sg>'^dZddlmZddlZddlmZddlmZddl m Z m Z m Z Gdd eZ y) z& Image/Text processor class for OWLv2 )ListN)ProcessorMixin) BatchEncoding)is_flax_availableis_tf_availableis_torch_availablecReZdZdZddgZdZdZfdZd dZdZ d Z d Z d Z xZ 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 &t|||y)N)super__init__)selfr r kwargs __class__s ]/var/www/html/venv/lib/python3.12/site-packages/transformers/models/owlv2/processing_owlv2.pyrzOwlv2Processor.__init__-s )4c || | td|{t|ts#t|tr+t|dts|j|f||d|g}nt|trt|dtrvg}t |Dcgc] }t |c}} |D]L}t || k7r|dg| t |z zz}|j|f||d|} |j| Nn td|dk(rRtj|D cgc]} | d c} d } tj|D cgc]} | d  c} d } n!|d k(rYtrOddl m } | j|D cgc]} | d c} d } | j|D cgc]} | d  c} d } n|d k(rWtrMddl}|j!|D cgc]} | d c} d } |j!|D cgc]} | d  c} d } ng|dk(rWt#rMddl}|j'|D cgc]} | d c} d } |j'|D cgc]} | d  c} d } n tdt)} | | d<| | d <|.t)} |j*|fd|i|j,}|| d<||j*|fd|i|}||j, d<| S||j, d<| S|| St)t/di|Scc}wcc} wcc} wcc} wcc} wcc} wcc} wcc} wcc} w)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. Both channels-first and channels-last formats are supported. 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_tensors zLInput text should be a string, a list of strings or a nested list of stringsnp input_ids)axisattention_maskjaxpt)dimtfz/Target return tensor type could not be returnedrquery_pixel_values pixel_values)data tensor_type) ValueError isinstancestrrr maxlenappend TypeErrorr concatenater jax.numpynumpyr torchcatr tensorflowstackrr r&dict)rtextimages query_imagesrrr encodingstmax_num_queriesencodingrr jnpr4r$r%image_featuress r__call__zOwlv2Processor.__call__1sH -@'OOS\,]xXk-B,]deOf !$]f1gQY(;K2L1gno!p4',>,@!IIY&Wx '<&W]^I_ !&W`+a8H5E,F+agh!i4'O,='HHI%Vh{&;%V]^H_ !#V_*`(84D+E*`gh!i!!RSS$H$-H[ !)7H% &  #$H!5!5!5"-;"?E"l .@H) *  1T11&bb[abN   2'5'B'BH^ $O  %&*<'5'B'BH^ $O  !9O d&<^&<.Y Yy'=,]0f -^1g 'X+a &W*`s6L L" L'? L,# L1 L6? L;7 M Mc:|jj|i|S)z This method forwards all its arguments to [`OwlViTImageProcessor.post_process_object_detection`]. Please refer to the docstring of this method for more information. )r post_process_object_detectionrargsrs rrDz,Owlv2Processor.post_process_object_detections# Bt##AA4R6RRrc:|jj|i|S)z This method forwards all its arguments to [`OwlViTImageProcessor.post_process_one_shot_object_detection`]. Please refer to the docstring of this method for more information. )r #post_process_image_guided_detectionrEs rrHz2Owlv2Processor.post_process_image_guided_detections$ Ht##GGXQWXXrc:|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_decoderEs rrJzOwlv2Processor.batch_decodes +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 decoderEs rrLzOwlv2Processor.decodes %t~~$$d5f55r)NNN max_lengthr)__name__ __module__ __qualname____doc__ attributesimage_processor_classtokenizer_classrrBrDrHrJrL __classcell__)rs@rr r sB $[1J1rZs,.4KKb6^b6r