sgdZddlmZmZmZddlmZddlmZddl m Z m Z m Z m Z ddlmZmZddlmZGd d e d Zej(eZGd de Zy)z$ Image/Text processor class for GIT )ListOptionalUnion) BatchFeature) ImageInput)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order)PreTokenizedInput TextInput)loggingceZdZiZy)GitProcessorKwargsN)__name__ __module__ __qualname__ _defaultsY/var/www/html/venv/lib/python3.12/site-packages/transformers/models/git/processing_git.pyrrsIrrF)totalc eZdZdZddgZdZdZfdZ ddee dee e e e e e e fd eed efd Zd Zd ZedZxZS) GitProcessora Constructs a GIT processor which wraps a CLIP image processor and a BERT tokenizer into a single processor. [`GitProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`BertTokenizerFast`]. See the [`~GitProcessor.__call__`] and [`~GitProcessor.decode`] for more information. Args: image_processor ([`AutoImageProcessor`]): The image processor is a required input. tokenizer ([`AutoTokenizer`]): The tokenizer is a required input. image_processor tokenizerAutoImageProcessor AutoTokenizercHt||||j|_y)N)super__init__rcurrent_processor)selfrr __class__s rr"zGitProcessor.__init__5s  )4!%!5!5rimagestextkwargsreturnc |jdd}|rtjd| | tdt ||\}}|j t fd|jji|}i}|'|j|fi|d} |j| |K|j|fi|d} |j| |s"|d dddd f|d <|d dddd f|d <t||d jd 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 BertTokenizerFast's [`~BertTokenizerFast.__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 (`TextInput`, `PreTokenizedInput`, `List[TextInput]`, `List[PreTokenizedInput]`, *optional*): 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`. legacyTa5Legacy behavior is being used. The current behavior will be deprecated in version 5.0.0. In the new behavior, if both images and text are provided, the last token (EOS token) of the input_ids and attention_mask tensors will be removed. To test the new behavior, set `legacy=False`as a processor call argument.Nz?You have to specify either text or images. Both cannot be none.tokenizer_init_kwargs text_kwargs images_kwargs input_idsattention_mask common_kwargsreturn_tensors)data tensor_type) poplogger warning_once ValueErrorr _merge_kwargsrr init_kwargsupdaterrget) r$r&r'audiovideosr(r+ output_kwargsr4 text_featuresimage_featuress r__call__zGitProcessor.__call__9sBRHd+    \  )?3B3)G%&=3Q3U3UVf3ghhrc:|jj|i|S)z This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoder$argsr(s rrEzGitProcessor.batch_decodes +t~~**D;F;;rc:|jj|i|S)z This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoderFs rrIzGitProcessor.decodes %t~~$$d5f55rc gdS)N)r/r1 pixel_valuesr)r$s rmodel_input_nameszGitProcessor.model_input_namess>>r)NNNN)rrr__doc__ attributesimage_processor_classtokenizer_classr"rrrrr rr rrrCrErIpropertyrL __classcell__)r%s@rrr#s $[1J0%O6 (,hl Ii$IiuY(94 ?DQbLccdeIi +, Ii IiV<6??rrN)rMtypingrrrfeature_extraction_utilsr image_utilsrprocessing_utilsr r r r tokenization_utils_baser rutilsrr get_loggerrr7rrrrrZsU)(4%kkC)   H %q?>q?r