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

How to get the image result of Visualization of attention? #5

Open
ZJU-PLP opened this issue Jul 9, 2022 · 2 comments
Open

How to get the image result of Visualization of attention? #5

ZJU-PLP opened this issue Jul 9, 2022 · 2 comments

Comments

@ZJU-PLP
Copy link

ZJU-PLP commented Jul 9, 2022

Hi, Zi Jian:

Thanks for sharing so nice work.
Could you mind sharing the method to reproduce your results for Visualization of attention? Just as presented by Fig5. and Fig6. from your paper?

@yewzijian
Copy link
Owner

Fig 5 does not show the attention but visualizes the locations of the keypoints and their corresponding locations. The network outputs all of these quantities so it should be quite easy to visualize them, and I have already provided a function to draw them here.

The attention weights are shown in Fig 6. For this, you need to first retrieve the attention weights, which can be obtained via the provided get_attentions() function here. After that, you can just colorize the point cloud using the weights of a particular point.

@ZJU-PLP
Copy link
Author

ZJU-PLP commented Jul 10, 2022

Ok, thanks for your patient reply. I will have a try.

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