rh%dZddlZddlmZddlmZddlmZddlm Z m Z m Z ddl m Z mZmZdd lmZd d lmZej(eZGd d e dZGdde ZdgZy)zq Processor class for InstructBLIP. Largely copy of Blip2Processor with addition of a tokenizer for the Q-Former. N)Union) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack) AddedTokenPreTokenizedInput TextInput)logging) AutoTokenizerc *eZdZdddddddddd idZy)InstructBlipProcessorKwargsTFr) add_special_tokenspaddingstridereturn_overflowing_tokensreturn_special_tokens_maskreturn_offsets_mappingreturn_token_type_ids return_lengthverbose) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaults/var/www/html/ai-insurance-compliance-backend/venv/lib/python3.12/site-packages/transformers/models/instructblip/processing_instructblip.pyrr!s0#').*/&+%*"   Ir"rF)totalc eZdZdZgdZdZdZdZdfd Z dde de e e e e e e fdeed efd Zd Zd Zed ZfdZefdZxZS)InstructBlipProcessora Constructs an InstructBLIP processor which wraps a BLIP image processor and a LLaMa/T5 tokenizer into a single processor. [`InstructBlipProcessor`] offers all the functionalities of [`BlipImageProcessor`] and [`AutoTokenizer`]. 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 (`AutoTokenizer`): An instance of ['PreTrainedTokenizer`]. The tokenizer is a required input. qformer_tokenizer (`AutoTokenizer`): An instance of ['PreTrainedTokenizer`]. The Q-Former tokenizer is a required input. num_query_tokens (`int`, *optional*):" Number of tokens used by the Qformer as queries, should be same as in model's config. )image_processor tokenizerqformer_tokenizer)BlipImageProcessorBlipImageProcessorFastrc t|ds2tddd|_|j|jgdn|j|_||_t ||||y)N image_tokenzFT) normalizedspecial)special_tokens)hasattrr r- add_tokensnum_query_tokenssuper__init__)selfr'r(r)r3kwargs __class__s r#r5zInstructBlipProcessor.__init__Jsby-0))tTD   $"2"2!3D I(44D  0 )5FGr"imagestextr7returnc | | td|jtfd|jji|}|dj dd}i}|Kt |tr|g}n.t |tst |dts td|j|fi|d} | j d|d <| j d |d <|djd |dd xx|jzcc<|j|fi|d} |t|jj|jz} d |dd<d |dd<d |dd<|j| fi|d} | D]} | | Dcgc] }| | |z c}| | < |j| |'|j|fi|d}|j|t!||}|Scc}w)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). Nz,You have to specify at least images or text.tokenizer_init_kwargsrreturn_tensorsrzAInvalid input text. Please provide a string, or a list of strings input_idsqformer_input_idsattention_maskqformer_attention_mask max_lengthFrr truncationr) tensor_type) ValueError _merge_kwargsrr( init_kwargspop isinstancestrlistr)getr3r-contentupdater'r)r6r9r:audiovideosr7 output_kwargsr>encodingqformer_text_encoding text_encoding image_tokensimage_text_encodingksampleimage_encodings r#__call__zInstructBlipProcessor.__call__Ts1, >dlKL L*** ' "&.."<"<  '}599:JDQ  $$vd+JtAw4L !dee$:D$:$:4$`=Q^C_$` !,A,E,Ek,RH( )1F1J1JK[1\H- .]+// =Im,\:d>S>SS:*DNN4P=3OPM!#//77$:O:OO EJ m,-AB:? m,Y7=B m,\:&4dnn\&b]S`Ea&b#&hAVcdeVf'gF(;A(>(G'gM!$h OOM *  1T11&[M/>. )~.>>abc c NT2!#n>Q!R ../EF.@  OO " "#6 7').CFC  OO 34 4Or"c t||fi|}t|tr|d}t j|d}||_|S)Nrr)) subfolder)r4from_pretrainedrJtuplerr))clspretrained_model_name_or_pathr7 processorr)r8s r#ryz%InstructBlipProcessor.from_pretrainedsPG+,ITVT  i '!! I)99:Wcvw&7 #r"rc)NNNN)rrr__doc__rqimage_processor_classtokenizer_classqformer_tokenizer_classr5rrr r rLr rrr[r]rapropertyrdrp classmethodry __classcell__)r8s@r#r&r&2s$GJL%O-H"^b AAI0$y/4HYCZZ[A 45 A AH<6XX &r"r&)r~rktypingrimage_processing_utilsr image_utilsrprocessing_utilsrrr tokenization_utils_baser r r utilsr autor get_loggerrloggerrr&__all__r!r"r#rsf 2%HHOO    H %"2%"YNYx # #r"