g>'fdZddlmZddlZddlmZddlmZddl m Z m Z m Z Gdd eZ dS) z& Image/Text processor class for OWLv2 )ListN)ProcessorMixin) BatchEncoding)is_flax_availableis_tf_availableis_torch_availablecReZdZdZddgZdZdZfdZdd Zd Z d Z d Z dZ 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 Lt||dS)N)super__init__)selfr r kwargs __class__s f/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/owlv2/processing_owlv2.pyrzOwlv2Processor.__init__-s# )44444N max_lengthnpc D|||td|t|ts0t|tr.t|dts|j|f||d|g}nt|trt|dtrsg}t d|D}|D]T} t | |kr| dg|t | z zz} |j| f||d|} || Untd|dkrBtj d |Dd } tj d |Dd } n"|d krWtrIddl m } | d |Dd } | d|Dd } n|dkrUtrGddl}|d|Dd} |d|Dd} nj|dkrUt#rGddl}|d|Dd } |d|Dd } ntdt)} | | d<| | d<|(t)} |j|fd|i|j}|| d<||j|fd|i|}|| |j| d<| S|| |j| d<| S||| St)t/di||S)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_tensorsc,g|]}t|S)len).0ts r z+Owlv2Processor.__call__..bs&<&<&.os+\+\+\hH[,A+\+\+\r)axiscg|] }|d Sattention_maskrr(s rr#z+Owlv2Processor.__call__..ps0f0f0fPX:J1K0f0f0frjaxcg|] }|d Sr&rr(s rr#z+Owlv2Processor.__call__..us,],],]xXk-B,],],]rcg|] }|d Sr,rr(s rr#z+Owlv2Processor.__call__..vs1g1g1gQY(;K2L1g1g1grptcg|] }|d Sr&rr(s rr#z+Owlv2Processor.__call__..{s&W&W&Wx '<&W&W&Wr)dimcg|] }|d Sr,rr(s rr#z+Owlv2Processor.__call__..|s+a+a+a8H5E,F+a+a+artfcg|] }|d Sr&rr(s rr#z+Owlv2Processor.__call__..s%V%V%Vh{&;%V%V%Vrcg|] }|d Sr,rr(s rr#z+Owlv2Processor.__call__..s*`*`*`(84D+E*`*`*`rz/Target return tensor type could not be returnedr'r-rquery_pixel_values pixel_values)data tensor_typer) ValueError isinstancestrrr maxr append TypeErrorr concatenater jax.numpynumpyr torchcatr tensorflowstackrr r9dict)rtextimages query_imagesrrr encodingsmax_num_queriesr"r)r'r-jnprEr5r8image_featuress r__call__zOwlv2Processor.__call__1s(H rhs......444444KKKKKKKKKKb6b6b6b6b6^b6b6b6b6b6r