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: in demo/cat fps nums is 9, not 8 default, in cat_points_3d.txt #16

Closed
zkailinzhang opened this issue Apr 25, 2019 · 4 comments

Comments

@zkailinzhang
Copy link

-2.315007150173187256e-04 2.015497535467147827e-03 1.328250020742416382e-02

and the trained model you supply, the number fps is 9fps,????
but ,in your literature compute 8fps by deflault

@zkailinzhang
Copy link
Author

zkailinzhang commented Apr 25, 2019

when i run demo.py, change vote_num=9, in line 29, error occur

RuntimeError: Error(s) in loading state_dict for Resnet18_8s:
        size mismatch for convraw.3.weight: copying a param of torch.Size([18, 32, 1, 1]) from checkpoint, where the shape is torch.Size([20, 32, 1, 1]) in current model.
        size mismatch for convraw.3.bias: copying a param of torch.Size([18]) from checkpoint, where the shape is torch.Size([20]) in current model.
Terminated

@zkailinzhang zkailinzhang changed the title question: in demo/cat fps nums is 9, not 8 default, in cat_points_3d.txt Question: in demo/cat fps nums is 9, not 8 default, in cat_points_3d.txt Apr 25, 2019
@zkailinzhang
Copy link
Author

zkailinzhang commented Apr 25, 2019

and the fps result ,fartherst data domain different,
in pvnet/data/demo/cat_points_3d.txt
2.178440988063812256e-02 -5.869993939995765686e-02 -4.146179929375648499e-02

in pvnet/data/LINEMOD/cat/farthest.txt
0.021784409880638123 -0.05869993939995766 -0.041461799293756485

@liuyuan-pal
Copy link

The default keypoints are 8 points sampled on the surface by FPS and the center of the object.

@pengsida
Copy link
Member

image

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

3 participants