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

请问keypoint信息怎么单独保存呀 #66

Open
yanheng01 opened this issue Oct 8, 2022 · 4 comments
Open

请问keypoint信息怎么单独保存呀 #66

yanheng01 opened this issue Oct 8, 2022 · 4 comments

Comments

@yanheng01
Copy link

大佬您好,请问检测到的关键点怎么单独保存呀,关键点只出现在keypoint_detecotr.py中吗,我想计算一下压缩率嘞

@sky24h
Copy link

sky24h commented Oct 10, 2022

如果你想保存的是kp_driving['value'], 它只是一个[n, 15, 3]的tensor,
你可以保存为.pt或者转换成np.array -> .npy

@yanheng01
Copy link
Author

yanheng01 commented Oct 14, 2022

如果你想保存的是kp_driving['value'], 它只是一个[n, 15, 3]的tensor, 你可以保存为.pt或者转换成np.array -> .npy

你好呀,感谢解答!就是论文中说的是keypoint传递的信息,每次是3K + 6个字节(以float16存储)。K是keypoint的点数,6是旋转和迁移的大小。我看了kp_driving['value']是一个3K的tensor,这里传递的旋转和迁移量的6在哪里呀。主要是这里不明白

@sky24h
Copy link

sky24h commented Oct 14, 2022

如果你想保存的是kp_driving['value'], 它只是一个[n, 15, 3]的tensor, 你可以保存为.pt或者转换成np.array -> .npy

你好呀,感谢解答!就是论文中说的是keypoint传递的信息,每次是3K + 6个字节(以float16存储)。K是keypoint的点数,6是旋转和迁移的大小。我看了kp_driving['value']是一个3K的tensor,这里传递的旋转和迁移量的6在哪里呀。主要是这里不明白

不好意思, 这我就不太清楚了, 以下按照我理解的范围来回答.
首先, 要向repo的作者确认, 是否严格按照论文来写的计算, 因为此repo的作者并非论文作者, 也许有出入.
其次, 有关rotation和translation的计算应该在这附近几行, 但我得不出对此问题确切的结论.

rot_mat = get_rotation_matrix(yaw, pitch, roll)

@yanheng01
Copy link
Author

好滴,非常感谢您的解答!

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