o Zh%@sdZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZddlmZeeZGd d d e d d ZGd dde ZdgZdS)z Processor class for Llava. )ListUnion) BatchFeature) ImageInputget_image_sizeto_numpy_array)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInput)loggingc@seZdZddiidZdS)LlavaProcessorKwargspaddingF) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaultsrrY/var/www/auris/lib/python3.10/site-packages/transformers/models/llava/processing_llava.pyrs  rF)totalc seZdZdZddgZgdZdZdZ       dfd d Z    dd e d e e e e e e e fdeedefddZddZddZeddZZS)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 tokenizer) chat_template patch_sizevision_feature_select_strategy image_tokennum_additional_image_tokensZAutoImageProcessorZ AutoTokenizerNrc  s^||_||_||_t|dr|jn||_t|ddr|jn||j|_tj |||ddS)Nr!image_token_id)r) rr"r hasattrr!getattrr$Zconvert_tokens_to_idssuper__init__) selfrrrr rr!r"kwargs __class__rrr(Ms   zLlavaProcessor.__init__imagestextr*returncKsh|dur |dur tdt||\}}|jtfd|jji|}|dur0|j|fi|d}ni}t|tr;|g}nt|t sKt|dtsKtd|}| ddur|d} t t | d\} } | |j | |j |j} |jdkrx| d 8} g}|D]} | |j|j| } || q||d d d}|j|fi|d }|j||d gd 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 `kwrags` 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`.Ztokenizer_init_kwargsrrzAInvalid input text. Please provide a string, or a list of strings pixel_valuesdefaultrreturn_tensorsimage)Z modalities)dataZ tensor_type) ValueErrorr Z _merge_kwargsrrZ init_kwargsr isinstancestrlistgetrrrr"r replacer!appendpopZ_check_special_mm_tokensr)r)r-r.ZaudioZvideosr*Z output_kwargsZ image_inputsZprompt_stringsr0heightwidthZnum_image_tokenssampler3Z text_inputsrrr__call__csH'   zLlavaProcessor.__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)argsr*rrrrCzLlavaProcessor.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. )rdecoderDrrrrGrFzLlavaProcessor.decodecCs"|jj}|jj}tt||S)N)rmodel_input_namesrr9dictfromkeys)r)Ztokenizer_input_namesZimage_processor_input_namesrrrrHsz LlavaProcessor.model_input_names)NNNNNr#r)NNNN)rrr__doc__ attributesZ valid_kwargsZimage_processor_classZtokenizer_classr(rrrr rr rrrArCrGpropertyrH __classcell__rrr+rr(s> SrN)rKtypingrrZfeature_extraction_utilsrZ image_utilsrrrZprocessing_utilsr r r r Ztokenization_utils_baser rutilsrZ get_loggerrloggerrr__all__rrrrs     &