+ jTRt^RIHt^RIHt^RIHt]!RR]44tR.tR#)z( Image/Text processor class for CLIPSeg )ProcessorMixin) BatchEncoding)auto_docstringcJaa]tRt^toRV3Rllt]RRl4tRtVtV;t #)CLIPSegProcessorc &<\SV`W4R#)N)super__init__)selfimage_processor tokenizerkwargs __class__s&&&,o/home/luca/screen-checking/.venv/lib/python3.14/site-packages/transformers/models/clipseg/processing_clipseg.pyr CLIPSegProcessor.__init__s 4c HVfVfVf \R4hVeVe \R4hVP!VP3RVPP/VBpVeVP!V3/VR,BpVeVP !V3/VR,BpVeVP !V3/VR,BpVe!VeRXP RXP /pV#VeVeXP XR&V#VeX#VeRXP /pV#\\R /XBR7#) a visual_prompt (`PIL.Image.Image`, `np.ndarray`, `torch.Tensor`, `list[PIL.Image.Image]`, `list[np.ndarray]`, `list[torch.Tensor]`): The visual prompt image or batch of images to be prepared. Each visual prompt 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. 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`. z9You have to specify either text, visual prompt or images.zMYou have to specify exactly one type of prompt. Either text or visual prompt.tokenizer_init_kwargs text_kwargs images_kwargs pixel_valuesconditional_pixel_values)data) ValueError _merge_kwargsvalid_processor_kwargsr init_kwargsr rrdict) r textimages visual_promptr output_kwargsencodingprompt_featuresimage_featuress &&&&, r__call__CLIPSegProcessor.__call__sU" 4>4>rrN) __doc__processing_utilsrtokenization_utils_baserutilsrr__all__rrrr5s;/4#9>~9>9>x  r