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

visualize_pose #53

Open
evanismli opened this issue Jan 16, 2024 · 3 comments
Open

visualize_pose #53

evanismli opened this issue Jan 16, 2024 · 3 comments

Comments

@evanismli
Copy link

vo
这是我按照ICRA权重得到的可视化轨迹,跟您的差距较大,请问还需要添加别的设置吗?其次我也按照链接https://github.com/ShuweiShao/AF-SfMLearner/issues/8在训练时将F. interpolate和F. grid_sample后都加个align_corners=True进行了训练效果依旧不好。希望得到您的回复,谢谢!

@ShuweiShao
Copy link
Owner

hi,ICRA的论文中并没有进行位姿的可视化,请使用MIA期刊论文的权重可视化轨迹。

@evanismli
Copy link
Author

hi,ICRA的论文中并没有进行位姿的可视化,请使用MIA期刊论文的权重可视化轨迹。

您好,我使用MIA权重可视化的效果为
image
我在evaluate_pose中pred_poses = np.concatenate(pred_poses)后添加如下
np.savez_compressed('./splits/endovis/val.npz', data=np.array(pred_poses))保存预测pose权重,然后在可视化位姿轨迹中的效果如上图,依旧存在差距

@ShuweiShao
Copy link
Owner

请问是直接加载的模型权重可视化的嘛?感觉像是某个操作出现了问题。

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