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

Meaning of the code and it's significance is not explained in the paper #3

Open
tmondalvogo opened this issue Dec 15, 2023 · 0 comments

Comments

@tmondalvogo
Copy link

Hello Dear Author,
Thank you for providing the code. This is helpful to understand the work and to evaluate it. I am having problems in understanding the the functionality of these lines of code :

From the line :

inter01 = np.intersect1d(lookup_list[0], lookup_list[1])

To the line :

new_lookup_list[2, remain_ind] = utils.to_torch(non_inter21)

I can understand what operation you are doing in these lines but I can't understand why you are doing these operations and what is the purpose of it

The lookup_list is a 3 x 4 matrix. What is the significance of these 3 rows? that means why are you randomly collecting the 4 warped key points, 3 times, and then after obtaining these 3 vectors (each vector is with 4 values), why are you doing such operations in lines 164 - 176 ?
Such operations or technique is nowhere mentioned in the paper and I am not able to understand why you do it ?

Thank you in advance for your reply

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

1 participant