Get a single or set of datasets.

Jitter the input box args: box - input bounding box (cx, cy, w, h) (4, ) mode - string 'template' or 'search' indicating template

target: (4, )

get detection results

Object pixel counts, grouped by object

Get parameters.

Compute cost based on IoU :type atlbrs: list[tlbr] | np.ndarray :type atlbrs: list[tlbr] | np.ndarray :rtype ious np.ndarray

Image reading using jpeg4py https://github.com/ajkxyz/jpeg4py

L2 loss. Args: pred (torch.Tensor): The prediction. target (torch.Tensor): The learning target of the prediction. Returns:

mask_feats: (1, 8, H//8, W//8), mask_feat_stride=8, mask_head_params: (N, 169), instance_locations: (N, 2), instance_fpn_levels: (N,

Test model with multiple gpus. This method tests model with multiple gpus and collects the results under two different modes: gpu and cpu mod

Single class NMS implemented in Numpy.

All objects in the sequence

Prepare results dict for pipeline.

Preprocesses data for utils.CLEAR_MOT_M. Returns a subset of the predictions.

Project state distribution to measurement space. Parameters ---------- mean : ndarray The state's mean vector (8

Random a color according to the input seed.

Run tracker on sequence. args: seq: Sequence to run the tracker on. visualization: Set visualization flag (None means

Extracts a square crop centered at target_bb box, of area search_area_factor^2 times target_bb area args: im - cv image target_b

From a segmentation, compute a binary boundary map with 1 pixel wide boundaries. The boundary pixels are offset by 1/2 pixel towards the

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

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

args: transform - The set of transformations to be applied on the images. Used only if template_transform or

Args: size (int): the total number of data of the underlying dataset to sample from shuffle (bool): whether to shuffl

Args: dataset(Dataset) : Pytorch dataset object. img_size (tuple): mosaic (bool): enable mosaic augmenta