
All you have to care is b=c and you are done:
m1: [a x b], m2: [c x d]
m1 is [a x b] which is [batch size x in features]
m2 is [c x d] which is [in features x out features]
本文深入讲解了矩阵乘法的基本原理,特别关注于如何通过理解矩阵的维度来简化运算过程,如将 [batchsize x infeatures] 的矩阵与 [infeatures x outfeatures] 的矩阵相乘。

All you have to care is b=c and you are done:
m1: [a x b], m2: [c x d]
m1 is [a x b] which is [batch size x in features]
m2 is [c x d] which is [in features x out features]
1312
9万+

被折叠的 条评论
为什么被折叠?