Why is gradient orthogonaly projected with 0_n matrix?

[dcwil]

In lines:

spdnet/spdnet/optimizer.py

Lines 37 to 39 in 2a15e90

	p.data.fill_(0)
	trans = orthogonal_projection(p.grad.data, p.data)
	p.grad.data.fill_(0).add_(trans)

Weight matrix (p.data) is set to 0 before computing the orthogonal projection with it's gradient, why is this the case?

[a912289748]

而且你这个学习率为什么没有加上