a ½ Àh“ã@s>dZddlZddlmZddlmZGdd„deƒZdgZdS)z% Image/Text processor class for CLIP éNé)ÚProcessorMixin)Ú BatchEncodingcsTeZdZdZddgZdZdZd‡fdd„ Zdd d „Ze d d „ƒZ e d d„ƒZ ‡Z S)Ú 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 ([`AutoTokenizer`], *optional*): The tokenizer is a required input. Úimage_processorÚ tokenizer)ZCLIPImageProcessorZCLIPImageProcessorFastZ AutoTokenizerNc sdd}d|vr"t dt¡| d¡}|dur.|n|}|durBtdƒ‚|durRtdƒ‚tƒ ||¡dS)NÚfeature_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`.)ÚwarningsÚwarnÚ FutureWarningÚpopÚ ValueErrorÚsuperÚ__init__)ÚselfrrÚkwargsr©Ú __class__©úd/var/www/html/assistant/venv/lib/python3.9/site-packages/transformers/models/clip/processing_clip.pyr+sý zCLIPProcessor.__init__c  sÒii}}|r:‡fdd„| ¡Dƒ}‡fdd„| ¡Dƒ}|durR|durRtdƒ‚|durpˆj|fd|i|¤Ž}|durŽˆj|fd|i|¤Ž}|dur¬|dur¬|j|d<|S|dur¸|Sttfi|¤Ž|dSdS) aÑ 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|]\}}|ˆjjvr||“qSr©rZ_valid_processor_keys©Ú.0ÚkÚv©rrrÚ aóz*CLIPProcessor.__call__..cs"i|]\}}|ˆjjvr||“qSrrrrrrrbsNz?You have to specify either text or images. Both cannot be none.Úreturn_tensorsÚ pixel_values)ÚdataZ tensor_type)Úitemsr rrrrÚdict) rÚtextZimagesrrZtokenizer_kwargsZimage_processor_kwargsÚencodingZimage_featuresrrrÚ__call__=s$"  ÿ zCLIPProcessor.__call__cCst dt¡|jS)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)r r r Úimage_processor_classrrrrÚfeature_extractor_classws þz%CLIPProcessor.feature_extractor_classcCst dt¡|jS)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)r r r rrrrrrs þzCLIPProcessor.feature_extractor)NN)NNN) Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú attributesr&Ztokenizer_classrr%Úpropertyr'rÚ __classcell__rrrrrs  : r)r+r Zprocessing_utilsrZtokenization_utils_baserrÚ__all__rrrrÚs   o