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

model is taking long inference time after training, can i reduce it? have you any idea about it? #243

Open
rahulverma7788 opened this issue Dec 11, 2024 · 2 comments

Comments

@rahulverma7788
Copy link

The model is taking too much time, even for small images. How can I reduce this?

@Ucas-HaoranWei
Copy link
Owner

Do you mean the inference becomes slower than origin after your training?

@rahulverma7788
Copy link
Author

I have a table dataset in images, and when I am predicting image-to-LaTeX after training, it is taking a significant amount of time during inference. The second issue is that it is not predicting correctly for table images with row spans and column spans. It is unable to predict complex tables accurately. I am working on image-to-LaTeX predictions. Do you have any solution for complex images? I have tested your demo as well, and it is also taking a significant amount of time, even for simple images.

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