摘要: 在BNN中,往往训练阶段较为复杂,而inference phase is simple. So how can we build a layer with complex training progress and simple inference algorithm? n1 = nn.Linear 阅读全文
posted @ 2020-09-16 22:50 LoveGood_luna 阅读(217) 评论(0) 推荐(0)
摘要: 今天看到一个代码: state_actions = { 'Init': init, 'Win': lambda: not_game('Win'), 'Gameover': lambda: not_game('Gameover'), 'Game': game } 但是我写的时候就直接: state_a 阅读全文
posted @ 2020-09-14 22:46 LoveGood_luna 阅读(197) 评论(0) 推荐(0)