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

hope to refer to pure pytorch Version of the source code #1

Open
westream opened this issue Jun 23, 2020 · 1 comment
Open

hope to refer to pure pytorch Version of the source code #1

westream opened this issue Jun 23, 2020 · 1 comment

Comments

@westream
Copy link

Hello, we are preparing for the work of cvpr2020, I hope you can quote your work, but the edflow library you use, although it runs very well, its debugging and use is still very difficult for me, I still hope to refer to pure pytorch Version of the source code

@pesser
Copy link
Contributor

pesser commented Jul 1, 2020

Hi,
Since we are using edflow extensively for our projects, we cannot provide a standalone version. However, if you are encountering a specific problem with it, we'd be happy to help! In any case, edflow mostly handles the necessary logistics of logging, parsing configs, loading and iterating over batches of data etc. The model and loss classes can be used independent of edflow. You would then only need to write your own dataloader and adapt the logic of the iterator class in your own loop over the batches.
Best

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