o h+@s`dZddlZddlmZddlZddlmZddlm Z ddl m Z m Z m Z Gdd d eZdS) z( Image/Text processor class for OWL-ViT N)List)ProcessorMixin) BatchEncoding)is_flax_availableis_tf_availableis_torch_availablecs|eZdZdZddgZdZdZdfdd Zdd d Zd dZ ddZ ddZ ddZ ddZ eddZeddZZS)OwlViTProcessora3 Constructs an OWL-ViT processor which wraps [`OwlViTImageProcessor`] and [`CLIPTokenizer`]/[`CLIPTokenizerFast`] into a single processor that interits both the image processor and tokenizer functionalities. See the [`~OwlViTProcessor.__call__`] and [`~OwlViTProcessor.decode`] for more information. Args: image_processor ([`OwlViTImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`CLIPTokenizer`, `CLIPTokenizerFast`], *optional*): The tokenizer is a required input. image_processor tokenizerOwlViTImageProcessor) CLIPTokenizerCLIPTokenizerFastNc 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__)selfr r kwargsr __class__b/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/owlvit/processing_owlvit.pyr.s zOwlViTProcessor.__init__ max_lengthnpcKs|dur|dur|durtd|durt|ts&t|tr4t|dts4|j|f||d|g}nCt|trst|dtrsg}tdd|D}|D]$} t| |kr`| dg|t| } |j| f||d|} || qMntd|d krt j d d|Ddd } t j d d|Ddd } nt|d krt rddl m } | j dd|Ddd } | j dd|Ddd } nN|dkrtrddl}|jdd|Ddd} |jdd|Ddd} n*|dkrtrddl}|jdd|Ddd } |jdd|Ddd } ntdt} | | d<| | d<|dur+t} |j|fd|i|j}|| d<|dur;|j|fd|i|}|durL|durL|j| d<| S|dur]|dur]|j| d<| S|dusg|duri| Sttdi||dS)a/ Main method to prepare for the model one or several text(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. 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. query_images (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`): The query image to be prepared, one query image is expected per target image to be queried. Each 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`. NzXYou have to specify at least one text or query image or image. All three cannot be none.r)paddingreturn_tensorscSsg|]}t|qSr)len).0trrr rz,OwlViTProcessor.__call__.. zLInput text should be a string, a list of strings or a nested list of stringsrcSg|]}|dqS input_idsrr"encodingrrrr$r%)axiscSr'attention_maskrr*rrrr$r%jaxcSr'r(rr*rrrr$r%cSr'r-rr*rrrr$r%ptcSr'r(rr*rrrr$r%)dimcSr'r-rr*rrrr$r%tfcSr'r(rr*rrrr$r%cSr'r-rr*rrrr$r%z/Target return tensor type could not be returnedr)r.r query_pixel_values pixel_values)data tensor_typer)r isinstancestrrr maxr!append TypeErrorr concatenater jax.numpynumpyrtorchcatr tensorflowstackrr r4dict)rtextimages query_imagesrr r encodingsmax_num_queriesr#r+r)r.jnpr?r2r3image_featuresrrr__call__@sv% "       zOwlViTProcessor.__call__cO|jj|i|S)z This method forwards all its arguments to [`OwlViTImageProcessor.post_process`]. Please refer to the docstring of this method for more information. )r post_processrargsrrrrrMzOwlViTProcessor.post_processcOrL)z This method forwards all its arguments to [`OwlViTImageProcessor.post_process_object_detection`]. Please refer to the docstring of this method for more information. )r post_process_object_detectionrNrrrrQrPz-OwlViTProcessor.post_process_object_detectioncOrL)z This method forwards all its arguments to [`OwlViTImageProcessor.post_process_one_shot_object_detection`]. Please refer to the docstring of this method for more information. )r #post_process_image_guided_detectionrNrrrrRrPz3OwlViTProcessor.post_process_image_guided_detectioncOrL)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_decoderNrrrrSrPzOwlViTProcessor.batch_decodecOrL)z This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r decoderNrrrrTrPzOwlViTProcessor.decodecCtdt|jS)Nzg`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.)rrrimage_processor_classrrrrfeature_extractor_class z'OwlViTProcessor.feature_extractor_classcCrU)Nz[`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.)rrrr rWrrrrrYz!OwlViTProcessor.feature_extractor)NN)NNNrr)__name__ __module__ __qualname____doc__ attributesrVtokenizer_classrrKrMrQrRrSrTpropertyrXr __classcell__rrrrr s   p r )r]rtypingrr>rprocessing_utilsrtokenization_utils_baserutilsrrrr rrrrs