Visualizes predictions on frames of the input video. Args: video (cv2.VideoCapture): a :class:`VideoCapture` object, who

Save the graph as SVG format. Args: output_file (str): a SVG file inputs: optional inputs given to the model

Save the model as caffe2's protobuf format. Args: output_dir (str): the output directory to save protobuf files.

Loss re-weighting. Re-weighting the loss according to the number of samples in each class. Args: labels (numpy.ndarray):

Create configs and perform basic setups.

Performs a single optimization step. Args: closure (callable, optional): A closure that reevaluates the model and

Return `num_samples` (or fewer, if not enough found) random samples from `labels` which is a mixture of positives & negatives. It will tr

Helper function to synchronize (barrier) among all processes when using distributed training

Convert InstancesList to List[Instances]. The input `instances_list` can also be a List[Instances], in this case this method is a non

Update centroids memory.

Upgrade a config from its current version to a newer version. Args: cfg (CfgNode): to_version (int): defaults to the latest

Helper function to Accumulate() Considers the evaluation results applicable to a particular category, area range, and max_detections parameter setting

Helper function to Accumulate() Compute a precision recall curve given a sorted list of detected instances encoded in evaluations, evaluation_indices,

For each IOU threshold, greedily match each detected instance to a ground truth instance (if possible) and store the results

Sort detections from highest score to lowest, such that detection_instances[detection_sorted_indices[t]] >= detection_instances[detection_sorted_indic

Partition the ground truth objects based on whether or not to ignore them based on area

Get outputs for the selected instance(s) Args: item (int or slice or tensor): selected items

NOTE: this interface is experimental. Args: num_keypoints (int): number of keypoints to predict loss_weight

Args: box2box_transform (Box2BoxTransform/Box2BoxTransformRotated): box2box transform instance for proposal-to-de

NOTE: this interface is experimental. Args: vis_period (int): visualization period

NOTE: this interface is experimental. Args: backbone: a backbone module, must follow detectron2's backbone interface

NOTE: this interface is experimental. Args: in_features (list[str]): list of names of input features to use

Deformable convolution from :paper:`deformconv`. Arguments are similar to :class:`Conv2D`. Extra arguments: Args:

Args: cfg (CfgNode): num_gpus (int): if 0, will run on CPU

Assert that each stride is 2x times its preceding stride, i.e. "contiguous in log2".

ONNX exported network doesn't have concept of device, assign necessary device option for each op in order to make it runable on GPU runtime.

Given two lists of boxes of N ground truth boxes and M anchor boxes, compute the assignment between the two, following the assignment rules i

Batch shuffle, for making use of BatchNorm. *** Only support DistributedDataParallel (DDP) model. ***

Undo batch shuffle. *** Only support DistributedDataParallel (DDP) model. ***

Returns: bool: whether the arguments contain CfgNode and should be considered forwarded to from_config.

Compute a few centroids.

Configurations for some libraries.

Convert different format of boxes to an NxB array, where B = 4 or 5 is the box dimension.

Convert different format of masks or polygons to a tuple of masks and polygons. Returns: list[GenericMask]:

Creates gradient clipping closure to clip by value or by norm, according to the provided config.

Create an instance of predictor outputs by copying the outputs from the base predictor and initializing confidence Args:

Args: boxes (list[Tensor]): per-image predicted boxes, each of shape Ri x 4 image_sizes (list[tuple]): list of image

Update queue.

Args: masks: N, 1, H, W boxes: N, 4 img_h, img_w (int): skip_empty (bool): only paste masks within the region tha