sg+'dZddlmZmZddlmZddlmZmZm Z ddl m Z m Z m Z mZddlmZmZddlmZej(eZGd d e d ZGd de Zy)z Processor class for Llava. )ListUnion) BatchFeature) ImageInputget_image_sizeto_numpy_array)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInput)loggingceZdZddiidZy)LlavaProcessorKwargspaddingF) text_kwargs images_kwargsN)__name__ __module__ __qualname__ _defaults]/var/www/html/venv/lib/python3.12/site-packages/transformers/models/llava/processing_llava.pyrrs u  IrrF)totalc eZdZdZddgZgdZdZdZ dfd Z dde d e e e e e e e fd eed efd Zd ZdZedZxZS)LlavaProcessorak Constructs a Llava processor which wraps a Llava image processor and a Llava tokenizer into a single processor. [`LlavaProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~LlavaProcessor.__call__`] and [`~LlavaProcessor.decode`] for more information. Args: image_processor ([`CLIPImageProcessor`], *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. Shoudl 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_tokensAutoImageProcessor AutoTokenizerc ||_||_||_t|dr |jn||_t ||||y)Nr%)r")r#r&r$hasattrr%super__init__) selfr r!r#r$r"r%r&kwargs __class__s rr,zLlavaProcessor.__init__MsJ%+F(.L+4;I}4U900[f )=Qrimagestextr.returnc x| | tdt||\}}|jtfd|jj i|}||j |fi|d}ni}t|tr|g}n.t|tst|dts td|}|jd|j|j|d} tt| d\} } | |jz| |jzz|jz} |jdk(r| |jz} g}|D]<} | j!|j"|j"| z} |j%| >nt&j)d|j|fi|d }t+i|| S) 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 doctsring 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`. z7You 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_valuesdefaultaExpanding inputs for image tokens in LLaVa should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config or set directly with `processor.patch_size = {{patch_size}}` and processor.vision_feature_select_strategy = {{vision_feature_select_strategy}}`. Using processors without these attributes in the config is deprecated and will throw an error in v4.50.r)data) ValueErrorr _merge_kwargsrr! init_kwargsr isinstancestrlistgetr#r$rr r&replacer%appendlogger warning_oncer)r-r0r1audiovideosr. output_kwargs image_inputsprompt_stringsr5heightwidthnum_image_tokenssample text_inputss r__call__zLlavaProcessor.__call__^sN >dlVW W9F ***  "&.."<"<   /4//Y-:XYLL dC 6DD$' 47C0H`a a   N + 7*t/R/R/^+N; .~l1o/N O $*doo$=T__,$44$5 66)C$(H(HH$!#"2F#^^D,<,N>NQa>abF"))&12##~%dnn^T}]7ST !@K!@r)NNNN)rrr__doc__ attributes valid_kwargsimage_processor_classtokenizer_classr,rrrrrr rrrMrOrSpropertyrU __classcell__)r/s@rrr(s2$[1JL1%O'+$%R&"^b VBVBI0$y/4HYCZZ[VB -. VB VBr<6XXrrN)rZtypingrrfeature_extraction_utilsr image_utilsrrr processing_utilsr r r r tokenization_utils_baserrutilsr get_loggerrrArrrrrrhsW4EEkkC   H %+5cX^cXr