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.

Sign up for GitHub

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

Jump to bottom

Training model #1

Open
WJinhai opened this issue Dec 9, 2019 · 6 comments
Open

Training model #1

WJinhai opened this issue Dec 9, 2019 · 6 comments

Comments

@WJinhai
Copy link

WJinhai commented Dec 9, 2019

The trained model can be public? Is it consistent with the results in the paper?
@SURFZJY
Copy link
Owner

SURFZJY commented Dec 10, 2019 •
edited
Loading

The sufflenetv2 model trianed on ic13 and15 has been released, but for some implementation details are different, the results are not as good as the results in the paper. I will continue to update this project with the reference to the official implementation.

@WJinhai
Copy link
Author

WJinhai commented Dec 16, 2019

Does this only work on GPU?

@SURFZJY
Copy link
Owner

SURFZJY commented Dec 16, 2019

It can work on CPU, by setting the gpu_id=None and uncommenting torch.cuda.synchronize(self.device).

@WJinhai
Copy link
Author

WJinhai commented Dec 17, 2019

This result looks not as good as in the paper

@SURFZJY
Copy link
Owner

SURFZJY commented Dec 17, 2019

yes, i am working hard to improve the performance. I will release a better version some days later.

@ghost
Copy link

ghost commented Mar 19, 2020

@SURFZJY Did the results got better?
whats the result on icdar15

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@SURFZJY @WJinhai