Get geometric center of all keypoints

Get geometric center of all keypoints

Get geometric center of all keypoints

Set up environment.

Set up slurm environment.

Method to be overridden by implementations. Args: similarity_matrix: Float tensor of shape [N, M] with pairwise similarity

Selects top-k predictions. Post-proc code adapted from Tensorflow version at: https://github.com/google/automl/tree/master/efficientdet and o

Register a module. Args: module (:obj:`nn.Module`): Module to be registered.

Rescoring mechanism gaussian or linear. Args: overlap: calculated ious scores: target scores. thr: retain oks overlap < th

return (b, r, g) tuple

Start a new tracklet

Start a new tracklet

Add field to box list. This method can be used to add related box data such as weights/labels, etc. Args: field: a strin

Parse arguements to the detect module

Parse arguements to the detect module

Parse arguements to the detect module

Assign classification and regression targets to each anchor. For a given set of anchors and groundtruth detections, match anchors to

Applies a batch of inverse kinematics transfoirm to the joints Parameters ---------- pose_skeleton : torch.tensor BxNx3 Loca

Applies a batch of inverse kinematics transfoirm to the joints Parameters ---------- pose_skeleton : torch.tensor BxNx3 Loca

Calculates the rotation matrices for a batch of rotation vectors Parameters ---------- rot_vecs: numpy.ndarray Nx3

Returns the IoU of two bounding boxes

Returns the IoU of two bounding boxes

Returns the IoU of two bounding boxes

BiFPN config with fast weighted sum.

BiFPN config with fast weighted sum.

Create a ResNet instance from config. Returns: ResNet: a :class:`ResNet` instance.

returns nT, nCorrect, tx, ty, tw, th, tconf, tcls

Detect bboxs in one image Input: 'str', full path of image Output: '[{"category_id":1,"score":float,"bbox":[x,y,w,h],"image_i

Computes matrix of pairwise similarity between BoxLists. This op (to be overridden) computes a measure of pairwise similarity between

Compute the average precision, given the recall and precision curves. Code originally from https://github.com/rbgirshick/py-faster-rcnn. #

Compute the average precision, given the recall and precision curves. Code originally from https://github.com/rbgirshick/py-faster-rcnn. # Ar

Compute the average precision, given the recall and precision curves. Code originally from https://github.com/rbgirshick/py-faster-rcnn. # Ar

Constructs module list of layer blocks from module configuration in module_defs

Crop bbox from image by Affinetransform. Parameters ---------- img: torch.Tensor A tensor with shape: `(3, H, W)`. bbox: list

Crop bbox from image by Affinetransform. Parameters ---------- img: torch.Tensor A tensor with shape: `(3, H, W)`. bbox: list

Crop bbox from image by Affinetransform. Parameters ---------- img: torch.Tensor A tensor with shape: `(3, H, W)`. bbox: list

Crop bbox from image by Affinetransform. Parameters ---------- img: torch.Tensor A tensor with shape: `(3, H, W)`. bbox: list

Transforms relative regression coordinates to absolute positions. Network predictions are normalized and relative to a given anchor; this rev

:param: delta_map, shape (nB, nA, nGh, nGw, 4) :param: anchors, shape (nA,4)

Returns a default detection configs.

Get list of macros to define for op

:param tracks: list[STrack] :param detections: list[BaseTrack] :param metric: :return: cost_matrix np.ndarray