Open dcwil opened 2 years ago
In lines: https://github.com/adavoudi/spdnet/blob/2a15e908634cd8db6c75ea45d9e3bd567203eccf/spdnet/optimizer.py#L37-L39
Weight matrix (p.data) is set to 0 before computing the orthogonal projection with it's gradient, why is this the case?
p.data
而且你这个学习率为什么没有加上
In lines: https://github.com/adavoudi/spdnet/blob/2a15e908634cd8db6c75ea45d9e3bd567203eccf/spdnet/optimizer.py#L37-L39
Weight matrix (
p.data
) is set to 0 before computing the orthogonal projection with it's gradient, why is this the case?