Match ground-truth boxes to a set of multi-level anchors. Args: gt_boxes: Ground-truth boxes from instances of an image.

Match proposals with groundtruth using the matcher at the given stage. Label the proposals as foreground or background based on the m

For untracked previous instances, under certain condition, still keep them in tracking and merge with the current instances.

Parse iterable values in the string. All elements inside '()' or '[]' are treated as iterable values. Args: val (str): V

Paste a list of masks that are of various resolutions (e.g., 28 x 28) into an image. The location, height, and width for pasting each mask is

Enhance relative import statements in config files, so that they: 1. locate files purely based on relative location, regardless of packages.

Post-process the output boxes for TensorMask. The input images are often resized when entering an object detector. As a result, we often

Substitute base variable placehoders to string, so that parsing would work.

Produce batches of data from images Args: images_and_categories (List[Tuple[torch.Tensor, Optional[str]]]): li

Method to get labels and DensePose results from an instance Args: instance (Instances): an instance of `DensePoseChartPr

Method to get labels and DensePose results from an instance Args: instance (Instances): an instance of `DensePoseEmbeddi

Convert DensePose predictor output to segmentation annotation - tensors of size (256, 256) and type `int64`. Args:

Before each uodate call, reset fields first

roundrobin('ABC', 'D', 'EF') --> A D E B F C

Args: features (list[Tensor]): #lvl input features to ROIHeads proposals (list[Instances]): #image Instances, with th

Sample DensPoseDataRelative from estimation results

Produce a random pair of different mesh names Return: tuple(str, str): a pair of different mesh names

Args: Same as in :meth:`__init__()`. Returns: fig (matplotlib.pyplot.figure): top level container for all th

Substitute variable strings to their actual values.

Get COCO API "tasks" (i.e. iou_type) from COCO-format predictions.