问题描述
我在图形中有一组MxM 对称矩阵变量,我想对其值进行优化.
I have a set of MxM symmetric matrix Variables in a graph whose values I'd like to optimize.
有没有办法执行对称条件?
我曾考虑过要在损失函数中添加一个术语以强制执行,但这似乎很尴尬和round回.我希望的是类似tf.matmul(A,B,symmA=True)
的东西其中仅会使用和学习A的三角形部分.也许像tf.upperTriangularToFull(A)
这样的东西会从三角形部分创建密集的矩阵.
I've thought about adding a term to the loss function to enforce it, but this seems awkward and roundabout. What I'd hoped for is something like tf.matmul(A,B,symmA=True)
where only a triangular portion of A would be used and learned. Or maybe something like tf.upperTriangularToFull(A)
which would create a dense matrix from a triangular part.
推荐答案
如果您symA = 0.5 * (A + tf.transpose(A))
怎么办?它效率低下,但至少是对称的.
What if you do symA = 0.5 * (A + tf.transpose(A))
? It is inefficient but at least it's symmetric.
这篇关于如何迫使张量流张量对称?的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!