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.

Sign up for GitHub

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

Jump to bottom

Should in1.clamp_(0, 1.0) be in1.clamp_(0, 255.0) ? #5

Open
psu1 opened this issue Jan 9, 2020 · 3 comments
Open

Should in1.clamp_(0, 1.0) be in1.clamp_(0, 255.0) ? #5

psu1 opened this issue Jan 9, 2020 · 3 comments

Comments

@psu1
Copy link

psu1 commented Jan 9, 2020

FreeAdversarialTraining/main_free.py

Line 183 in d707740

in1.clamp_(0, 1.0)

is in1.clamp_(0, 1.0) should be in1.clamp_(0, 255.0) ? As "in1" has not been normalized yet.
@anonymous530
Copy link

FreeAdversarialTraining/main_free.py

Line 183 in d707740

in1.clamp_(0, 1.0)

is in1.clamp_(0, 1.0) should be in1.clamp_(0, 255.0) ? As "in1" has not been normalized yet.

Yeah, I also have the same question. There may be similar question in validate_pgd function?

@a-name-not-used
Copy link

a-name-not-used commented Mar 8, 2020 •
edited
Loading

The pytorch transform ToTensor() applied on image datasets will output tensors in [0., 1.0].

@anonymous530
Copy link

The pytorch transform ToTensor() applied on image datasets will output tensors in [0., 1.0].

Yes, you're right.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@anonymous530 @psu1 @a-name-not-used