Encode a box list relative to an anchor collection. Args: boxes: BoxList holding N boxes to be encoded anchors: BoxList o

Vectorized, approximated, fast NMS, adopted from YOLACT: https://github.com/dbolya/yolact/blob/master/layers/functions/detection.py Th

Flip thetas. Parameters ---------- thetas : numpy.ndarray Joints in shape (num_thetas, 3) theta_pairs : list List of

Compute gating distance between state distribution and measurements. A suitable distance threshold can be obtained from `chi2inv95`. If

Generates detections with RetinaNet model outputs and anchors. Args: cls_outputs: a torch tensor with shape [N, 1], which has the highest

Returns all fields.

:param cls_feat: [1, rsize*rsize, H, W] :param rois: numpy array [N, 4] ( x1, y1, x2, y2) :return: [N], [N]

Get the default config for EfficientDet based on model name.

Performs Linear Blend Skinning with the given shape and skeleton joints Parameters ---------- betas : torch.tensor BxNB

Inverse pass for the SMPL model Parameters ---------- pose_skeleton: torch.tensor, optional, shape Bx(J*3)

Returns boolean column indicator where True means the column is ignored. Returns: column_indicator: boolean vector which is True

Returns column indices that are ignored (neither Matched nor Unmatched). The indices returned by this op are always sorted in increasing orde

Get list of include paths, relative to root of package. NOTE: the path should be elative to root of package. Otherwise,

Initializes model with pretrained weights. Layers that don't match with pretrained layers in name or size are kept unchanged.

Create track from unassociated measurement. Parameters ---------- measurement : ndarray Bounding box coordin

Create track from unassociated measurement. Parameters ---------- measurement : ndarray Bounding box coordin

We resize both tensors to [A,B,2] without new malloc: [A,2] -> [A,1,2] -> [A,B,2] [B,2] -> [1,B,2] -> [A,B,2] Then we compute the area

Compute pairwise intersection areas between boxes. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList holding M boxes

Computes pairwise intersection-over-union between box collections. Args: boxlist1: BoxList holding N boxes boxlist2: BoxList hold

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

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

Compute the jaccard overlap of two sets of boxes. The jaccard overlap is simply the intersection over union of two boxes. Here we operate on

Labels anchors with ground truth inputs. Args: gt_boxes: A float tensor with shape [N, 4] representing groundtruth boxes.

Performs Linear Blend Skinning with the given shape and pose parameters Parameters ---------- betas : torch.tensor BxNB

r"""Loads checkpoint. ``UnicodeDecodeError`` can be well handled, which means python2-saved files can be read from python3. Args:

r"""Loads pretrianed weights to model. Features:: - Incompatible layers (unmatched in name or size) will be ignored. - Can au