model architecture with unexpected changes after pruning

Open moonlightian opened this issue 3 years ago • 2 comments

model architecture seems to be changed with some unexpected modules after prunning, activation function has changed as well. How can I implement channel prunning without such changes carried? changed to

Aug 24 '22 13:08 moonlightian

Greetings, @moonlightian,

there is no logic in pruning algo which could possibly do such changes, could you please share a model for reproduction?

Aug 29 '22 14:08 daniil-lyakhov

@moonlightian , can you provide us a model example so that we could deeply look at your issue?

Sep 30 '22 10:09 MaximProshin

I close this issue as there is no feedback from the user for a long time period. Feel free to create a new issue, if it's still valid.

Jun 20 '23 08:06 MaximProshin