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

t-sne #15

Open
fuchao01 opened this issue Aug 12, 2020 · 5 comments
Open

t-sne #15

fuchao01 opened this issue Aug 12, 2020 · 5 comments

Comments

@fuchao01
Copy link

In the paper, which layer of features is used in Figure 5 to make t-sne
@swathikirans
Copy link
Owner

The feature obtained after spatial average pooling in BNInception is used for the t-SNE.

@fuchao01
Copy link
Author

Is it the feature obtained from here (https://github.com/swathikirans/GSM/blob/master/models.py#L194)?

@swathikirans
Copy link
Owner

Yes, you are right.

@fuchao01
Copy link
Author

Thank you for your reply. But the shape I extracted from base_out is (8, 2048). How to make the spatial average pooling

@swathikirans
Copy link
Owner

The output from the backbone (8X2048) is temporal average pooled to obtain a vector (2048) and is used for t-SNE visualization.

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
@fuchao01 @swathikirans