sg dZddlmZmZmZddlmZddlmZddl m Z m Z m Z m Z mZddlmZmZGdd e d ZGd d e d ZGdde Zy)z Processor class for Chameleon. )ListOptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixin TextKwargsUnpack!_validate_images_text_input_order)PreTokenizedInput TextInputceZdZUeed<y)ChameleonTextKwargsreturn_for_text_completionN)__name__ __module__ __qualname__bool__annotations__e/var/www/html/venv/lib/python3.12/site-packages/transformers/models/chameleon/processing_chameleon.pyrrs $$rrF)totalc,eZdZUeed<dddddidZy)ChameleonProcessorKwargs text_kwargsF)paddingrreturn_tensorspt)r common_kwargsN)rrrrr _defaultsrrrrrs($$*/ d Irrc eZdZdZddgZdZdZddedeffd Z dd e e d e e e eee eefd eed efd ZdZdZedZxZS)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_tokenc||_t|dr |jn||_t|dr |jnd|_t|dr |j nd|_t|!||y)Nr, boi_tokenz eoi_tokenz) r+hasattrr,r.image_start_tokenr/image_end_tokensuper__init__)selfr&r'r+r, __class__s rr4zChameleonProcessor.__init__Csl 04;I}4U900[f#*9k#BI   7>i6Uy22[c )4rimagestextkwargsreturnc t||\}}t|tr|g}n.t|tst|dts t d| | t d|j tfd|jji|}|djdd}g}|j|j|jzz|jz} |D]J} | j|j| } |s| |jj z } |j#| L|j|fi|d} ||j$|fi|dd | d <t'| |d d  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`. rzAInvalid input text. Please provide a string, or a list of stringsz&You must provide either text or imagestokenizer_init_kwargsrrF images_kwargs pixel_valuesr"r )data tensor_type)r isinstancestrlist TypeError ValueError _merge_kwargsrr' init_kwargspopr1r,r+r2replace sep_tokenappendr&r) r5r7r8audiovideosr9 output_kwargsrprompt_stringsone_img_tokenssampler?s r__call__zChameleonProcessor.__call__MsR9F  dC 6DD$' 47C0H_` ` )NNNN)rrr__doc__ attributestokenizer_classimage_processor_classintrBr4rrrrrrr rrrRrTrXpropertyrZ __classcell__)r6s@rr%r%,s$$[1J>O55S5^a5(,hl Fe$FeuY(94 ?DQbLccdeFe 12 Fe FeR<6XXrr%N)r_typingrrrfeature_extraction_utilsr image_utilsrprocessing_utilsr r r r r tokenization_utils_baserrrrr%rrrrksN)(4%wwC%*E% /u ~X~Xr