S^(hdZddlmZmZddlmZddlmZmZm Z m Z ddl m Z m Z mZGdded ZGd d eZd gZy )z& Image/Text processor class for ALIGN )ListUnion) ImageInput)ProcessingKwargsProcessorMixinUnpack!_validate_images_text_input_order) BatchEncodingPreTokenizedInput TextInputceZdZddddiZy)AlignProcessorKwargs text_kwargs max_length@)paddingrN)__name__ __module__ __qualname__ _defaultsh/var/www/skyplay_api_hub/venv/lib/python3.12/site-packages/transformers/models/align/processing_align.pyrrs # IrrF)totalc eZdZdZddgZdZdZfdZ ddede e e e e e e fd e ed efd Zd Zd ZedZxZS)AlignProcessoray Constructs an ALIGN processor which wraps [`EfficientNetImageProcessor`] and [`BertTokenizer`]/[`BertTokenizerFast`] into a single processor that interits both the image processor and tokenizer functionalities. See the [`~AlignProcessor.__call__`] and [`~OwlViTProcessor.decode`] for more information. The preferred way of passing kwargs is as a dictionary per modality, see usage example below. ```python from transformers import AlignProcessor from PIL import Image model_id = "kakaobrain/align-base" processor = AlignProcessor.from_pretrained(model_id) processor( images=your_pil_image, text=["What is that?"], images_kwargs = {"crop_size": {"height": 224, "width": 224}}, text_kwargs = {"padding": "do_not_pad"}, common_kwargs = {"return_tensors": "pt"}, ) ``` Args: image_processor ([`EfficientNetImageProcessor`]): The image processor is a required input. tokenizer ([`BertTokenizer`, `BertTokenizerFast`]): The tokenizer is a required input. image_processor tokenizerEfficientNetImageProcessor) BertTokenizerBertTokenizerFastc&t|||yN)super__init__)selfrr __class__s rr&zAlignProcessor.__init__Fs )4rimagestextkwargsreturnc | | tdt||\}}|jtfd|jj i|}||j|fi|d}||j |fi|d}d|dvr|djdd} ||jd<|S|Sttd i S) a Main method to prepare text(s) and image(s) to be fed as input to the model. This method forwards the `text` arguments to BertTokenizerFast's [`~BertTokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `images` arguments to EfficientNetImageProcessor's [`~EfficientNetImageProcessor.__call__`] if `images` is not `None`. Please refer to the docstring of the above two methods for more information. Args: 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. text (`str`, `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). 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`. Nz'You must specify either text or images.tokenizer_init_kwargsr images_kwargsreturn_tensors common_kwargs pixel_values)data tensor_typer) ValueErrorr _merge_kwargsrr init_kwargsrpopr2r dict) r'r)r*audiovideosr+ output_kwargsencodingimage_featuresr0s r__call__zAlignProcessor.__call__IsL rWsH%kkRR+5zX^zXz  r