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 implement 92.9% OA? #65

Open
357998846 opened this issue Jun 20, 2020 · 4 comments
Open

How to implement 92.9% OA? #65

357998846 opened this issue Jun 20, 2020 · 4 comments

Comments

@357998846
Copy link

Hello, the OA of modelnet40 is 91.7% or 92.2%?
How is 92.9% in the paper realistic?
My own recurrence is only 91.7%.
How to implement 92.9% OA?
Thank you very much.

@guochengqian
Copy link

I confirm it is easy to achieve the 92.9 OA using their code (results reported using the best model).
Exp show that you can achieve even better results (like 93.1) using the same number epochs as KPConv (400 epochs) instead of 250 epochs.

@sheshap
Copy link

sheshap commented Jul 9, 2021

I got 92.4%

@sunhufei
Copy link

sunhufei commented Dec 5, 2021

Train 26, loss: 3.676545, train acc: 0.075407, train avg acc: 0.030953
Test 26, loss: 3.640235, test acc: 0.042139, test avg acc: 0.026000
Train 27, loss: 3.671733, train acc: 0.072358, train avg acc: 0.030758
Test 27, loss: 3.637559, test acc: 0.044976, test avg acc: 0.027750
Train 28, loss: 3.675745, train acc: 0.073272, train avg acc: 0.031713
Test 28, loss: 3.636188, test acc: 0.068071, test avg acc: 0.042000
Train 29, loss: 3.691305, train acc: 0.071545, train avg acc: 0.030454

@sunhufei
Copy link

sunhufei commented Dec 5, 2021

Why is the accuracy rate so low? #81

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

4 participants