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

Enhanced C++ implementation #10

Closed
jesusmolrdv opened this issue Dec 20, 2022 · 3 comments
Closed

Enhanced C++ implementation #10

jesusmolrdv opened this issue Dec 20, 2022 · 3 comments

Comments

@jesusmolrdv
Copy link
Contributor

The NMS-Resampling method is very useful and easy to understand.

However, I have found that applying the official implementation in Python (see here) really slows the training process.

I have managed to implement it in C++ and integrate it in mmcv, which in my case gives between 3x and 4x speed-ups in the whole training process.

If you are interested, I can create a pull request with the code and the instructions to make use of this faster implementation. I think that this make help pepople using this useful tool.

Best regards!

@JialianW
Copy link
Owner

Thanks for your interests! Sure, it is great to integrate your better implementation into this repo if it has no compatibility issues. Thanks for your contribution! Did you integrate NMS sampling into official mmcv or mmdet repo?

@jesusmolrdv
Copy link
Contributor Author

I have not integrated in the official repositories, but it should be something easy to do.
Indeed, it could be interesting to try a pull request to those repositories in the future.

Regarding this repo, I would prepare a PR (inlcuding the code and instructions) in the following weeks and let you know once it's ready.

@JialianW
Copy link
Owner

Pull request merged and thus close the issue

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