g"+ndZddlZddlmZddlZddlmZddlm Z ddl m Z m Z m Z Gdd eZdS) z( Image/Text processor class for OWL-ViT N)List)ProcessorMixin) BatchEncoding)is_flax_availableis_tf_availableis_torch_availableceZdZdZddgZdZdZdfd Zdd Zd Z d Z d Z dZ dZ edZedZxZS)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 d}d|vr/tjdt|d}||n|}|t d|t dt ||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__s h/var/www/html/ai-engine/env/lib/python3.11/site-packages/transformers/models/owlvit/processing_owlvit.pyrzOwlViTProcessor.__init__.s  & ( ( M    !' +> ? ? -<-H//N_  "HII I  ABB B )44444 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,OwlViTProcessor.__call__..qs&<&<&.~s+\+\+\hH[,A+\+\+\r)axiscg|] }|d Sattention_maskr%r.s rr)z,OwlViTProcessor.__call__..s0f0f0fPX:J1K0f0f0frjaxcg|] }|d Sr,r%r.s rr)z,OwlViTProcessor.__call__..s,],],]xXk-B,],],]rcg|] }|d Sr2r%r.s rr)z,OwlViTProcessor.__call__..s1g1g1gQY(;K2L1g1g1grptcg|] }|d Sr,r%r.s rr)z,OwlViTProcessor.__call__..s&W&W&Wx '<&W&W&Wr)dimcg|] }|d Sr2r%r.s rr)z,OwlViTProcessor.__call__..s+a+a+a8H5E,F+a+a+artfcg|] }|d Sr,r%r.s rr)z,OwlViTProcessor.__call__..s%V%V%Vh{&;%V%V%Vrcg|] }|d Sr2r%r.s rr)z,OwlViTProcessor.__call__..s*`*`*`(84D+E*`*`*`rz/Target return tensor type could not be returnedr-r3r#query_pixel_values pixel_values)data tensor_typer%)r isinstancestrrr maxr&append TypeErrorr concatenater jax.numpynumpyr torchcatr tensorflowstackrr r?dict)rtextimages query_imagesr"r#r encodingsmax_num_queriesr(r/r-r3jnprJr;r>image_featuress r__call__zOwlViTProcessor.__call__@s(H rts......444444KKKKKKKKKKC$C$C$C$C$nC$C$C$C$C$r