Params: dets - a numpy array of detections in the format [[x1,y1,x2,y2,score],[x1,y1,x2,y2,score],...] Requires: this metho

Parse arguements to the detect module

3x3 convolution with padding

Takes a bounding box in the form [x1,y1,x2,y2] and returns z in the form [x,y,s,r] where x,y is the centre of the box and s is the scale/ar

Takes a bounding box in the centre form [x,y,s,r] and returns it in the form [x1,y1,x2,y2] where x1,y1 is the top left and x2,y2 is the bot

Assigns detections to tracked object (both represented as bounding boxes) Returns 3 lists of matches, unmatched_detections and unmatched_tra

Returns the IoU of two bounding boxes

convert a box to center,scale information required for pose transformation Parameters ---------- box : (x1, y1, x2, y2) model_image_wi

get predictions from score maps heatmaps: numpy.ndarray([batch_size, num_joints, height, width])

Returns the current bounding box estimate.

Computes IUO between two bboxes in the form [x1,y1,x2,y2]

resize image with unchanged aspect ratio using padding

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

Advances the state vector and returns the predicted bounding box estimate.

Updates the state vector with observed bbox.

https://blog.paperspace.com/how-to-implement-a-yolo-v3-object-detector-from-scratch-in-pytorch-part-4/ prediction: (B x 10647 x 85)