`i$ddlmZmZddlmZddlmZddlmZm Z m Z ddl m Z m Z ddlmZejeZGdd ed ZGd d e Zd gZdS))OptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)loggingceZdZddiidZdS)Ovis2ProcessorKwargspaddingF) text_kwargs image_kwargsN)__name__ __module__ __qualname__ _defaults~/home/jaya/work/projects/VOICE-AGENT/VIET/agent-env/lib/python3.11/site-packages/transformers/models/ovis2/processing_ovis2.pyrrs+ u  IIIrrF)totalc eZdZdZddgZdZdZ dfd Z dd ee d e e e e e e e fd eed efdZd e e de e efdZdZdZedZxZS)Ovis2Processora Constructs a Ovis2 processor which wraps Ovis2 image processor and a Qwen2 tokenizer into a single processor. [`Ovis2Processor`] offers all the functionalities of [`Ovis2VideoProcessor`], [`Ovis2ImageProcessor`] and [`Qwen2TokenizerFast`]. See the [`~Ovis2Processor.__call__`] and [`~Ovis2Processor.decode`] for more information. Args: image_processor ([`Ovis2ImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`Qwen2TokenizerFast`], *optional*): The tokenizer is a required input. chat_template (`str`, *optional*): A Jinja template which will be used to convert lists of messages in a chat into a tokenizable string. image_token (`str`, *optional*, defaults to `""`): Special token used to denote image location. image_seq_length (`int`, *optional*, defaults to 256): The number of image tokens to be used for each image in the input. image_processor tokenizerAutoImageProcessor AutoTokenizerNc ||_t|dr|jn||_t|ddr|jn||j|_t j||fd|i|dS)N image_tokenimage_token_id chat_template)image_seq_lengthhasattrr$getattrr%convert_tokens_to_idssuper__init__)selfrrr&r$r'kwargs __class__s rr,zOvis2Processor.__init__=s!14;I}4U4Uf900[fy"2D99 CI $ $001ABB  )[[=[TZ[[[[[rimagestextr.returnc |jtfd|jji|}t |t r|g}n?t |t s*t |dt stdi}|Q|j|fi|d}| d }| ||}|j|fi|d}ti||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 Qwen2TokenizerFast's [`~Qwen2TokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` and `kwargs` arguments to Ovis2ImageProcessor's [`~Ovis2ImageProcessor.__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). 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`. - **image_sizes** -- Size of each image that will be used to unpad an image. Returned when `images` is not `None`. tokenizer_init_kwargsrzAInvalid input text. Please provide a string, or a list of stringsN images_kwargsgridsr)data) _merge_kwargsrr init_kwargs isinstancestrlist ValueErrorrpoptolist_expand_image_tokensr)r-r0r1r. output_kwargs image_inputs image_grids text_inputss r__call__zOvis2Processor.__call__Os&B+*   "&."<   dC  b6DDD$'' b 47C0H0H b`aa a  /4/YY-:XYYL&**733::<} t|D]} | d|jzz } | |dz kr| dz } | |dz kr| dz } ?| d z } |d| d}|dz }d|v|||S) Nrr!z z z z z z )r'rangereplaceappend) r-r1r6processed_text grid_indexsamplegridrowcol placeholderrcs rr@z#Ovis2Processor._expand_image_tokenss+   * *Fv%%Z(7DGS\L4;P,P\\\ 9q=="3ZZ77!&s;;A'lT=R.R+TTK 37{{ +{ : sQw;;';6K{*  ;BBa v%%  ! !& ) ) ) )rc&|jj|i|S)z This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoder-argsr.s rrUzOvis2Processor.batch_decodes +t~*D;F;;;rc&|jj|i|S)z This method forwards all its arguments to Qwen2TokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoderVs rrYzOvis2Processor.decodes %t~$d5f555rcp|jj}|jj}t|t|zS)N)rmodel_input_namesrr<)r-tokenizer_input_namesimage_processor_input_namess rr[z Ovis2Processor.model_input_namess6 $ @&*&:&L#)**T2M-N-NNNr)NNNr!r")NN)rrr__doc__ attributesimage_processor_classtokenizer_classr,rrrr r r<r rrrEintr@rUrYpropertyr[ __classcell__)r/s@rrr%s\&$[1J0%O \\\\\\((,^b4B4B$4BI0$y/4HYCZZ[4B-. 4B  4B4B4B4Bl9oDI6<<<666OOXOOOOOrrN)typingrrfeature_extraction_utilsr image_utilsrprocessing_utilsrr r tokenization_utils_baser r utilsr get_loggerrloggerrr__all__rrrrns #"""""""444444%%%%%%HHHHHHHHHHCCCCCCCC  H % %+5MOMOMOMOMO^MOMOMO`  r