o Zh-!@sdZddlmZmZddlmZddlmZddlm Z m Z m Z m Z ddl mZmZddlmZeeZd ZGd d d e d d ZGddde d d ZGddde ZdgZdS)z Processor class for Janus. )ListUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixin TextKwargsUnpack)PreTokenizedInput TextInput)loggingzYou are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language. c@seZdZUeed<dS)JanusTextKwargsgeneration_modeN)__name__ __module__ __qualname__str__annotations__rrY/var/www/auris/lib/python3.10/site-packages/transformers/models/janus/processing_janus.pyr(s rF)totalc@s*eZdZUeed<dddddidZdS) JanusProcessorKwargs text_kwargsFtext)paddingrZreturn_tensorspt)rZ common_kwargsN)rrrrr _defaultsrrrrr,s  rc seZdZdZddgZddgZdZdZdfd d Z    dd e e e e e e e fd e deedefddZddZddZd e fddZeddZZS)JanusProcessora7 Constructs a Janus processor which wraps a Janus Image Processor and a Llama tokenizer into a single processor. [`JanusProcessor`] offers all the functionalities of [`JanusImageProcessor`] and [`LlamaTokenizerFast`]. See the [`~JanusProcessor.__call__`] and [`~JanusProcessor.decode`] for more information. Args: image_processor ([`JanusImageProcessor`]): The image processor is a required input. tokenizer ([`LlamaTokenizerFast`]): The tokenizer is a required input. chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. use_default_system_prompt (`str`, *optional*, defaults to `False`): Use default system prompt for Text Generation. image_processor tokenizer chat_templateuse_default_system_promptZJanusImageProcessorZLlamaTokenizerFastNFc s:d|_|j|_|j|_|j|_||_tj|||ddS)Ni@)r!) num_image_tokens image_tokenZ boi_tokenimage_start_tokenZ eoi_tokenimage_end_tokenr"super__init__)selfrr r!r"kwargs __class__rrr(Ks zJanusProcessor.__init__rimagesr*returnc Ks8|jtfd|jji|}|dur|durtd|dur:t|tr&|g}nt|ttfr6t dd|Ds:td|d d}g}|j |j |j |j} |D]"} | |j | } |jre|d kret| } |d krn| |j 7} || qQ|j|fi|d} |dur|d kr|jdd |i|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 JanusImageProcessor's [`~JanusImageProcessor.__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. Both channels-first and channels-last formats are supported. 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`. Ztokenizer_init_kwargsNz'You must specify either text or images.css|]}t|tVqdSN) isinstancer).0trrr sz*JanusProcessor.__call__..zAInvalid input text. Please provide a string, or a list of stringsrrrimager-Z images_kwargsZ pixel_values)datar)Z _merge_kwargsrr Z init_kwargs ValueErrorr0rlisttupleallpopr%r$r#r&replacer"DEFAULT_SYSTEM_PROMPTappendrr) r)rr-ZvideosZaudior*Z output_kwargsrZprompt_stringsZone_img_tokenspromptr5rrr__call__Ts<(     zJanusProcessor.__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)argsr*rrrrAzJanusProcessor.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 decoderBrrrrErDzJanusProcessor.decodecKs|jj|fi|S)z Forwards all arguments to the image processor's `postprocess` method. Refer to the original method's docstring for more details. )r postprocess)r)r-r*rrrrFszJanusProcessor.postprocesscCs"|jj}|jj}tt||Sr/)r model_input_namesrr7dictfromkeys)r)Ztokenizer_input_namesZimage_processor_input_namesrrrrGsz JanusProcessor.model_input_names)NF)NNNN)rrr__doc__ attributesZ valid_kwargsZimage_processor_classZtokenizer_classr(rr r rrr rrr?rArErFpropertyrG __classcell__rrr+rr4s2  LrN)rJtypingrrZfeature_extraction_utilsrZ image_utilsrZprocessing_utilsrrr r Ztokenization_utils_baser r utilsr Z get_loggerrloggerr<rrr__all__rrrrs