o hr@stdZddlmZmZmZddlmZddlmZddl m Z ddl m Z m Z mZmZddlmZGd d d e Zd S) z Processor class for Llava. )ListOptionalUnion) BatchFeature) ImageInput)ProcessorMixin)PaddingStrategyPreTokenizedInput TextInputTruncationStrategy) TensorTypecseZdZdZddgZdZdZdfdd Zddd ddej fd e e e e e e e fd ed e eeefd e eeefdee eefdef ddZddZddZeddZZS)LlavaProcessora) 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. image_processor tokenizerCLIPImageProcessor)LlamaTokenizerLlamaTokenizerFastNcst||dSN)super__init__)selfrr __class__`/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/llava/processing_llava.pyr/szLlavaProcessor.__init__Ftextimagespadding truncationreturn_tensorsreturnc CsJ|dur|j||dd}nd}|j|||||d}ti|d|idS)aK 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: 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). 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. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a number of channels, H and W are image height and width. padding (`bool`, `str` or [`~utils.PaddingStrategy`], *optional*, defaults to `False`): Select a strategy to pad the returned sequences (according to the model's padding side and padding index) among: - `True` or `'longest'`: Pad to the longest sequence in the batch (or no padding if only a single sequence if provided). - `'max_length'`: Pad to a maximum length specified with the argument `max_length` or to the maximum acceptable input length for the model if that argument is not provided. - `False` or `'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of different lengths). max_length (`int`, *optional*): Maximum length of the returned list and optionally padding length (see above). truncation (`bool`, *optional*): Activates truncation to cut input sequences longer than `max_length` to `max_length`. 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`. N)r pixel_values)r rr max_length)data)rrr) rrrrrr#r r" text_inputsrrr__call__2s7 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_decoderargskwargsrrrr(tzLlavaProcessor.batch_decodecOr')z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder)rrrr-|r,zLlavaProcessor.decodecCs"|jj}|jj}tt||Sr)rmodel_input_namesrlistdictfromkeys)rtokenizer_input_namesimage_processor_input_namesrrrr.sz LlavaProcessor.model_input_names)NN)__name__ __module__ __qualname____doc__ attributesimage_processor_classtokenizer_classrr PYTORCHrr r rrboolstrr r rrr&r(r-propertyr. __classcell__rrrrrs:    BrN)r7typingrrrfeature_extraction_utilsr image_utilsrprocessing_utilsrtokenization_utils_baser r r r utilsr rrrrrs