search

xavihart / Diff-PGD

[NeurIPS'2023] Official Code Repo:Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability
79 stars 6 forks source link

Some question #5

Closed Raineasy closed 9 months ago

Raineasy commented 9 months ago

Very glad you shared your code! I'm sorry to bother you, but is the code incomplete, after I installed the corresponding environment as well as the data path, there is still a part of the unknown error, such as in the denoise.py file from improved_diffusion.script_util import ... this improved_diffusion part and also the create_argparser() in the same file, and InputCenterLayer() in the dataset.py doesn't seem to appear in the whole code. I run the code on my win10 system. I'm still a novice when it comes to coding, so if you know how to fix my problem I'd appreciate it! :)

xavihart commented 9 months ago

Yes, we did not include experiments on CIFAR-10 so the code may not work very well. You can try the diffusion model on ImageNet using our code, which is based on guided diffusion instead of improved diffusion.

Raineasy commented 9 months ago

Thank you for your reply！：）