Unpack the given archive file to the same directory. Args: path(str): The folder containing the archive. Will contain the contents.

mock online request_input for local test Returns: input to _build_sample

Map EfficientNet model name to parameter coefficients. Args: model_name (str): Model name to be queried. Returns: params_dic

use convolution layer to extract feature . Args: inputs (tensor): Input tensor. Returns: Output of the final

online returned format Args: report(antmmf.common.report.Report): Returns: format_result(dict): must

create an efficientnet model according to name. Args: model_name (str): Name of PVT model, e.g. pvt_v2_b0 weights_pat

Add gaussian noise or speckle noise to img. @param img: ndarray Input image data on range[0,255]. @param mean:float, optional

r"""Generate a square mask for the sequence. The masked positions are filled with float('-inf'). Unmasked positions are filled with float(0.0)

Get question ids that satisfy given filter conditions. default skips that filter :param imgIds (int array) : get question ids f

calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the configuration of video.

:param text_embed_l1: bsz_text, hidden :param video_embed_l1: bsz_video * n_clips, hidden :return: bsz_text, b

Return a mask that indicate whether the position is exact data or padding data. Args: nums (torch.Tensor): the length of each sequen

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

:return: bsz_text, bsz_video, num_clips: clip-level score for training bsz_text, num_clips: clip-level score for val/

:return: bsz_text, bsz_video, num_clips: clip-level score for training bsz_text, num_clips: clip-level score for val/

:return: bsz_text, bsz_video, num_clips: clip-level score for training bsz_text, num_clips: clip-level score for val/

Initializes loss and metrics for the model based ``losses`` key and ``metrics`` keys. Automatically called by antmmf internally after

Load a CNCLIP model Parameters ---------- config : name A model name listed by `_MODELS.keys()`, config : dict

Load a CLIP model Parameters ---------- name : str A model name listed by `clip.available_models()`, or the path to

:param with_ckpt: if load_model=True, load model weights if provided :param load_model: if False, only load processors :retu

Make the directory and any nonexistent parent directories (`mkdir -p`).