Zhang Shudong

你好，我把content_loss设置为1，style_loss和tv_loss都设的0，训练时loss很大，数值从几万到几十万不等，最小的时候也是快2W，我想请问一下这样的情况正常吗？

Great implementation, it will be even more perfect if adding resume options. haha

I am a programming beginner. Could you please add some code comments for easy reading? Thanks!

Is there a way to use GPU to accelerate the calculation of Bayesian Gaussian process? The Bayesian optimization calculations in the original code are all done using the CPU, which...

Hi, thank you for release the source code. But I didn't find the train and test data of CLB attack. Could you upload the "clb-data"? Thank you very much!

Hi, where are the pretrained models? Can you provide? --t_weight1 pretrained_models/cifar10_resnet18_std_SA_best.pt \ --t_weight2 pretrained_models/cifar10_resnet18_adv_RA_best.pt

模型和数据集下载可以提供别的链接吗？

1

百度网盘下载太慢了，可以提供一下别的网盘下载链接吗？比如Google drive。