get rand indices according to mask. Args: mask (torch.Tensor): Shape: (N, L) 0 indicates the positions that we can sample, 1 other

Sinusoid position encoding table

Get the grayscale for the input images. The channels of images should be in order BGR. Args: images (tensor): the input images fo

Compute pairwise intersection areas between boxes. Args: boxes1: a numpy array with shape [N, 4] holding N boxes boxes2: a numpy array with

Compute pairwise intersection areas between masks. Args: masks1: a numpy array with shape [N, height, width] holding N masks. Masks value

Loads label map proto. Args: path: path to StringIntLabelMap proto text file. Returns: a StringIntLabelMapProto

The values in a will override values in b. Args: a (dict): source dict. b (dict): target dict. Returns: dict. recursively me

RandAugment: Practical automated data augmentation... - https://arxiv.org/abs/1909.13719 Create a RandAugment transform :param config_st

Loads boxes and class labels from a CSV file in the AVA format. CSV file format described at https://research.google.com/ava/download.html.

Loads boxes and class labels from a CSV file in the AVA format. CSV file format described at https://research.google.com/ava/download.html.

Args: input_dict (dict): all the values will be reduced average (bool): whether to do average or sum Reduce the values in the

Sort boxes and associated fields according to a scalar field. A common use case is reordering the boxes according to descending scores. Args:

Perform spatial sampling on the given video frames. If spatial_idx is -1, perform random scale, random crop, and random flip on the given

Normalize a given tensor by subtracting the mean and dividing the std. Args: tensor (tensor): tensor to normalize. mean (tens

Performs invalid character removal and whitespace cleanup on text.

Compute CorLoc score for object detection result. Args: detected_boxes: A float numpy array of shape [N, 4], representing N regio

Compute CorLoc score for a single class. Args: detected_boxes: A numpy array of shape [N, 4] representing detected box coordinate

Labels true/false positives of detections of an image across all classes. Args: detected_boxes: A float numpy array of shape [N, 4], repres

Labels boxes detected with the same class from the same image as tp/fp. Args: detected_boxes: A numpy array of shape [N, 4] representing de

Computes overlaps and scores between detected and groudntruth boxes. Args: detected_boxes: A numpy array of shape [N, 4] representing detec

Computes overlaps and scores between detected and groudntruth masks. Args: detected_boxes: A numpy array of shape [N, 4] representing detec

Checks whether CP is the codepoint of a CJK character.

Check whether dataset fullfills the format of N*[ymin, xmin, ymax, xmin]. Args: data: a numpy array of shape [N, 4] representing box coordi

Removes entries with invalid boxes. A box is invalid if either its xmax is smaller than its xmin, or its ymax is smaller than its ymin.

Splits punctuation on a piece of text.

Adds whitespace around any CJK character.

Update grouth truth statitistics. 1. Difficult boxes are ignored when counting the number of ground truth instances as done in Pascal VOC dev

Checks if a label map is valid. Args: label_map: StringIntLabelMap to validate. Raises: ValueError: if label map is invalid.