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

training issues #50

Open
shiyuancao opened this issue Jan 13, 2025 · 2 comments
Open

training issues #50

shiyuancao opened this issue Jan 13, 2025 · 2 comments

Comments

@shiyuancao
Copy link

I would like to ask you a few questions, thank you.1.Can I use my own dataset for training? If it's possible, do I just need to prepare my own dataset and modify the config, or are there other modifications required?
2.For a custom dataset, do I only need images and mask images?

@liuqk3
Copy link
Owner

liuqk3 commented Jan 14, 2025

@shiyuancao Thanks for your interest in our work. The answers to your questions are:

(1) You can train the model on your own dataset. You just need to prepare your data similar to the instructions in './readme/prepare_data.md'. Then you need to modify the 'dataloader' namespace in a config file.

(2) For a custom dataset, you only need images and mask images. In factor, the mask images are optional. The scripts can generate random masks with proper configurations.

@shiyuancao
Copy link
Author

Thank you for your reply. I wish you all the 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