I am using gluon now.
for a brief example, AntisymmetricRNN
That network seems difficult for me to reproduce, mxnet has no “Antisymmetric matrix” now, but I found it is much easier to get an antisymmetric weight matrix by:
x=[i for i in net.collect('the weight I want').values()]
x._data could be what I want.
BUT… the question is, I cannot using
gluon.Trainer will raise an exception.
My solution is using
x._data+=... or something else, much ugly than what I expected.
Is there any good solutions to manipulate parameters directly?