o h'@sXdZddlmZddlZddlmZddlmZddl m Z m Z m Z Gdd d eZ dS) z& Image/Text processor class for OWLv2 )ListN)ProcessorMixin) BatchEncoding)is_flax_availableis_tf_availableis_torch_availablecsZeZdZdZddgZdZdZfddZdd d Zd dZ ddZ ddZ ddZ Z S)Owlv2Processora Constructs an Owlv2 processor which wraps [`Owlv2ImageProcessor`] 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 ([`Owlv2ImageProcessor`]): The image processor is a required input. tokenizer ([`CLIPTokenizer`, `CLIPTokenizerFast`]): The tokenizer is a required input. image_processor tokenizerOwlv2ImageProcessor) CLIPTokenizerCLIPTokenizerFastc st||dS)N)super__init__)selfr r kwargs __class__`/var/www/html/ai/venv/lib/python3.10/site-packages/transformers/models/owlv2/processing_owlv2.pyr-szOwlv2Processor.__init__N 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 cz+Owlv2Processor.__call__.. zLInput text should be a string, a list of strings or a nested list of stringsrcSg|]}|dqS input_idsrrencodingrrrrpr)axiscSr!attention_maskrr$rrrrqrjaxcSr!r"rr$rrrrvrcSr!r'rr$rrrrwrptcSr!r"rr$rrrr|r)dimcSr!r'rr$rrrr}rtfcSr!r"rr$rrrrrcSr!r'rr$rrrrrz/Target return tensor type could not be returnedr#r(rquery_pixel_values pixel_values)data tensor_typer) ValueError isinstancestrrr maxrappend TypeErrorr concatenater jax.numpynumpyrtorchcatr tensorflowstackrr r.dict)rtextimages query_imagesrrr encodingsmax_num_queriesrr%r#r(jnpr:r,r-image_featuresrrr__call__1sv% "       zOwlv2Processor.__call__cO|jj|i|S)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_detectionrargsrrrrrHz,Owlv2Processor.post_process_object_detectioncOrG)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_detectionrIrrrrLrKz2Owlv2Processor.post_process_image_guided_detectioncOrG)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_decoderIrrrrMrKzOwlv2Processor.batch_decodecOrG)z This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )r decoderIrrrrNrKzOwlv2Processor.decode)NNNrr)__name__ __module__ __qualname____doc__ attributesimage_processor_classtokenizer_classrrFrHrLrMrN __classcell__rrrrr s   qr )rRtypingrr9rprocessing_utilsrtokenization_utils_baserutilsrrrr rrrrs