Creates a specified YOLOv5 model Arguments: name (str): name of model, i.e. 'yolov5s' pretrained (bool): load pretrained weights

Runs Non-Maximum Suppression (NMS) on inference results Returns: list of detections, on (n,6) tensor per image [xyxy, conf, cls]

根据检测的结果，寻找最佳射击坐标 :param detections: 检测结果 :return: 最佳射击坐标

增量式PID控制

Decorator to make all processes in distributed training wait for each local_master to do something.

返回中心坐标; :param p: [lx,ly,w,h]->[左上x坐标，左上y坐标] :return: [x,y]

Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Arguments:

两点间距离 :param a:a点 (xa,ya) :param b: b点(xb,yb) :return: sqrt((xa-xb)**2 + (yb-ya)**2)

截取游戏中要检测区域的图片 :return: (h,w,c)

Compute the average precision, given the recall and precision curves. Source: https://github.com/rafaelpadilla/Object-Detection-Metrics. # Ar

Compute the average precision, given the recall and precision curves # Arguments recall: The recall curve (list) precision: Th