question in Backward code about dynamic-network-surgery HOT 4 CLOSED

You are right, @flymark2010 . That might be some testing code that I forgot to comment. Better comment those lines for higher efficiency.

from dynamic-network-surgery.

@yiwenguo Ok. Thanks !

from dynamic-network-surgery.

@yiwenguo I also have a question about this part. According to your paper, weight_diff[k] and bias_diff[k] are supposed to be updated according to weightMask[k] and biasMask[k] . So is it right to move line 13 - 15 after line 18, and move line 23 - 25 after line 31? Or just remove line 13 - 15 and 23 - 25?
Thank you very much!

from dynamic-network-surgery.

@kai-xie I think if we use mask computed diffs(just as moving codes as you asked),weights and biases masked wil never be alive.So we pass errors to udpate those masked parameters to see if they can come alive although it's not correct in mathematics.

from dynamic-network-surgery.