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

For the StyleGan projectd, can we use pretrained model to resume training? #6

Open
Moamoza opened this issue Aug 9, 2020 · 1 comment

Comments

@Moamoza
Copy link

Moamoza commented Aug 9, 2020

No description provided.

@justinpinkney
Copy link
Owner

A pretrained model can be used to resume training, assuming you have got the same resolution and config etc. The original repository doesn't expose the option in the command line interface of run_training, but you can take a look at my fork (https://github.com/justinpinkney/stylegan2) which gives a --resume-pkl option at the command line. You can then run the training using something like:

python run_training.py --num-gpus=1 --metric=fid50k --data-dir=./dataset --config=config-f --dataset=my-dataset --min-h=4 --min-w=4 --res-log2=8 --result-dir="/content/drive/My Drive/somewhere" --resume-pkl="my-pretrained-mdoel.pkl"

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