o i6'@sdZddlmZmZddlZddlmZddlm Z m Z m Z ddl m Z mZmZmZddlmZmZdd lmZeeZGd d d ed d ZGdddeZdgZdS)z Processor class for Llava. )OptionalUnionN) BatchFeature) ImageInputget_image_sizeto_numpy_array)MultiModalDataProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)loggingc@seZdZdddidZdS)LlavaProcessorKwargsF)paddingreturn_mm_token_type_ids) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaultsrrg/home/ubuntu/veenaModal/venv/lib/python3.10/site-packages/transformers/models/llava/processing_llava.pyr&s rF)totalc seZdZdZddgZdZdZ       dfd d Z    dd ee d e e e e e e e fd eedefddZdddZZS)LlavaProcessoram Constructs a LLaVa processor which wraps a LLaVa image processor and a LLaMa tokenizer into a single processor. [`LlavaProcessor`] offers all the functionalities of [`LlavaImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~LlavaProcessor.__call__`] and [`~LlavaProcessor.decode`] for more information. Args: image_processor ([`LlavaImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`], *optional*): The tokenizer is a required input. 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 chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. 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_processor tokenizerAutoImageProcessor AutoTokenizerNrc  sT||_||_||_t|dr|jn||_|j|jddd|_tj|||ddS)N image_tokenF)add_special_tokensr) chat_template) patch_sizenum_additional_image_tokensvision_feature_select_strategyhasattrr"encodeimage_token_idsuper__init__) selfrrr%r'r$r"r&kwargs __class__rrr,Ks  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)a Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments to LlamaTokenizerFast's [`~LlamaTokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` and `kwargs` arguments to CLIPImageProcessor's [`~CLIPImageProcessor.__call__`] if `images` is not `None`. Please refer to the docstring of the above two methods for more information. Args: images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `list[PIL.Image.Image]`, `list[np.ndarray]`, `list[torch.Tensor]`): 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 (`str`, `list[str]`, `list[list[str]]`): 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. 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_kwargsrrzAInvalid 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 TypeErrorgetrrr%r&r'replacer"appendpop_check_special_mm_tokensnparray zeros_liker*tolistr)r-r1r2audiovideosr. output_kwargs image_inputsprompt_stringsr5heightwidthnum_image_tokenssampler8r text_inputs array_idsr<rrr__call__]sR'    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. Nr crop_sizerTrUr6r7)rVnum_image_patchesr) rrrFupdaterr[r%r&r'lenr ) r- image_sizesr. vision_datarr[resized_height resized_widthrVr\rrr_get_num_multimodal_tokenss    z)LlavaProcessor._get_num_multimodal_tokens)NNNNNr!r)NNNN)N)rrr__doc__ attributesimage_processor_classtokenizer_classr,rrrrr rDr rrrZrc __classcell__rrr/rr-s6 Wr)rdtypingrrnumpyrKfeature_extraction_utilsr image_utilsrrrprocessing_utilsr r r r tokenization_utils_baser rutilsr get_loggerrloggerrr__all__rrrrs    (