2642机器学习简单derivationshort
BatchNorm Running Mean Update 13
题目
A BatchNorm layer updates its running mean by mu_new = m mu_old + (1-m) mu_batch. What does this formula mean operationally?
解题计时
0:00
提交作答时记录，用于后续平均用时统计。
题目
A BatchNorm layer updates its running mean by mu_new = m mu_old + (1-m) mu_batch. What does this formula mean operationally?
解题计时
0:00
提交作答时记录，用于后续平均用时统计。