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

Question about similarities computation #2

Open
hi-zhengcheng opened this issue Feb 27, 2020 · 0 comments
Open

Question about similarities computation #2

hi-zhengcheng opened this issue Feb 27, 2020 · 0 comments

Comments

@hi-zhengcheng
Copy link

hi-zhengcheng commented Feb 27, 2020

Thanks for your work, it gives me a good example on how to fuse local features. When reading through the source code, I just find following places where I can't understand clearly, hope you can help me out.

Code 1

alpha = w_1 + tf.transpose(w_2, [0, 2, 1])

When computing the similarities of neighbor points in local area, I think dot product is the right way just as the formula(3) in the paper. But here, it uses a plus operation instead. So would you please share some ideas or experience about why plus is used here ?

Code 2

energy_new=tf.tile(D, multiples=[1, 1,energy.shape[2]])-energy

I didn't get the idea why this subtraction is used here to compute the energy_new. Could you give some explanation on it ?

Thanks again for your nice work.

@hi-zhengcheng hi-zhengcheng changed the title Question about similarit Question about similarities computation Feb 27, 2020
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

2 participants
@hi-zhengcheng and others