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

How to train on my own dataset? #3

Closed
Badw0lf613 opened this issue Aug 28, 2023 · 3 comments
Closed

How to train on my own dataset? #3

Badw0lf613 opened this issue Aug 28, 2023 · 3 comments

Comments

@Badw0lf613
Copy link

Sorry to bother. I'm trying to train DDColor on my own dataset. Is there any training scripts? By the way, how to prepare and organize my dataset?

@Badw0lf613
Copy link
Author

@piddnad

@Badw0lf613
Copy link
Author

I see the training scripts and files, that is basicsr/train.py.

@piddnad
Copy link
Owner

piddnad commented Aug 30, 2023

Sure! It's easy to train DDColor on your own dataset.

First, you need to organize your dataset by placing the images in a folder, and then use data_list/get_meta_file.py to generate a datalist file.

Next, you need to modify the path to the training dataset's metadata file in the training config.

Finally, as you mentioned, you can use basicsr/train.py for training. The command format can be found in scripts/train.sh.

Hope this answer has addressed your question.

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