o Zh`@s6dZddlmZddlmZGdddeZdgZdS)z Processor class for TVP. )ProcessorMixin) BatchEncodingcs`eZdZdZddgZdZdZdfdd Zdd d Zd d Z d dZ ddZ e ddZ ZS) TvpProcessora Constructs an TVP processor which wraps a TVP image processor and a Bert tokenizer into a single processor. [`TvpProcessor`] offers all the functionalities of [`TvpImageProcessor`] and [`BertTokenizerFast`]. See the [`~TvpProcessor.__call__`] and [`~TvpProcessor.decode`] for more information. Args: image_processor ([`TvpImageProcessor`], *optional*): The image processor is a required input. tokenizer ([`BertTokenizerFast`], *optional*): The tokenizer is a required input. image_processor tokenizerZTvpImageProcessor)Z BertTokenizerZBertTokenizerFastNc s2|durtd|durtdt||dS)Nz)You need to specify an `image_processor`.z"You need to specify a `tokenizer`.) ValueErrorsuper__init__)selfrrkwargs __class__U/var/www/auris/lib/python3.10/site-packages/transformers/models/tvp/processing_tvp.pyr )s zTvpProcessor.__init__c Ks|dd}|dur|durtdi}|dur.|jj|fdd|d|dd|}|||durB|j|fd|i|}||t||d S) a Main method to prepare for the model one or several sequences(s) and image(s). This method forwards the `text` and `kwargs` arguments to BertTokenizerFast's [`~BertTokenizerFast.__call__`] if `text` is not `None` to encode the text. To prepare the image(s), this method forwards the `videos` and `kwargs` arguments to TvpImageProcessor's [`~TvpImageProcessor.__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`. max_text_lengthNz?You have to specify either text or videos. Both cannot be none.T max_lengthF)Z truncationpaddingrZpad_to_max_lengthreturn_tensorsZreturn_token_type_idsr)dataZ tensor_type)poprrZbatch_encode_plusupdaterr) r textZvideosrr rencodingZ textual_inputZimage_featuresrrr__call__1s, %   zTvpProcessor.__call__cO|jj|i|S)z This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring of this method for more information. )r batch_decoder argsr rrrrozTvpProcessor.batch_decodecOr)z This method forwards all its arguments to BertTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of this method for more information. )rdecoderrrrrvrzTvpProcessor.decodecCs>t|dd|dt|dd|d}}||fS)a Compute the time of the video. Args: logits (`torch.Tensor`): The logits output of TvpForVideoGrounding. video_durations (`float`): The video's duration. Returns: start (`float`): The start time of the video. end (`float`): The end time of the video. )roundtolist)r ZlogitsZvideo_durationsstartendrrrpost_process_video_grounding}sz)TvpProcessor.post_process_video_groundingcCs"|jj}|jj}tt||S)N)rmodel_input_namesrlistdictfromkeys)r Ztokenizer_input_namesZimage_processor_input_namesrrrr'szTvpProcessor.model_input_names)NN)NNN)__name__ __module__ __qualname____doc__ attributesZimage_processor_classZtokenizer_classr rrrr&propertyr' __classcell__rrr rrs  >rN)r.Zprocessing_utilsrZtokenization_utils_baserr__all__rrrrs