o ei@sdZddlZddlmZddlmZmZmZddl m Z m Z m Z m Z ddlmZmZddlmZmZeeZGd d d e d d ZeGd dde ZdgZdS)z Processor class for Llava. N) BatchFeature) ImageInputget_image_sizeto_numpy_array)MultiModalDataProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)auto_docstringloggingc@seZdZddddiZdS)LlavaProcessorKwargs text_kwargsF)paddingreturn_mm_token_type_idsN)__name__ __module__ __qualname__ _defaultsrrh/home/ubuntu/transcripts/venv/lib/python3.10/site-packages/transformers/models/llava/processing_llava.pyr#s rF)totalc sveZdZ       dfdd Ze  ddedBdeeBeeBeeBde e d e fd d Z dd d Z ZS)LlavaProcessorNrc  sT||_||_||_t|dr|jn||_|j|jddd|_tj|||ddS)a patch_size (`int`, *optional*): Patch size from the vision tower. vision_feature_select_strategy (`str`, *optional*): The feature selection strategy used to select the vision feature from the vision backbone. Should be same as in model's config image_token (`str`, *optional*, defaults to `""`): Special token used to denote image location. num_additional_image_tokens (`int`, *optional*, defaults to 0): Number of additional tokens added to the image embeddings, such as CLS (+1). If the backbone has no CLS or other extra tokens appended, no need to set this arg. image_tokenF)add_special_tokensr) chat_templateN) patch_sizenum_additional_image_tokensvision_feature_select_strategyhasattrrencodeimage_token_idsuper__init__) selfimage_processor tokenizerrr!rrr kwargs __class__rrr&+s zLlavaProcessor.__init__imagestextr*returncKs|dur |dur td|jtfd|jji|}|dur)|j|fi|d}ni}t|tr4|g}nt|tsDt|dtsDt d|}| ddur|d}t t |d\}} ||j | |j |j} |jdkrq| d 8} g}|D]} | |j|j| } || qu|d d d} |d d d } |j|fi|d d di}|j||dgd| rt|d}t|d}d |||jk<||d<ti||| dS)aA 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`. Nz7You have to specify at least one of `images` or `text`.tokenizer_init_kwargs images_kwargsrzAInvalid input text. Please provide a string, or a list of strings pixel_valuesdefaultrreturn_tensorsrFimage) modalities input_idsmm_token_type_ids)data tensor_type) ValueError _merge_kwargsrr) init_kwargsr( isinstancestrlist TypeErrorgetrrrr r!replacerappendpop_check_special_mm_tokensnparray zeros_liker$tolistr)r'r-r.r* output_kwargs image_inputsprompt_stringsr2heightwidthnum_image_tokenssampler5r text_inputs array_idsr9rrr__call__IsR    zLlavaProcessor.__call__c Ksi}|durStjdi}|||ddp|jj}|d|d}}||j||j}||j7}|jdkr=|d8}|gt |}dgt |} ||| dt d i|S) a Computes the number of placeholder tokens needed for multimodal inputs with the given sizes. Args: image_sizes (`list[list[int]]`, *optional*): The input sizes formatted as (height, width) per each image. Returns: `MultiModalData`: A `MultiModalData` object holding number of tokens per each of the provided input modalities, along with other useful data. Nr1 crop_sizerOrPr3r4)rQnum_image_patchesr) rrrCupdater(rVrr r!lenr) r' image_sizesr* vision_datar1rVresized_height resized_widthrQrWrrr_get_num_multimodal_tokenss    z)LlavaProcessor._get_num_multimodal_tokens)NNNNNrr)NN)N)rrrr&r rr r rAr rrrUr^ __classcell__rrr+rr)s, @r)__doc__numpyrHfeature_extraction_utilsr image_utilsrrrprocessing_utilsrrr r tokenization_utils_baser r utilsr r get_loggerrloggerrr__all__rrrrs