Mauricio Romero
Mauricio Romero
I've found the answer in this post: https://github.com/spatialaudio/python-sounddevice/issues/74#issuecomment-296383036 Thanks a lot!!!!!
I removed the file "anaconda3/lib/libstdc++.so.6" and replaced with "/usr/lib/x86_64-linux-gnu/libstdc++.so.6". Yes, I think is the best option too. I will do it soon.
Hi sjp611, a practical solution is adding a small constant (1e-10) to the logarithm argument: log(p + 1e-10). It is not the best option but at least is numerically stable.
> > > > Hi sjp611, > > a practical solution is adding a small constant (1e-10) to the logarithm argument: log(p + 1e-10). It is not the best option...
> > > > > Hi, > > > I met another problem when I tried to train the model. I set the `mem_dim = 2k` and reset the params...