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

About how to prediction #322

Open
cxy99zyr opened this issue May 14, 2024 · 3 comments
Open

About how to prediction #322

cxy99zyr opened this issue May 14, 2024 · 3 comments

Comments

@cxy99zyr
Copy link

Hello, thank you very much for contributing to this project.I encountered a question during the study process, I hope you can answer it, appreciate it!
How can I use the weights of the trained superpoint to make predictions on my own data and output the prediction results?

@cxy99zyr
Copy link
Author

@rpautrat hope you can see my problem soon

@rpautrat
Copy link
Owner

Hi, you can take the example of this script and adapt it to your own images for example.

@cxy99zyr
Copy link
Author

Thank you very much for taking the time to answer my question, I see that you proposed a part of the code about loading the weight file and making predictions, which helped me solve a large part of the problem, thanks again。
image
I think I also need some precise guidance from you, the code you gave is modular, the implementation of MagicPoint is based on basemodel.py and other files,like this pic:
image

I wonder if I can create my own MagicPoint model, and apply the weights of MagicPoint obtained by the method you gave to the following model, the following model is what I wrote:

image

Or can I generate a model in pytorch format based on the superpoint_pytorch.py file you gave to use:
image
This question has been bothering me for a long time, I feel like I've been busy every day but haven't been able to solve this problem, I may not be able to do it enough, thank you for your patience!

Hi, you can take the example of this script and adapt it to your own images for example.

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