Nuoyan Zhou comments

Repositories
Issues
Comments

Results 3 comments of


                                            Nuoyan Zhou

Why does the first term in the loss_robust equal F.log_softmax(model(x_adv))?

> I think you mean that it is uesd to keep consistent with log_softmaxed vector which is in the cross entropy when optimizing. Thx a lot.

Error while trying to install nms-extension

Hello, thanks for your contribution! I have used torch1.9.0+cudnn11.4 to run > python exec.py --mode test --exp_source experiments/exp0 --exp_dir experiments/exp0 . But it brings a problem in nms.py in the...

Error while trying to install nms-extension

Thank you for your answer ！the cause of the previous problem is indeed related to the version of the torch, I have switched to the torch 1.7 to solve the...