bCi|SrSSKJrJr SSKJr SSKJrJrJ r SSK J r J r J r "SS\S S 9r"S S \5rS /rg )z Processor class for Blip. )OptionalUnion) ImageInput)ProcessingKwargsProcessorMixinUnpack) BatchEncodingPreTokenizedInput TextInputc 2\rSrSrSSSSSSSSSS. 0S.rSrg) BlipProcessorKwargsTFr) add_special_tokenspaddingstridereturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mappingreturn_token_type_ids return_lengthverbose) text_kwargs images_kwargsN)__name__ __module__ __qualname____firstlineno__ _defaults__static_attributes__rb/home/james-whalen/.local/lib/python3.13/site-packages/transformers/models/blip/processing_blip.pyrrs0#').*/&+%*"   Ir"rF)totalc ^\rSrSrSrSS/rSrSrU4SjrSS\ \ S \ \ \ \ \ \\4S \\S \4S jjr\S 5rSrU=r$) BlipProcessor+a9 Constructs a BLIP processor which wraps a BERT tokenizer and BLIP image processor into a single processor. [`BlipProcessor`] offers all the functionalities of [`BlipImageProcessor`] and [`BertTokenizerFast`]. See the docstring of [`~BlipProcessor.__call__`] and [`~BlipProcessor.decode`] for more information. Args: image_processor (`BlipImageProcessor`): An instance of [`BlipImageProcessor`]. The image processor is a required input. tokenizer (`BertTokenizerFast`): An instance of ['BertTokenizerFast`]. The tokenizer is a required input. image_processor tokenizer)BlipImageProcessorBlipImageProcessorFast) BertTokenizerBertTokenizerFastc T>SUl[TU] X5 URUlg)NF)rsuper__init__r(current_processor)selfr(r)kwargs __class__s r#r0BlipProcessor.__init__=s&*/ ' 4!%!5!5r"imagestextr3returnc UcUc [S5eSnUR"[4SURR0UD6nUbUR"U40USD6nUb,UR "U40USD6nUbUR U5 U$U$)a This method uses [`BlipImageProcessor.__call__`] method to prepare image(s) for the model, and [`BertTokenizerFast.__call__`] to prepare text for the model. Please refer to the docstring of the above two methods for more information. Args: 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. 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). return_tensors (`str` or [`~utils.TensorType`], *optional*): If set, will return tensors of a particular framework. Acceptable values are: - `'tf'`: Return TensorFlow `tf.constant` objects. - `'pt'`: Return PyTorch `torch.Tensor` objects. - `'np'`: Return NumPy `np.ndarray` objects. - `'jax'`: Return JAX `jnp.ndarray` objects. Nz*You have to specify either images or text.tokenizer_init_kwargsrr) ValueError _merge_kwargsrr) init_kwargsr(update) r2r6r7audiovideosr3 text_encoding output_kwargsencoding_image_processors r#__call__BlipProcessor.__call__Bs8 >dlIJ J **  "&.."<"<    NN4P=3OPM  '+';';F'emTcFd'e $((// >+ +r"cURRnURRnUVs/sH o3S:wdM UPM nnX-$s snf)Ntoken_type_ids)r)model_input_namesr()r2tokenizer_input_namesimage_processor_input_namesnames r#rHBlipProcessor.model_input_namesusP $ @ @&*&:&:&L&L#2G d2G$ScKc2G d$BB!es A A )r1)NNNN)rrrr__doc__ attributesimage_processor_classtokenizer_classr0rrrstrlistr r r rr rDpropertyrHr! __classcell__)r4s@r#r&r&+s $[1JLrZsH#%HHRR*%"OCNOCd  r"