U 4Afn@s8dZddlZddlmZddlmZGdddeZdS)z( Image/Text processor class for CLIPSeg N)ProcessorMixin) BatchEncodingcsdeZdZdZddgZdZdZdfdd Zdd d Zd d Z d dZ e ddZ e ddZ ZS)CLIPSegProcessora. Constructs a CLIPSeg processor which wraps a CLIPSeg image processor and a CLIP tokenizer into a single processor. [`CLIPSegProcessor`] offers all the functionalities of [`ViTImageProcessor`] and [`CLIPTokenizerFast`]. See the [`~CLIPSegProcessor.__call__`] and [`~CLIPSegProcessor.decode`] for more information. Args: image_processor ([`ViTImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`CLIPTokenizerFast`], *optional*): The tokenizer is a required input. image_processor tokenizerZViTImageProcessor)Z CLIPTokenizerZCLIPTokenizerFastNc 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/clipseg/processing_clipseg.pyr+s zCLIPSegProcessor.__init__c Ks |dkr |dkr |dkr td|dk r8|dk r8td|dk rV|j|fd|i|}|dk rt|j|fd|i|}|dk r|j|fd|i|}|dk r|dk r|j|jd}|S|dk r|dk r|j|d<|S|dk r|S|dk rd|ji}|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 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 ViTImageProcessor's [`~ViTImageProcessor.__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. visual_prompt (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`): The visual prompt image or batch of images to be prepared. Each visual prompt 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`. Nz9You have to specify either text, visual prompt or images.zMYou have to specify exactly one type of prompt. Either text or visual prompt.return_tensors) pixel_valuesconditional_pixel_valuesrr)dataZ tensor_type)r rrrrdict) rtextZimagesZ visual_promptrrencodingZprompt_featuresZimage_featuresrrr__call__=s4& zCLIPSegProcessor.__call__cOs|jj||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_decoderargsrrrrrszCLIPSegProcessor.batch_decodecOs|jj||S)z This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoderrrrr!szCLIPSegProcessor.decodecCstdt|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_classs z(CLIPSegProcessor.feature_extractor_classcCstdt|jS)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)r r r rr#rrrrs z"CLIPSegProcessor.feature_extractor)NN)NNNN)__name__ __module__ __qualname____doc__ attributesr"Ztokenizer_classrrrr!propertyr$r __classcell__rrrrrs  H r)r(r Zprocessing_utilsrZtokenization_utils_baserrrrrrs