# coding=utf-8 # Copyright 2022 The HuggingFace Inc. team. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """ Image/Text processor class for XCLIP """ import warnings from ...processing_utils import ProcessorMixin from ...tokenization_utils_base import BatchEncoding class XCLIPProcessor(ProcessorMixin): r""" Constructs an X-CLIP processor which wraps a VideoMAE image processor and a CLIP tokenizer into a single processor. [`XCLIPProcessor`] offers all the functionalities of [`VideoMAEImageProcessor`] and [`CLIPTokenizerFast`]. See the [`~XCLIPProcessor.__call__`] and [`~XCLIPProcessor.decode`] for more information. Args: image_processor ([`VideoMAEImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`CLIPTokenizerFast`], *optional*): The tokenizer is a required input. """ attributes = ["image_processor", "tokenizer"] image_processor_class = "VideoMAEImageProcessor" tokenizer_class = ("CLIPTokenizer", "CLIPTokenizerFast") def __init__(self, image_processor=None, tokenizer=None, **kwargs): feature_extractor = None if "feature_extractor" in kwargs: warnings.warn( "The `feature_extractor` argument is deprecated and will be removed in v5, use `image_processor`" " instead.", FutureWarning, ) feature_extractor = kwargs.pop("feature_extractor") image_processor = image_processor if image_processor is not None else feature_extractor if image_processor is None: raise ValueError("You need to specify an `image_processor`.") if tokenizer is None: raise ValueError("You need to specify a `tokenizer`.") super().__init__(image_processor, tokenizer) self.current_processor = self.image_processor def __call__(self, text=None, videos=None, return_tensors=None, **kwargs): """ Main method to prepare for the model one or several sequences(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 `videos` and `kwargs` arguments to VideoMAEImageProcessor's [`~VideoMAEImageProcessor.__call__`] if `videos` is not `None`. Please refer to the docstring 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). videos (`List[PIL.Image.Image]`, `List[np.ndarray]`, `List[torch.Tensor]`, `List[List[PIL.Image.Image]]`, `List[List[np.ndarray]]`,: `List[List[torch.Tensor]]`): The video or batch of videos to be prepared. Each video should be a list of frames, which can be either PIL images or NumPy arrays. In case of NumPy arrays/PyTorch tensors, each frame should be of shape (H, W, C), where H and W are frame height and width, and C is a number of channels. 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 `videos` is not `None`. """ if text is None and videos is None: raise ValueError("You have to specify either text or videos. Both cannot be none.") if text is not None: encoding = self.tokenizer(text, return_tensors=return_tensors, **kwargs) if videos is not None: image_features = self.image_processor(videos, return_tensors=return_tensors, **kwargs) if text is not None and videos is not None: encoding["pixel_values"] = image_features.pixel_values return encoding elif text is not None: return encoding else: return BatchEncoding(data=dict(**image_features), tensor_type=return_tensors) def batch_decode(self, *args, **kwargs): """ This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. """ return self.tokenizer.batch_decode(*args, **kwargs) def decode(self, *args, **kwargs): """ This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. """ return self.tokenizer.decode(*args, **kwargs) @property def model_input_names(self): return ["input_ids", "attention_mask", "position_ids", "pixel_values"] @property def feature_extractor_class(self): warnings.warn( "`feature_extractor_class` is deprecated and will be removed in v5. Use `image_processor_class` instead.", FutureWarning, ) return self.image_processor_class @property def feature_extractor(self): warnings.warn( "`feature_extractor` is deprecated and will be removed in v5. Use `image_processor` instead.", FutureWarning, ) return self.image_processor __all__ = ["XCLIPProcessor"]