sg>dZddlZddlmZddlmZGddeZy)z% Image/Text processor class for CLIP N)ProcessorMixin) BatchEncodingcxeZdZdZddgZdZdZd fd ZddZdZ d Z e d Z e d Z e d ZxZS) 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 tokenizerCLIPImageProcessor) CLIPTokenizerCLIPTokenizerFastc d}d|vr+tjdt|jd}||n|}| t d| t dt |||y)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__)selfrr kwargsr __class__s [/var/www/html/venv/lib/python3.12/site-packages/transformers/models/clip/processing_clip.pyrzCLIPProcessor.__init__+sw  & ( MM  !' +> ? -<-H/N_  "HI I  AB B )4c ii}}|rx|jDcic]!\}}||jjvs||#}}}|jDcic]!\}}||jjvs||#}}}| | td||j|fd|i|} ||j|fd|i|} || j  d<| S| St tdi |Scc}}wcc}}w)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 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`. z?You have to specify either text or images. Both cannot be none.return_tensors pixel_values)data tensor_type)itemsr_valid_processor_keysrr rrdict) rtextimagesrrtokenizer_kwargsimage_processor_kwargskvencodingimage_featuress r__call__zCLIPProcessor.__call__=s*D46r0 17wA1DL`L`LvLvCv1w w!'&A18L8L8b8b3b1& "& ^M]^H  1T11&rr[qrN   2'5'B'BH^ $O  O d&<^&<.Y Y) x&s C+C+ C17C1c:|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_decoderargsrs rr.zCLIPProcessor.batch_decodews +t~~**D;F;;rc:|jj|i|S)z This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r decoder/s rr2zCLIPProcessor.decode~s %t~~$$d5f55rc|jj}|jj}ttj ||zS)N)r model_input_namesrlistr#fromkeys)rtokenizer_input_namesimage_processor_input_namess rr4zCLIPProcessor.model_input_namess? $ @ @&*&:&:&L&L#DMM"7:U"UVWWrcNtjdt|jS)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)rrrimage_processor_classrs rfeature_extractor_classz%CLIPProcessor.feature_extractor_classs" u  )))rcNtjdt|jS)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)rrrrr;s rrzCLIPProcessor.feature_extractors" i  ###r)NN)NNN)__name__ __module__ __qualname____doc__ attributesr:tokenizer_classrr,r.r2propertyr4r<r __classcell__)rs@rrrss $[1J0rHs#.4@$N@$r