zorrocai

In my pytorch implementation, and just train on MNIST dataset.

I found that the wrong position of line S_W += lambda*I caused the problem. I added this line before S_B=S_T - S_W. After I moved S_W +=lambda*I behind S_B=S_T -...

@tchaton I have written the deeplda in pytorch.But it seems that it doesn't work well too. Insteading of the loss exploding problem in your tensorflow version, the training problem in...

Thanks. there are so many hard obstacles in the deeplda model...

@tchaton Of course, sending pytorch code to your email [email protected].

Hi, @tchaton Yeah, for symmetric matrix,eigenvalues are the same as singular values.  you can see it in matrix cookbook for detail. [https://www.math.uwaterloo.ca/~hwolkowi/matrixcookbook.pdf](url) And I found that I have made...

@RoyiAvital Thanks