o Zh&@s>dZddlZddlmZddlmZGdddeZdgZdS)z% Image/Text processor class for CLIP N)ProcessorMixin) BatchEncodingcspeZdZdZddgZdZdZdfdd Zdd d Zd d Z d dZ e ddZ e ddZ e ddZZS) CLIPProcessora! Constructs a CLIP processor which wraps a CLIP image processor and a CLIP tokenizer into a single processor. [`CLIPProcessor`] offers all the functionalities of [`CLIPImageProcessor`] and [`CLIPTokenizerFast`]. See the [`~CLIPProcessor.__call__`] and [`~CLIPProcessor.decode`] for more information. Args: image_processor ([`CLIPImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`CLIPTokenizerFast`], *optional*): The tokenizer is a required input. image_processor tokenizer)ZCLIPImageProcessorZCLIPImageProcessorFast)Z CLIPTokenizerZCLIPTokenizerFastNc sdd}d|vrtdt|d}|dur|n|}|dur!td|dur)tdt||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__W/var/www/auris/lib/python3.10/site-packages/transformers/models/clip/processing_clip.pyr+s zCLIPProcessor.__init__c  sii}}|rfdd|D}fdd|D}|dur)|dur)td|dur8j|fd|i|}|durGj|fd|i|}|durV|durV|j|d<|S|dur\|Sttd i||dS) 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 CLIPTokenizerFast's [`~CLIPTokenizerFast.__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 docstring 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`. cs"i|] \}}|jjvr||qSrrZ_valid_processor_keys.0kvrrr as"z*CLIPProcessor.__call__..cs"i|] \}}|jjvr||qSrrrrrrrbsNz?You have to specify either text or images. Both cannot be none.return_tensors pixel_values)dataZ tensor_typer)itemsr rrrrdict) rtextZimagesrrZtokenizer_kwargsZimage_processor_kwargsencodingZimage_featuresrrr__call__=s$ "  zCLIPProcessor.__call__cO|jj|i|S)z This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoderargsrrrrr&wzCLIPProcessor.batch_decodecOr%)z This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoder'rrrr*~r)zCLIPProcessor.decodecCs"|jj}|jj}tt||S)N)rmodel_input_namesrlistr!fromkeys)rZtokenizer_input_namesZimage_processor_input_namesrrrr+szCLIPProcessor.model_input_namescCtdt|jS)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)r r r image_processor_classrrrrfeature_extractor_class z%CLIPProcessor.feature_extractor_classcCr.)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)r r r rrrrrrr1zCLIPProcessor.feature_extractor)NN)NNN)__name__ __module__ __qualname____doc__ attributesr/Ztokenizer_classrr$r&r*propertyr+r0r __classcell__rrrrrs  :  r)r5r Zprocessing_utilsrZtokenization_utils_baserr__all__rrrrs