r"""Move internal buffers of the ExponentialMovingAverage to `device`. Args: device: like `device` argument to `torch.Tensor.t

This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.decode`]. Please refer to the docstring of thi

r"""Move internal buffers of the ExponentialMovingAverage to `device`. Args: device: like `device` argument to `torch.Tensor.t

This method forwards all its arguments to CLIPTokenizerFast's [`~PreTrainedTokenizer.batch_decode`]. Please refer to the docstring

Generates and yields batches from the reordered array. Parameters: - n (int): The size of each batch. Defaults to 1.

Restores the original order of elements from the reordered list. Parameters: - newarr (List): The reordered array.

Return the mean squared error.

Parse the JSON object, including nested JSON strings.

Tokenizes table cells

Compute the evaluation score for keypoint estimation. Args: pred_keypoints (list or np.ndarray): List or array of predic

Read video using the PyAV library. Args: video_path (str): The path to the video file. num_frm (int, optional): The max

dumps the current config as a dictionary object, as a printable format. null fields will not be printed. Used for dumping results alon

Try to cast an object as a dict.

Groups elements of an iterable based on a provided function. Parameters: - arr (Iterable): The iterable to be grouped.

Initialize weights of a linear or embedding module. :param config: The model config. :param module: The linear or embedding submodule to

Initialize weights of a linear or embedding module. :param config: The model config. :param module: The linear or embedding submodul

Initialize weights of a linear or embedding module. :param config: The model config. :param module: The linear or embedding submodul

Try to cast an object as a set.

r""" Returns the state of the ExponentialMovingAverage as a dict. This method is used by accelerate during checkpointing to save the

Converts a string representation of an iterable to a set.

Defines the operation to perform on a list of the `inst.resps` properties of `Instance` objects. Should return the list of (filtered)

Computes TEDS score between the prediction and the ground truth of a given sample

Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona

Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona

Aggregate the results of the RefCOCO evaluation task using the specified metric. Args: - results (list of dict): List of result dictiona

Aggregate the results of the screenspot evaluation task using the specified metric. Args: - results (list of dict): List of result dicti

:return: Iterable[obj] A iterable of any object, that doc_to_text can handle

:return: Iterable[obj] A iterable of any object, that doc_to_text can handle

Converts a markdown table to the corresponding html string for TEDS computation.

calculate the wups score :param pred: :param truth: :return:

Generate table of results.