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 transformer on custom data configuration file is missing #257

Open
RAHULPRRAHUL opened this issue Sep 12, 2024 · 0 comments
Open

Comments

@RAHULPRRAHUL
Copy link

RAHULPRRAHUL commented Sep 12, 2024

Hi Team,

After training vqgan model on custom data as per below steps:
---Put your image files in a folder custom_data folder
---Create 2 text files a xx_train.txt and xx_test.txt that point to the files in your training and test set respectively
---Adapt configs/custom_vqgan.yaml to point to these 2 files
---Run python main.py --base configs/custom_vqgan.yaml -t True --gpus 0,1 to train on two GPUs.

We need to train transformer on custom data similar to to FFHQ+ CelebA-HQ data and To do so custom_transformer.yaml configuration file is not available to use.

python main.py --base configs/custom_transformer.yaml -t True --gpus 0,

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

1 participant