8000 Ensembled models of CPN with different ground truth heatmaps. · Issue #60 · chenyilun95/tf-cpn · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Ensembled models of CPN with different ground truth heatmaps. #60

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

Open
7color94 opened this issue Oct 29, 2018 · 1 comment
Open

Ensembled models of CPN with different ground truth heatmaps. #60

7color94 opened this issue Oct 29, 2018 · 1 comment

Comments

@7color94
Copy link

Hello, in the Section 4.3 of your paper: "Without extra data involved in training, we achieve 72.1 AP using a single model of CPN and 73.0 using ensembled models of CPN with different ground truth heatmaps."
Here, what dose the ensembled models of CPN with different ground truth heatmaps mean?
Thanks for your reply.

@chenyilun95
Copy link
Owner

The ensemble strategy is using the average heatmap from different models as the final heatmap.

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
0