenizedInput`, `List[TextInput]`, `List[PreTokenizedInput]`): The sequence or batch of sequences to be encoded. Each sequence can be a string or a list of strings (pretokenized string). If the sequences are provided as list of strings (pretokenized), you must set `is_split_into_words=True` (to lift the ambiguity with a batch of sequences). images (`ImageInput`): The image or batch of images to be prepared. Each image can be a PIL image, NumPy array or PyTorch tensor. Both channels-first and channels-last formats are supported. Returns: [`BatchFeature`]: A [`BatchFeature`] with the following fields: - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`. - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not `None`). - **pixel_values** -- Pixel values to be fed to a model. Returned when `images` is not `None`. - **pixel_mask** -- Pixel mask to be fed to a model. Returned when `images` is not `None`. Ztokenizer_init_kwargsrzAInvalid input text. Please provide a string, or a list of stringsNrr num_cropsrrimage)Z modalities)dataZ tensor_type)Z _merge_kwargsrr Z init_kwargs isinstancestrlist ValueErrorrr"Z pixel_valuesshapepopreplacer+appendZ_check_special_mm_tokensr)r.r1r2ZaudioZvideosr3Z output_kwargsZ image_inputsZtokens_per_imageZprompt_stringsr5samplerZ text_inputsrrr__call__Rs<  zAriaProcessor.__call__cO|jj|i|S)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoder.argsr3rrrrCzAriaProcessor.batch_decodecOrB)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r decoderDrrrrGrFzAriaProcessor.decodecCs0|jj}|jj}dd|D}tt||S)NcSsg|]}|dkr|qS)r5r)r&namerrr sz3AriaProcessor.model_input_names..)r model_input_namesrr:dictfromkeys)r.Ztokenizer_input_namesZimage_processor_input_namesrrrrJszAriaProcessor.model_input_names)NNNN)NNN)rrr__doc__ attributesZ valid_kwargsZimage_processor_classZtokenizer_classrrr9rrfloatr%r-r r rrr rrrArCrGpropertyrJ __classcell__rrr/rr,sB  @rN)typingrrrrZimage_processing_utilsrZ image_utilsrZprocessing_utilsr r r Ztokenization_utilsr r utilsrautorrr__all__rrrrs