o Zh"@sdZddlmZmZmZddlmZddlmZddl m Z m Z m Z m Z mZddlmZmZGdd d e d d ZGd d d e d d ZGddde ZdgZdS)z Processor class for Chameleon. )ListOptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixin TextKwargsUnpack!_validate_images_text_input_order)PreTokenizedInput TextInputc@seZdZUeed<dS)ChameleonTextKwargsreturn_for_text_completionN)__name__ __module__ __qualname__bool__annotations__rra/var/www/auris/lib/python3.10/site-packages/transformers/models/chameleon/processing_chameleon.pyrs rF)totalc@s*eZdZUeed<dddddidZdS)ChameleonProcessorKwargs text_kwargsF)paddingrreturn_tensorspt)rZ common_kwargsN)rrrrr _defaultsrrrrrs  rc seZdZdZddgZdZddgZdZddede ffd d Z dd e e de e eeeeeefdeedefddZddZddZeddZZS)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)ZLlamaTokenizerZLlamaTokenizerFastimage_seq_length image_tokenZChameleonImageProcessorcsh||_t|dr |jn||_||j|_t|dr|jnd|_t|dr(|jnd|_t ||dS)Nr# boi_tokenz eoi_tokenz) r"hasattrr#Zconvert_tokens_to_idsZimage_token_idr&image_start_tokenr'image_end_tokensuper__init__)selfr r!r"r# __class__rrr,DszChameleonProcessor.__init__Nimagestextkwargsreturnc Ks:t||\}}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} || qQ|d d d} |j|fi|d} |j|| d gd |dur|j|fi|d d | d <t| | 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 imagesZtokenizer_init_kwargsrrFrimage)Z modalitiesZ images_kwargsZ pixel_values)dataZ tensor_type)r isinstancestrlist TypeError ValueErrorZ _merge_kwargsrr!Z init_kwargspopr)r#r"r*replaceZ sep_tokenappendZ_check_special_mm_tokensr r) r-r0r1ZaudioZvideosr2Z output_kwargsrZprompt_stringsZone_img_tokenssamplerr5rrr__call__Os8)    zChameleonProcessor.__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-argsr2rrrrAzChameleonProcessor.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. )r!decoderBrrrrErDzChameleonProcessor.decodecCs"|jj}|jj}tt||S)N)r!model_input_namesr r8dictfromkeys)r-Ztokenizer_input_namesZimage_processor_input_namesrrrrFsz$ChameleonProcessor.model_input_names)r$r%)NNNN)rrr__doc__ attributesZtokenizer_classZ valid_kwargsZimage_processor_classintr7r,rrrrr rr rrr?rArEpropertyrF __classcell__rrr.rr,s0  KrN)rItypingrrrZfeature_extraction_utilsrZ image_utilsrZprocessing_utilsrr r r r Ztokenization_utils_baser rrrr__all__rrrrs