Implement SSI with Toeplitz
weidler opened this issue · comments
Toeplitz proved to be a lot faster, so we should reimplement Toeplitz (and Recurrent?) using it.
Done but could also entirely replace old version when we have zero padding as option.
Biologically Inspired Lateral Connectivity in Convoluiontal Neural Networks
weidler opened this issue · comments
Toeplitz proved to be a lot faster, so we should reimplement Toeplitz (and Recurrent?) using it.
Done but could also entirely replace old version when we have zero padding as option.