Skip to content
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

Code for constructing datasets #6

Open
ZuowenWang0000 opened this issue Dec 20, 2019 · 5 comments
Open

Code for constructing datasets #6

ZuowenWang0000 opened this issue Dec 20, 2019 · 5 comments

Comments

@ZuowenWang0000
Copy link

Hello, Could you please also release the code for constructing the robust and non-robust datasets? Specifically the code for C.4 section and C.5 section in the appendix of the paper.
Thanks!

@yw981
Copy link

yw981 commented Feb 1, 2021

+1
Thx

1 similar comment
@wushan0125
Copy link

+1
Thx

@zhiyugege
Copy link

+1
Thx

https://github.com/MadryLab/robust_representations/blob/master/image_inversion.ipynb [for constructing robust datasets]

@ahadda5
Copy link

ahadda5 commented Nov 18, 2021

+1
Thx

https://github.com/MadryLab/robust_representations/blob/master/image_inversion.ipynb [for constructing robust datasets]

Not sure that is the correct code requested.
This notebook just applies a custom loss, scales the images for inversion and applies the adv-trained model to generate the inversion. What is important are the last two steps (argmin and Union till the whole Robust set is constructed),
image

@ahadda5
Copy link

ahadda5 commented Nov 20, 2021

Nevermind, it is answered here

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants