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

请问是否可以在pytorch上利用tensor进行操作呢 #1

Open
jhch1995 opened this issue Apr 7, 2023 · 1 comment
Open

请问是否可以在pytorch上利用tensor进行操作呢 #1

jhch1995 opened this issue Apr 7, 2023 · 1 comment
Labels
question Further information is requested

Comments

@jhch1995
Copy link

jhch1995 commented Apr 7, 2023

非常感谢作者的工作,我最近也想将orb的mathcing和feature extractor部分抽象出来,但是不知道怎么做。之前看到有些是通过pytorch自带的TORCH_LIBRARY,通过添加binding文件完成python和c++的数据交互,但是我发现对于orbfeature和matcher是有opencv的第三方库,因此没办法直接加载调用?想问下作者1. 这种思路是否可行? 2. 这份代码可以在外部配置orb feature提取的维度个数和层数吗?非常感谢!

@jhch1995 jhch1995 changed the title 请问如何在x86平台上进行编译呢 请问是否可以在pytorch上利用tensor进行操作呢 Apr 7, 2023
@mnixry mnixry added the question Further information is requested label Apr 7, 2023
@mnixry
Copy link
Owner

mnixry commented Apr 7, 2023

其实我是做工程的不是搞算法的,这些我也一知半解

  1. 这种思路是否可行?

大多数特征提取算法好像都非常依赖OpenCV来做一些底层运算,不依赖OpenCV直接用是不太可能的。但是你可以参考我的编译方法把OpenCV直接静态编译进去,或者在系统里面装好opencv-devel之类的东西做动态链接,这样还是可以用的

  1. 这份代码可以在外部配置orb feature提取的维度个数和层数吗?

支持的参数是这些:

def __init__(
self,
n_features: int = 1000,
scale_factor: float = 1.2,
n_levels: int = 8,
ini_th_fast: int = 20,
min_th_fast: int = 7,
interpolation: int = 1,
angle: bool = True,
) -> None:

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants