holmesshuan / dynamic-network-surgery-caffe-reimplementation Goto Github PK

Hi Shuan,

Thanks for the great implementation.
I wonder what do you mean by 'didn't prune the bias term'.
Do you mean that you only use Wx (instead of Wx+b) to get the predictions and calculate the gradients?

For the pruned models of interests, should I use:

1. both new weights and (original) bias (which does not make sense).
2. only new weights (which may cause negative effects on the accuracy of original models because bia terms are omitted).

Thanks!

thanks for your work, do you have good result about convolution with sparsity 90%? or in your best result, what sparsity do your set?