摘要:
一、ChatGPT基础知识 transformer机制 和RLHF 想了解Transformer原理,可参考该链接:transformer原理详解 RLHF(Reinforcement Learning from Human Feedback)是基于人类反馈来构建强化学习,使用强化学习的方法和框架, 阅读全文
摘要:
NMS Python版 def NMS(boxes,scores, thresholds): x1 = boxes[:,0] y1 = boxes[:,1] x2 = boxes[:,2] y2 = boxes[:,3] areas = (x2-x1)*(y2-y1) _,order = score 阅读全文