Yijiang.Kris.Liu issues

Repositories
Issues
Comments

Results 1 issues of


                                            Yijiang.Kris.Liu

How does torch.clamp() reviving dead weights?

Appreciate your excellent work! I look up the code in **binarized_modules.py** and find that **torch.clamp()** is applied to constrain weights within ±Q_tau. In backwards, this approach stops "dead weights"(which >=Q_tau...