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

why we have num_grid=8 in LinearizedMutilSampler() class #3

Open
hassaanmahmood opened this issue Mar 14, 2020 · 2 comments
Open

why we have num_grid=8 in LinearizedMutilSampler() class #3

hassaanmahmood opened this issue Mar 14, 2020 · 2 comments

Comments

@hassaanmahmood
Copy link

hi,
what is the effect of num_grid? can you please explain what is this for?
@hassaanmahmood
Copy link
Author

when I reduce num_grid=2, I got more red arrows.

@jiangwei221
Copy link
Collaborator

Hi, num_grid represents the number of sample points used for linearization. as shown in Fig10(a) in the paper. We found 8 samples works stable. If you use 2 samples, I don't think the linearization process will give you a reasonable gradient.

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
2 participants
@hassaanmahmood @jiangwei221