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

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

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

Apply func recursively to all DictConfig in cfg.

Accumulate instances data for one image Args: instances_one_image (Instances): instances data to accumulate

Accumulate per image evaluation results and store the result in self.eval :param p: input params for evaluation :return: None

Add config for additional category-related dataset options - category whitelisting - category mapping

Add config for densepose head.

Add configuration options for Continuous Surface Embeddings (CSE)

Augment `proposals` with `gt`. Args: Same as `add_ground_truth_to_proposals`, but with gt and proposals per image. Retu

Add config for HRNet backbone.

Adjusts the compatibility of widths, bottlenecks, and groups.

Called after each iteration.

Match names between the two state-dict, and returns a new chkpt_state_dict with names converted to match model_state_dict with heuristics. Th

Use ``T.AugmentationList(augmentations)(inputs)`` instead.

Equivalent of ``AugmentationList(augmentations)(self)``

img should be a numpy array, formatted as Height * Width * Nchannels

Computes area of the mask. Only works with Polygons, using the shoelace formula: https://stackoverflow.com/questions/24467972

Returns all the metadata as a dict. Note that modifications to the returned dict will not reflect on the Metadata object.

A function to assemble caffe2 model's outputs (i.e. Dict[str, Tensor]) to detectron2's format (i.e. list of Instances instance). This onl

Map each box in `box_lists` to a feature map level index and return the assignment vector. Args: box_lists (list[Boxes] | list[R

Based on IoU for each pair of bbox, assign the associated value in cost matrix Args: cost_matrix: np.ndarray, initialize

When the config is defined for certain number of workers (according to ``cfg.SOLVER.REFERENCE_WORLD_SIZE``) that's different from the

Called before each iteration.

Called before the first iteration.

Args: proposal_boxes/gt_boxes are tensors with the same shape (R, 4 or 5). pred_deltas has shape (R, 4 or 5), or (R,

Build dataset that provides data to bootstrap on Args: dataset_name (str): Name of the dataset, needs to have associated metadata

Build DensePose data filter which selects data for training Args: cfg (CfgNode): configuration options Return: Callable

Build DensePose head based on configurations options Args: cfg (CfgNode): configuration options input_channels (int): input

Build DensePose loss based on configurations options Args: cfg (CfgNode): configuration options Return: An instance of D

Create an instance of DensePose predictor based on configuration options. Args: cfg (CfgNode): configuration options input_c

Similar to `build_detection_train_loader`, with default batch size = 1, and sampler = :class:`InferenceSampler`. This sampler coordinates all

Similar to `build_detection_train_loader`. But this function uses the given `dataset_name` argument (instead of the names in cfg), and us

Build a dataloader for object detection with some default features. Args: dataset (list or torch.utils.data.Dataset): a list of data

A data loader is created in a way similar to that of Detectron2. The main differences are: - it allows to combine datasets with differen

Returns: DatasetEvaluator or None It is not implemented by default.