-
Notifications
You must be signed in to change notification settings - Fork 134
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
A pytorch re-implementation of Structured Sparsity Learning #36
Comments
@zjykzj it's great that you are reimplementing it in pytorch after the old days of using caffe. |
把代码里少的那个根号加上重新传一遍吧。这个根号项就是group的全部精髓。要是没有这个根号把一个卷积核装进一个篮子里,这个pytorch版的代码只相当于手动计算了一下没有开平方的L2范数的惩罚项。丢掉了SSL的核心。 P.S. 又踩一坑 |
@caikengxiaonengshou 能否具体解释一下开根号前后的差异性?另外有相关的试验结果木有? |
@caikengxiaonengshou 嗯嗯 我先研究一下,相关的实验估计也得重做。欢迎PR |
hi @wenwei202 , Thank you for your sharing. Based on your paper, I implemented ZJCV/SSL using pytorch, including
train-prune-finetuing
for VGGNet and ResNetFrom the experimental results, we can see that the pruning effect is very good. Thank you again for SSL
The text was updated successfully, but these errors were encountered: