o wi)@sdZddlmZmZddlZddlmZddlm Z ddl m Z m Z m Z mZmZmZddlmZmZGd d d ed d ZGd dde d d ZGddde ZdgZdS)z Processor class for Chameleon. )OptionalUnionN) BatchFeature) ImageInput)MultiModalDataProcessingKwargsProcessorMixin TextKwargsUnpack!_validate_images_text_input_order)PreTokenizedInput TextInputc@seZdZUeed<dS)ChameleonTextKwargsreturn_for_text_completionN)__name__ __module__ __qualname__bool__annotations__rro/home/ubuntu/sommelier/.venv/lib/python3.10/site-packages/transformers/models/chameleon/processing_chameleon.pyr$s rF)totalc@s,eZdZUeed<ddddddidZdS)ChameleonProcessorKwargs text_kwargsF)paddingrreturn_mm_token_type_idsreturn_tensorspt)r common_kwargsN)rrrrr _defaultsrrrrr(s  rc seZdZdZddgZdZdZdded effd d Z dd e e de e e eee eefdeedefddZdddZddZddZeddZZS)ChameleonProcessora/ Constructs a Chameleon processor which wraps a Chameleon image processor and a Chameleon tokenizer into a single processor. [`ChameleonProcessor`] offers all the functionalities of [`ChameleonImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~ChameleonProcessor.__call__`] and [`~ChameleonProcessor.decode`] for more information. Args: image_processor ([`ChameleonImageProcessor`]): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`]): The tokenizer is a required input. image_seq_length (`int`, *optional*, defaults to 1024): Sequence length of one image embedding. image_token (`str`, *optional*, defaults to `""`): The special token used to indicate image in the text. image_processor tokenizer)LlamaTokenizerLlamaTokenizerFastChameleonImageProcessorimage_seq_length image_tokencs||_t|dr |jn||_||j|_t|dr|jnd|_t|dr(|jnd|_||j|_||j|_ ||j|_ |j|j |j g|_ t ||dS)Nr* boi_tokenz eoi_tokenz)r)hasattrr*convert_tokens_to_idsimage_token_idr+image_start_tokenr,image_end_tokenimage_start_token_idimage_end_token_id image_idssuper__init__)selfr"r#r)r* __class__rrr6MszChameleonProcessor.__init__NimagestextkwargsreturncKst||\}}t|tr|g}nt|ts t|dts td|dur,|dur,td|jtfd|jj i|}|d dd}g}|j |j |j |j} |D]} | |j | } |sb| |jj7} || qQi} |dury|j|fi|d } |d d d} |d d d} |j|fi|dd di}|j||d gd | rt|d}t|d}d|t||j<||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 `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`. rzAInvalid input text. Please provide a string, or a list of stringsNz&You must provide either text or imagestokenizer_init_kwargsrrF images_kwargsrrimage) modalities input_idsmm_token_type_ids)data tensor_type)r isinstancestrlist TypeError ValueError _merge_kwargsrr# init_kwargspopr0r*r)r1replace sep_tokenappendr"_check_special_mm_tokensnparray zeros_likeisinr4tolistr)r7r:r;audiovideosr< output_kwargsrprompt_stringsone_img_tokenssample image_inputsrr text_inputs array_idsrDrrr__call__\sF)    zChameleonProcessor.__call__cKsLi}|dur|jdgt|}dgt|}|||dtdi|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. NrC)num_image_tokensnum_image_patchesr)r)lenupdater)r7 image_sizesr< vision_datarcrdrrr_get_num_multimodal_tokenss  z-ChameleonProcessor._get_num_multimodal_tokenscO|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_decoder7argsr<rrrrkzChameleonProcessor.batch_decodecOrj)z This method forwards all its arguments to LlamaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r#decoderlrrrrornzChameleonProcessor.decodecCs"|jj}|jj}tt||SN)r#model_input_namesr"rIdictfromkeys)r7tokenizer_input_namesimage_processor_input_namesrrrrqsz$ChameleonProcessor.model_input_names)r'r()NNNNrp)rrr__doc__ attributestokenizer_classimage_processor_classintrHr6rrrrr rIr rrrarirkropropertyrq __classcell__rrr8rr!6s0 Rr!)rvtypingrrnumpyrSfeature_extraction_utilsr image_utilsrprocessing_utilsrrr r r r tokenization_utils_baser rrrr!__all__rrrrs    (