Computes matches among row and column indices and returns the result. Computes matches among the row and column indices based on the similari

Returns column indices that are matched. Returns: column_indices: int32 tensor of shape [K] with column indices.

Converts a matplotlib figure to a RGB frame after updating the canvas. Modified from https://github.com/Zulko/moviepy/blob/master/moviepy/vid

Dispatch to either CPU or GPU NMS implementations. The input can be either a torch tensor or numpy array. GPU NMS will be used if the input i

Get optional list of compiler flags to forward to nvcc when building CUDA sources

OKS NMS implementations. Args: kpts_db: keypoints. thr: Retain overlap < thr. sigmas: standard deviation of keypoint label

Update members while disallowing new keys.

Takes a configuration file Returns a list of blocks. Each blocks describes a block in the neural network to be built. Block is repre

parse from a string in format 'x=a,y=2' and return the dict.

Parses the yolo-v3 layer configuration file and returns module definitions

Parametric Pose NMS algorithm bboxes: bbox locations list (n, 4) bbox_scores: bbox scores list (n, 1) bbox_ids: bbox

Parametric Pose NMS algorithm bboxes: bbox locations list (n, 4) bbox_scores: bbox scores list (n, 1) bbox_ids: bbox

Render the mesh under camera coordinates vertices: (N_v, 3), vertices of mesh faces: (N_f, 3), faces of mesh translation: (3, ), translat

Retrieve a module class from config dict. Args: cfg (dict): Config dict. It should at least contain the key "type". registry (:ob

This function is borrowed from https://github.com/kornia/kornia Convert 3x4 rotation matrix to 4d quaternion vector This algorithm is b

Convert quaternion coefficients to rotation matrix. Args: Rotation matrix corresponding to the quaternion -- size = [B, 3, 3] Returns:

set state in optimizer to a device. move to cpu if device_id==None :param state: optimizer.state :param device_id: None or a number :

Soft OKS NMS implementations. Args: kpts_db thr: retain oks overlap < thr. max_dets: max number of detections to keep.

Convert a ``PIL Image`` or ``numpy.ndarray`` to tensor. See ``ToTensor`` for more details. Args: pic (PIL Image or numpy.ndarray): I

Creates a batch of transformation matrices Args: - R: Bx3x3 array of a batch of rotation matrices - t: Bx3x1 array of

Returns column indices that do not match any row. The indices returned by this op are always sorted in increasing order. Returns:

Run Kalman filter correction step. Parameters ---------- mean : ndarray The predicted state's mean vector (8

Run Kalman filter correction step. Parameters ---------- mean : ndarray The predicted state's mean vector (8

Update members while allowing new keys.

frame: frame image im_res: im_res of predictions format: coco or mpii return rendered image

frame: frame image im_res: result dict smpl_output: predictions return rendered image

frame: frame image im_res: result dict smpl_output: predictions return rendered image