jnoylinc
jnoylinc
> Thanks a lot for answering! > > I agree that a sequence of linear convolution layers can be collapsed into a single one, but is there a simple way...
> > @jnoylinc `post_process_k` does two things. It first zeros out negligible values in the extracted kernel, which, if anything, only results in the kernel further deviating from the generator....
> Hi @1214635079, I haven't. I might be wrong here but I do not think the extracted kernel is the same as the learned generator. > > Hi @sefibk, have...
there is some bugs in your code,be careful, my code is deleted,I am soory