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

How to train my own dataset #181

Open
littlebig-balala opened this issue Mar 6, 2024 · 6 comments
Open

How to train my own dataset #181

littlebig-balala opened this issue Mar 6, 2024 · 6 comments

Comments

@littlebig-balala
Copy link

Dear author:
I want to train a meteorological type dataset, I don't know how to use RAFT to train my own dataset, do I need to make the optical flow groudtruth of my dataset?

@Guo-1212
Copy link

Have you found a way to train your own dataset, and can you let me know?

@littlebig-balala
Copy link
Author

The pixels moving back and forth in the meteorological data can vary somewhat in value, so this resulted in not a good optical flow map, so I used the pre-trained model to generate the optical flow data.

1 similar comment
@littlebig-balala
Copy link
Author

The pixels moving back and forth in the meteorological data can vary somewhat in value, so this resulted in not a good optical flow map, so I used the pre-trained model to generate the optical flow data.

@Guo-1212
Copy link

Where did you find the pre-trained model?

@littlebig-balala
Copy link
Author

You can take a closer look at the author's project, which has a downloadable address

@jiangguangan
Copy link

How to train your own dataset?Pls did anyone fix this

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