hddlmZddlmZddlmZddlmZmZm Z ddl m Z m Z ddl mZejeZGdd ed ZGd d eZd gZy))Union) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack)PreTokenizedInput TextInput)loggingceZdZddiidZy)Ovis2ProcessorKwargspaddingF) text_kwargs image_kwargsN)__name__ __module__ __qualname__ _defaultsh/var/www/html/eduruby.in/venv/lib/python3.12/site-packages/transformers/models/ovis2/processing_ovis2.pyrrs u  IrrF)totalc eZdZdZddgZdZdZ dfd Z ddede e e e e e e fd e ed efd Zde e d e e efd ZdZdZedZxZS)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 AutoTokenizerc ||_t|dr |jn||_t|ddr |jn|j |j|_t |||fd|i|y)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__=sy!14;I}4U900[fy"2D9  $ $001A1AB  )[=[TZ[rimagestextr+returnc |jtfd|jji|}t |t r|g}n.t |t st |dt s tdi}|G|j|fi|d}|jdj}|j||}|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 `kwrags` 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 strings images_kwargsgridsr)data) _merge_kwargsrr init_kwargs isinstancestrlist ValueErrorrpoptolist_expand_image_tokensr)r*r-r.r+ output_kwargs image_inputs image_grids text_inputss r__call__zOvis2Processor.__call__OsB+**  "&.."<"<  dC 6DD$' 47C0H`a a  /4//Y-:XYL&**73::z z z z z z )r$rangereplaceappend) r*r.r3processed_text grid_indexsamplegridrowcol placeholderrcs rr=z#Ovis2Processor._expand_image_tokenss   *Fv%Z(7DGS +L4;P;P,P+QQ[\ 9q="3Z7!&s;A'lT=R=R.R-STK 37{ +{ : ;sQw;';6K 7{*  ;Ba v%  ! !& )# *$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 rrSzOvis2Processor.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. )rdecoderTs rrWzOvis2Processor.decodes %t~~$$d5f55rc|jj}|jj}t|t|zS)N)rmodel_input_namesrr9)r*tokenizer_input_namesimage_processor_input_namess rrYz Ovis2Processor.model_input_namess; $ @ @&*&:&:&L&L#)*T2M-NNNr)NNNrD)NN)rrr__doc__ attributesimage_processor_classtokenizer_classr)rrr r r9r rrrBintr=rSrWpropertyrY __classcell__)r,s@rrr%s&$[1J0%O \("^b4B4BI0$y/4HYCZZ[4B-. 4B  4Bl9oDI6<6OOrrN)typingrfeature_extraction_utilsr image_utilsrprocessing_utilsrrr tokenization_utils_baser r utilsr get_loggerrloggerrr__all__rrrrmsZ 4%HHC   H %+5MO^MO`  r