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

Switching to saving samples and checkpoints based on kimgs #21

Merged
merged 13 commits into from Aug 16, 2021
Merged

Conversation

duskvirkus
Copy link
Owner

  • fixed tensor device bug in EqualLinear.forward() method
  • added 3 training integration tests (from scratch, ffhq, and custom resume)
  • switched to using wget with digital ocean hosted pretrained models
  • moved ci files out of repository
  • added create_sample_grid_vectors.py script
  • added KimgSaverCallback which saves samples and checkpoints based on kimgs
  • removed --n_samples argument
  • added --save_sample_every_kimgs, --save_checkpoint_every_kimgs, --start_kimg_count, --stop_training_at_kimgs and --sample_grid arguments

@duskvirkus duskvirkus added this to the v1.0.0 milestone Aug 9, 2021
@duskvirkus duskvirkus merged commit acf8245 into devel Aug 16, 2021
@duskvirkus duskvirkus deleted the kimgs branch August 16, 2021 04:14
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

Successfully merging this pull request may close these issues.

None yet

1 participant