U ,È-enã@s0dZddlmZddlmZGdd„deƒZdS)z$ Image/Text processor class for GIT é)ÚProcessorMixin)Ú BatchEncodingcsVeZdZdZddgZdZdZ‡fdd„Zdd d „Zd d „Z d d„Z e dd„ƒZ ‡Z S)Ú 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. Úimage_processorÚ tokenizerZAutoImageProcessorZ AutoTokenizercstƒ ||¡|j|_dS)N)ÚsuperÚ__init__rZcurrent_processor)Úselfrr©Ú __class__©úg/var/www/html/Darija-Ai-Train/env/lib/python3.8/site-packages/transformers/models/git/processing_git.pyr(szGitProcessor.__init__NcKs”|dkr|dkrtdƒ‚|dk r6|j|fd|i|—Ž}|dk rT|j|fd|i|—Ž}|dk rr|dk rr|j|d<|S|dk r~|Sttf|Ž|dSdS)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: 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. In case of a NumPy array/PyTorch tensor, each image should be of shape (C, H, W), where C is a number of channels, H and W are image height and width. 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: [`BatchEncoding`]: A [`BatchEncoding`] 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`. Nz?You have to specify either text or images. Both cannot be none.Úreturn_tensorsÚ pixel_values)ÚdataZ tensor_type)Ú ValueErrorrrrrÚdict)r ÚtextZimagesrÚkwargsÚencodingZimage_featuresr r r Ú__call__,s$ zGitProcessor.__call__cOs|jj||ŽS)zÁ This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )rÚ batch_decode©r Úargsrr r r raszGitProcessor.batch_decodecOs|jj||ŽS)z» This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rÚdecoderr r r rhszGitProcessor.decodecCs dddgS)NZ input_idsZattention_maskrr )r r r r Úmodel_input_namesoszGitProcessor.model_input_names)NNN)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú attributesZimage_processor_classZtokenizer_classrrrrÚpropertyrÚ __classcell__r r r r rs   5rN)rZprocessing_utilsrZtokenization_utils_baserrr r r r Ús