U 4Af@s8dZddlZddlmZddlmZGdddeZdS)z( Image/Text processor class for AltCLIP N)ProcessorMixin) BatchEncodingcsXeZdZdZddgZdZdZdfdd Zdd d Zd d Z d dZ e ddZ Z S)AltCLIPProcessoraD Constructs a AltCLIP processor which wraps a CLIP image processor and a XLM-Roberta tokenizer into a single processor. [`AltCLIPProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`XLMRobertaTokenizerFast`]. See the [`~AltCLIPProcessor.__call__`] and [`~AltCLIPProcessor.decode`] for more information. Args: image_processor ([`CLIPImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`XLMRobertaTokenizerFast`], *optional*): The tokenizer is a required input. image_processor tokenizerZCLIPImageProcessor)ZXLMRobertaTokenizerZXLMRobertaTokenizerFastNc sdd}d|kr"tdt|d}|dk r.|n|}|dkrBtd|dkrRtdt||dS)Nfeature_extractorzhThe `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor` instead.z)You need to specify an `image_processor`.z"You need to specify a `tokenizer`.)warningswarn FutureWarningpop ValueErrorsuper__init__)selfrrkwargsr __class__R/tmp/pip-unpacked-wheel-zw5xktn0/transformers/models/altclip/processing_altclip.pyr,s zAltCLIPProcessor.__init__cKs|dkr|dkrtd|dk r6|j|fd|i|}|dk rT|j|fd|i|}|dk rr|dk rr|j|d<|S|dk r~|Sttf||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 XLMRobertaTokenizerFast's [`~XLMRobertaTokenizerFast.__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. 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: [`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.return_tensors pixel_values)dataZ tensor_type)r rrrrdict)rtextZimagesrrencodingZimage_featuresrrr__call__>s# zAltCLIPProcessor.__call__cOs|jj||S)z This method forwards all its arguments to XLMRobertaTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoderargsrrrrrrszAltCLIPProcessor.batch_decodecOs|jj||S)z This method forwards all its arguments to XLMRobertaTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoderrrrr yszAltCLIPProcessor.decodecCs"|jj}|jj}tt||S)N)rmodel_input_namesrlistrfromkeys)rZtokenizer_input_namesZimage_processor_input_namesrrrr!sz"AltCLIPProcessor.model_input_names)NN)NNN)__name__ __module__ __qualname____doc__ attributesZimage_processor_classZtokenizer_classrrrr propertyr! __classcell__rrrrrs 4r)r'r Zprocessing_utilsrZtokenization_utils_baserrrrrrs