huihui__huihui的博客

目标检测算法 https://www.cnblogs.com/MY0213/p/9858383.html https://www.cnblogs.com/MY0213/p/9460562.html faster rcnn https://blog.youkuaiyun.com/weixin_39749553/article/details/88070100 https://blog.youkuaiyun.com/weixin_43198141/article/details/90178512 https://www.cn

Batch Norm x = torch.rand(5, 3, 5, 5) #batchsize=4 RGB图像 x1 = x.permute(1, 0, 2, 3).reshape(3, -1) # 对(N, H, W)计算均值方差 mean = x1.mean(dim=1).reshape(1, 3, 1, 1) # x1.mean(dim=1)后维度为(3,) std = x1.std(dim=1, unbiased=False).reshape(1, 3, 1, 1) my_bn = (x - m